diff --git a/data/benchmarks.json b/data/benchmarks.json
index b89fad043205746a1fe3c3d97fb375c96123e519..9571727dfcd0f5a5c4445684a0e339ea8b9100b5 100644
--- a/data/benchmarks.json
+++ b/data/benchmarks.json
@@ -57,7 +57,7 @@
   },
   {
     "benchmark": "reward-bench",
-    "model_count": 328
+    "model_count": 327
   },
   {
     "benchmark": "swe-bench",
diff --git a/data/benchmarks/appworld_test_normal.json b/data/benchmarks/appworld_test_normal.json
index 27bfa4d8d1ae3df861f951b1a84e2236e37e45c3..df9e46daf5dd19a85e092a1af20da57930852dac 100644
--- a/data/benchmarks/appworld_test_normal.json
+++ b/data/benchmarks/appworld_test_normal.json
@@ -5,7 +5,7 @@
       "name": "claude-opus-4-5",
       "developer": "Anthropic",
       "scores": {
-        "appworld/test_normal": 0.7
+        "appworld/test_normal": 0.64
       }
     },
     {
@@ -13,7 +13,7 @@
       "name": "gemini-3-pro-preview",
       "developer": "Google",
       "scores": {
-        "appworld/test_normal": 0.55
+        "appworld/test_normal": 0.36
       }
     },
     {
diff --git a/data/benchmarks/browsecompplus.json b/data/benchmarks/browsecompplus.json
index fa5cad4bfa9a7ba3be365ad38a5955a6ca39cc9b..34f802eb19d92b7a54aef0531fdda5bcd88b81cf 100644
--- a/data/benchmarks/browsecompplus.json
+++ b/data/benchmarks/browsecompplus.json
@@ -13,7 +13,7 @@
       "name": "gemini-3-pro-preview",
       "developer": "Google",
       "scores": {
-        "browsecompplus": 0.3333
+        "browsecompplus": 0.48
       }
     },
     {
@@ -21,7 +21,7 @@
       "name": "gpt-5.2-2025-12-11",
       "developer": "OpenAI",
       "scores": {
-        "browsecompplus": 0.43
+        "browsecompplus": 0.26
       }
     }
   ]
diff --git a/data/benchmarks/hfopenllm_v2.json b/data/benchmarks/hfopenllm_v2.json
index caf5db92e1eb1042b92e8b5d4090c0a48c4f57e2..69cfd9d7907951c5385529f14c35f4b9a0820d64 100644
--- a/data/benchmarks/hfopenllm_v2.json
+++ b/data/benchmarks/hfopenllm_v2.json
@@ -1747,12 +1747,12 @@
       "name": "NeuralDaredevil-SuperNova-Lite-7B-DARETIES-abliterated",
       "developer": "BoltMonkey",
       "scores": {
-        "IFEval": 0.459,
-        "BBH": 0.5185,
-        "MATH Level 5": 0.0937,
-        "GPQA": 0.2743,
-        "MUSR": 0.4083,
-        "MMLU-PRO": 0.3631
+        "IFEval": 0.7999,
+        "BBH": 0.5152,
+        "MATH Level 5": 0.1193,
+        "GPQA": 0.281,
+        "MUSR": 0.4019,
+        "MMLU-PRO": 0.3733
       }
     },
     {
@@ -2176,12 +2176,12 @@
       "name": "LION-Gemma-2b-dpo-v1.0",
       "developer": "Columbia-NLP",
       "scores": {
-        "IFEval": 0.3102,
-        "BBH": 0.3881,
-        "MATH Level 5": 0.0536,
-        "GPQA": 0.2534,
-        "MUSR": 0.4081,
-        "MMLU-PRO": 0.1665
+        "IFEval": 0.3278,
+        "BBH": 0.392,
+        "MATH Level 5": 0.0431,
+        "GPQA": 0.2492,
+        "MUSR": 0.412,
+        "MMLU-PRO": 0.1666
       }
     },
     {
@@ -3229,12 +3229,12 @@
       "name": "PathfinderAI",
       "developer": "Daemontatox",
       "scores": {
-        "IFEval": 0.4855,
-        "BBH": 0.6627,
-        "MATH Level 5": 0.4841,
-        "GPQA": 0.3096,
-        "MUSR": 0.4256,
-        "MMLU-PRO": 0.5542
+        "IFEval": 0.3745,
+        "BBH": 0.6668,
+        "MATH Level 5": 0.4758,
+        "GPQA": 0.3943,
+        "MUSR": 0.4858,
+        "MMLU-PRO": 0.5593
       }
     },
     {
@@ -4009,12 +4009,12 @@
       "name": "Llama-3.2-1B-SPIN-iter0",
       "developer": "DavieLion",
       "scores": {
-        "IFEval": 0.1507,
-        "BBH": 0.293,
-        "MATH Level 5": 0.0,
-        "GPQA": 0.2534,
+        "IFEval": 0.1549,
+        "BBH": 0.2937,
+        "MATH Level 5": 0.006,
+        "GPQA": 0.2576,
         "MUSR": 0.3565,
-        "MMLU-PRO": 0.1125
+        "MMLU-PRO": 0.1128
       }
     },
     {
@@ -4048,12 +4048,12 @@
       "name": "Llama-3.2-1B-SPIN-iter3",
       "developer": "DavieLion",
       "scores": {
-        "IFEval": 0.1336,
-        "BBH": 0.2975,
-        "MATH Level 5": 0.0068,
-        "GPQA": 0.2534,
-        "MUSR": 0.35,
-        "MMLU-PRO": 0.1128
+        "IFEval": 0.1324,
+        "BBH": 0.2972,
+        "MATH Level 5": 0.0,
+        "GPQA": 0.2643,
+        "MUSR": 0.3527,
+        "MMLU-PRO": 0.1129
       }
     },
     {
@@ -4321,12 +4321,12 @@
       "name": "Llama-3.1-8b-ITA",
       "developer": "DeepMount00",
       "scores": {
-        "IFEval": 0.5365,
-        "BBH": 0.517,
-        "MATH Level 5": 0.1707,
-        "GPQA": 0.3062,
-        "MUSR": 0.4487,
-        "MMLU-PRO": 0.396
+        "IFEval": 0.7917,
+        "BBH": 0.5109,
+        "MATH Level 5": 0.1088,
+        "GPQA": 0.2878,
+        "MUSR": 0.4136,
+        "MMLU-PRO": 0.3876
       }
     },
     {
@@ -7025,12 +7025,12 @@
       "name": "Fireball-Meta-Llama-3.1-8B-Instruct-Agent-0.003-128K-code-ds-auto",
       "developer": "EpistemeAI",
       "scores": {
-        "IFEval": 0.7305,
-        "BBH": 0.4649,
-        "MATH Level 5": 0.1397,
-        "GPQA": 0.2659,
-        "MUSR": 0.3209,
-        "MMLU-PRO": 0.348
+        "IFEval": 0.7207,
+        "BBH": 0.461,
+        "MATH Level 5": 0.1314,
+        "GPQA": 0.2701,
+        "MUSR": 0.3432,
+        "MMLU-PRO": 0.3354
       }
     },
     {
@@ -7675,12 +7675,12 @@
       "name": "Herplete-LLM-Llama-3.1-8b",
       "developer": "Etherll",
       "scores": {
-        "IFEval": 0.6106,
-        "BBH": 0.5347,
-        "MATH Level 5": 0.1548,
-        "GPQA": 0.3146,
-        "MUSR": 0.3991,
-        "MMLU-PRO": 0.3752
+        "IFEval": 0.4672,
+        "BBH": 0.5013,
+        "MATH Level 5": 0.0279,
+        "GPQA": 0.2861,
+        "MUSR": 0.386,
+        "MMLU-PRO": 0.3482
       }
     },
     {
@@ -8455,12 +8455,12 @@
       "name": "Josiefied-Qwen2.5-0.5B-Instruct-abliterated-v1",
       "developer": "Goekdeniz-Guelmez",
       "scores": {
-        "IFEval": 0.3472,
-        "BBH": 0.3268,
-        "MATH Level 5": 0.0891,
-        "GPQA": 0.2517,
-        "MUSR": 0.3262,
-        "MMLU-PRO": 0.1641
+        "IFEval": 0.3417,
+        "BBH": 0.3292,
+        "MATH Level 5": 0.0023,
+        "GPQA": 0.2576,
+        "MUSR": 0.3249,
+        "MMLU-PRO": 0.1638
       }
     },
     {
@@ -8702,12 +8702,12 @@
       "name": "Nature-Reason-1.2-reallysmall",
       "developer": "GuilhermeNaturaUmana",
       "scores": {
-        "IFEval": 0.4985,
-        "BBH": 0.5645,
-        "MATH Level 5": 0.2576,
-        "GPQA": 0.3003,
-        "MUSR": 0.4373,
-        "MMLU-PRO": 0.4429
+        "IFEval": 0.4791,
+        "BBH": 0.5649,
+        "MATH Level 5": 0.25,
+        "GPQA": 0.2995,
+        "MUSR": 0.4439,
+        "MMLU-PRO": 0.4408
       }
     },
     {
@@ -9170,12 +9170,12 @@
       "name": "SmolLM2-360M-Instruct",
       "developer": "HuggingFaceTB",
       "scores": {
-        "IFEval": 0.083,
-        "BBH": 0.3053,
-        "MATH Level 5": 0.0083,
-        "GPQA": 0.2651,
-        "MUSR": 0.3423,
-        "MMLU-PRO": 0.1126
+        "IFEval": 0.3842,
+        "BBH": 0.3144,
+        "MATH Level 5": 0.0151,
+        "GPQA": 0.255,
+        "MUSR": 0.3461,
+        "MMLU-PRO": 0.1117
       }
     },
     {
@@ -13031,12 +13031,12 @@
       "name": "SpydazWeb_AI_HumanAI_012_INSTRUCT_IA",
       "developer": "LeroyDyer",
       "scores": {
-        "IFEval": 0.3036,
-        "BBH": 0.4575,
+        "IFEval": 0.3066,
+        "BBH": 0.4577,
         "MATH Level 5": 0.0446,
-        "GPQA": 0.3012,
-        "MUSR": 0.4253,
-        "MMLU-PRO": 0.2329
+        "GPQA": 0.2995,
+        "MUSR": 0.4254,
+        "MMLU-PRO": 0.2318
       }
     },
     {
@@ -13057,12 +13057,12 @@
       "name": "SpydazWeb_AI_HumanAI_012_INSTRUCT_XA",
       "developer": "LeroyDyer",
       "scores": {
-        "IFEval": 0.3798,
-        "BBH": 0.4483,
-        "MATH Level 5": 0.04,
-        "GPQA": 0.3129,
-        "MUSR": 0.4148,
-        "MMLU-PRO": 0.2389
+        "IFEval": 0.3579,
+        "BBH": 0.4477,
+        "MATH Level 5": 0.0423,
+        "GPQA": 0.3096,
+        "MUSR": 0.4134,
+        "MMLU-PRO": 0.2376
       }
     },
     {
@@ -14305,12 +14305,12 @@
       "name": "Llama-3-8B-Magpie-Align-v0.1",
       "developer": "Magpie-Align",
       "scores": {
-        "IFEval": 0.4027,
-        "BBH": 0.4789,
-        "MATH Level 5": 0.0461,
-        "GPQA": 0.2768,
-        "MUSR": 0.3087,
-        "MMLU-PRO": 0.3001
+        "IFEval": 0.4118,
+        "BBH": 0.4811,
+        "MATH Level 5": 0.034,
+        "GPQA": 0.2752,
+        "MUSR": 0.3047,
+        "MMLU-PRO": 0.3006
       }
     },
     {
@@ -16874,6 +16874,19 @@
         "MMLU-PRO": 0.232
       }
     },
+    {
+      "model_id": "NousResearch/Yarn-Llama-2-7b-128k",
+      "name": "Yarn-Llama-2-7b-128k",
+      "developer": "NousResearch",
+      "scores": {
+        "IFEval": 0.1485,
+        "BBH": 0.3248,
+        "MATH Level 5": 0.0151,
+        "GPQA": 0.2601,
+        "MUSR": 0.3967,
+        "MMLU-PRO": 0.1791
+      }
+    },
     {
       "model_id": "NousResearch/Yarn-Llama-2-7b-64k",
       "name": "Yarn-Llama-2-7b-64k",
@@ -18128,11 +18141,11 @@
       "developer": "PrimeIntellect",
       "scores": {
         "IFEval": 0.1757,
-        "BBH": 0.274,
+        "BBH": 0.276,
         "MATH Level 5": 0.0,
-        "GPQA": 0.25,
-        "MUSR": 0.3753,
-        "MMLU-PRO": 0.112
+        "GPQA": 0.2534,
+        "MUSR": 0.3339,
+        "MMLU-PRO": 0.1123
       }
     },
     {
@@ -18257,12 +18270,12 @@
       "name": "Casa-14b-sce",
       "developer": "Quazim0t0",
       "scores": {
-        "IFEval": 0.6654,
-        "BBH": 0.6901,
-        "MATH Level 5": 0.4698,
-        "GPQA": 0.3331,
-        "MUSR": 0.431,
-        "MMLU-PRO": 0.5426
+        "IFEval": 0.6718,
+        "BBH": 0.6891,
+        "MATH Level 5": 0.4985,
+        "GPQA": 0.3339,
+        "MUSR": 0.4323,
+        "MMLU-PRO": 0.5408
       }
     },
     {
@@ -18699,12 +18712,12 @@
       "name": "ODB-14B-sce",
       "developer": "Quazim0t0",
       "scores": {
-        "IFEval": 0.2922,
-        "BBH": 0.6559,
-        "MATH Level 5": 0.2545,
-        "GPQA": 0.2659,
-        "MUSR": 0.3929,
-        "MMLU-PRO": 0.5207
+        "IFEval": 0.7016,
+        "BBH": 0.6942,
+        "MATH Level 5": 0.4116,
+        "GPQA": 0.3624,
+        "MUSR": 0.4571,
+        "MMLU-PRO": 0.5411
       }
     },
     {
@@ -19453,12 +19466,12 @@
       "name": "Qwen2.5-0.5B-Instruct",
       "developer": "Qwen",
       "scores": {
-        "IFEval": 0.3071,
-        "BBH": 0.3341,
-        "MATH Level 5": 0.0,
-        "GPQA": 0.2576,
-        "MUSR": 0.3329,
-        "MMLU-PRO": 0.1697
+        "IFEval": 0.3153,
+        "BBH": 0.3322,
+        "MATH Level 5": 0.1035,
+        "GPQA": 0.2592,
+        "MUSR": 0.3342,
+        "MMLU-PRO": 0.172
       }
     },
     {
@@ -19973,12 +19986,12 @@
       "name": "Replete-LLM-Qwen2-7b",
       "developer": "Replete-AI",
       "scores": {
-        "IFEval": 0.0905,
-        "BBH": 0.2985,
+        "IFEval": 0.0932,
+        "BBH": 0.2977,
         "MATH Level 5": 0.0,
-        "GPQA": 0.2534,
-        "MUSR": 0.3848,
-        "MMLU-PRO": 0.1158
+        "GPQA": 0.2475,
+        "MUSR": 0.3941,
+        "MMLU-PRO": 0.1157
       }
     },
     {
@@ -25056,12 +25069,12 @@
       "name": "Llama3.1-8B-Cobalt",
       "developer": "ValiantLabs",
       "scores": {
-        "IFEval": 0.7168,
-        "BBH": 0.4911,
-        "MATH Level 5": 0.1533,
-        "GPQA": 0.2861,
-        "MUSR": 0.3512,
-        "MMLU-PRO": 0.3663
+        "IFEval": 0.3496,
+        "BBH": 0.4947,
+        "MATH Level 5": 0.1269,
+        "GPQA": 0.3037,
+        "MUSR": 0.3959,
+        "MMLU-PRO": 0.3644
       }
     },
     {
@@ -26499,12 +26512,12 @@
       "name": "autotrain-0tmgq-5tpbg",
       "developer": "abhishek",
       "scores": {
-        "IFEval": 0.1952,
-        "BBH": 0.3127,
-        "MATH Level 5": 0.0128,
-        "GPQA": 0.2592,
-        "MUSR": 0.3584,
-        "MMLU-PRO": 0.1144
+        "IFEval": 0.1957,
+        "BBH": 0.3135,
+        "MATH Level 5": 0.0,
+        "GPQA": 0.2517,
+        "MUSR": 0.365,
+        "MMLU-PRO": 0.1151
       }
     },
     {
@@ -26590,12 +26603,12 @@
       "name": "QAIMath-Qwen2.5-7B-TIES",
       "developer": "adriszmar",
       "scores": {
-        "IFEval": 0.1746,
-        "BBH": 0.3126,
-        "MATH Level 5": 0.0,
-        "GPQA": 0.245,
-        "MUSR": 0.4096,
-        "MMLU-PRO": 0.1087
+        "IFEval": 0.1685,
+        "BBH": 0.3124,
+        "MATH Level 5": 0.0015,
+        "GPQA": 0.2492,
+        "MUSR": 0.3963,
+        "MMLU-PRO": 0.1066
       }
     },
     {
@@ -26876,12 +26889,12 @@
       "name": "Llama-3.1-Storm-8B",
       "developer": "akjindal53244",
       "scores": {
-        "IFEval": 0.8033,
-        "BBH": 0.5196,
-        "MATH Level 5": 0.1624,
-        "GPQA": 0.3096,
+        "IFEval": 0.8051,
+        "BBH": 0.5189,
+        "MATH Level 5": 0.1722,
+        "GPQA": 0.3263,
         "MUSR": 0.4028,
-        "MMLU-PRO": 0.3812
+        "MMLU-PRO": 0.3803
       }
     },
     {
@@ -26902,12 +26915,12 @@
       "name": "Llama-3.1-Tulu-3-70B",
       "developer": "allenai",
       "scores": {
-        "IFEval": 0.8291,
-        "BBH": 0.6164,
-        "MATH Level 5": 0.4502,
+        "IFEval": 0.8379,
+        "BBH": 0.6157,
+        "MATH Level 5": 0.3829,
         "GPQA": 0.3733,
-        "MUSR": 0.4948,
-        "MMLU-PRO": 0.4645
+        "MUSR": 0.4988,
+        "MMLU-PRO": 0.4656
       }
     },
     {
@@ -26941,12 +26954,12 @@
       "name": "Llama-3.1-Tulu-3-8B",
       "developer": "allenai",
       "scores": {
-        "IFEval": 0.8267,
-        "BBH": 0.405,
-        "MATH Level 5": 0.1964,
-        "GPQA": 0.2987,
+        "IFEval": 0.8255,
+        "BBH": 0.4061,
+        "MATH Level 5": 0.2115,
+        "GPQA": 0.297,
         "MUSR": 0.4175,
-        "MMLU-PRO": 0.2827
+        "MMLU-PRO": 0.2821
       }
     },
     {
@@ -30347,12 +30360,12 @@
       "name": "Llama-3.2-3B-Deep-Test",
       "developer": "bunnycore",
       "scores": {
-        "IFEval": 0.1775,
-        "BBH": 0.295,
-        "MATH Level 5": 0.0,
-        "GPQA": 0.2517,
-        "MUSR": 0.3647,
-        "MMLU-PRO": 0.1049
+        "IFEval": 0.4652,
+        "BBH": 0.4531,
+        "MATH Level 5": 0.1284,
+        "GPQA": 0.2643,
+        "MUSR": 0.3394,
+        "MMLU-PRO": 0.3152
       }
     },
     {
@@ -32154,12 +32167,12 @@
       "name": "Llama-3-8B-Orpo-v0.1",
       "developer": "dfurman",
       "scores": {
-        "IFEval": 0.3,
-        "BBH": 0.3853,
-        "MATH Level 5": 0.0415,
-        "GPQA": 0.2617,
-        "MUSR": 0.3579,
-        "MMLU-PRO": 0.2281
+        "IFEval": 0.2835,
+        "BBH": 0.3842,
+        "MATH Level 5": 0.0521,
+        "GPQA": 0.2609,
+        "MUSR": 0.3566,
+        "MMLU-PRO": 0.2298
       }
     },
     {
@@ -37258,19 +37271,6 @@
         "MMLU-PRO": 0.3103
       }
     },
-    {
-      "model_id": "icefog72/IceSakeV6RP-7b",
-      "name": "IceSakeV6RP-7b",
-      "developer": "icefog72",
-      "scores": {
-        "IFEval": 0.5033,
-        "BBH": 0.4976,
-        "MATH Level 5": 0.0619,
-        "GPQA": 0.2911,
-        "MUSR": 0.42,
-        "MMLU-PRO": 0.3093
-      }
-    },
     {
       "model_id": "icefog72/IceSakeV8RP-7b",
       "name": "IceSakeV8RP-7b",
@@ -37692,12 +37692,12 @@
       "name": "Kosmos-EVAA-Fusion-8B",
       "developer": "jaspionjader",
       "scores": {
-        "IFEval": 0.4418,
-        "BBH": 0.5406,
-        "MATH Level 5": 0.1352,
-        "GPQA": 0.3062,
+        "IFEval": 0.4345,
+        "BBH": 0.5419,
+        "MATH Level 5": 0.1292,
+        "GPQA": 0.3087,
         "MUSR": 0.4277,
-        "MMLU-PRO": 0.386
+        "MMLU-PRO": 0.3854
       }
     },
     {
@@ -43971,12 +43971,12 @@
       "name": "Phi-3-mini-4k-instruct",
       "developer": "microsoft",
       "scores": {
-        "IFEval": 0.5477,
-        "BBH": 0.5491,
-        "MATH Level 5": 0.1639,
-        "GPQA": 0.3322,
-        "MUSR": 0.4284,
-        "MMLU-PRO": 0.4022
+        "IFEval": 0.5613,
+        "BBH": 0.5676,
+        "MATH Level 5": 0.1163,
+        "GPQA": 0.3196,
+        "MUSR": 0.395,
+        "MMLU-PRO": 0.3866
       }
     },
     {
@@ -44101,12 +44101,12 @@
       "name": "phi-4",
       "developer": "microsoft",
       "scores": {
-        "IFEval": 0.0585,
-        "BBH": 0.6691,
-        "MATH Level 5": 0.3165,
-        "GPQA": 0.406,
+        "IFEval": 0.0488,
+        "BBH": 0.6703,
+        "MATH Level 5": 0.2787,
+        "GPQA": 0.401,
         "MUSR": 0.5034,
-        "MMLU-PRO": 0.5287
+        "MMLU-PRO": 0.5295
       }
     },
     {
@@ -44413,12 +44413,12 @@
       "name": "Mistral-Small-Instruct-2409",
       "developer": "mistralai",
       "scores": {
-        "IFEval": 0.667,
-        "BBH": 0.5213,
-        "MATH Level 5": 0.1435,
-        "GPQA": 0.3238,
-        "MUSR": 0.3632,
-        "MMLU-PRO": 0.396
+        "IFEval": 0.6283,
+        "BBH": 0.583,
+        "MATH Level 5": 0.2039,
+        "GPQA": 0.3331,
+        "MUSR": 0.4063,
+        "MMLU-PRO": 0.4099
       }
     },
     {
@@ -44465,12 +44465,12 @@
       "name": "Mixtral-8x7B-v0.1",
       "developer": "mistralai",
       "scores": {
-        "IFEval": 0.2415,
-        "BBH": 0.5087,
-        "MATH Level 5": 0.102,
-        "GPQA": 0.3138,
-        "MUSR": 0.4321,
-        "MMLU-PRO": 0.385
+        "IFEval": 0.2326,
+        "BBH": 0.5098,
+        "MATH Level 5": 0.0937,
+        "GPQA": 0.3205,
+        "MUSR": 0.4413,
+        "MMLU-PRO": 0.3871
       }
     },
     {
@@ -44725,12 +44725,12 @@
       "name": "NeuralDaredevil-8B-abliterated",
       "developer": "mlabonne",
       "scores": {
-        "IFEval": 0.7561,
-        "BBH": 0.5111,
-        "MATH Level 5": 0.0906,
-        "GPQA": 0.3062,
-        "MUSR": 0.4019,
-        "MMLU-PRO": 0.3841
+        "IFEval": 0.4162,
+        "BBH": 0.5124,
+        "MATH Level 5": 0.0853,
+        "GPQA": 0.3029,
+        "MUSR": 0.415,
+        "MMLU-PRO": 0.3802
       }
     },
     {
@@ -47598,12 +47598,12 @@
       "name": "wide_3b_sft_stage1.1-ss1-with_generics_intr_math_stories.no_issue",
       "developer": "ontocord",
       "scores": {
-        "IFEval": 0.1162,
-        "BBH": 0.3184,
-        "MATH Level 5": 0.0076,
-        "GPQA": 0.2634,
-        "MUSR": 0.3447,
-        "MMLU-PRO": 0.1124
+        "IFEval": 0.1128,
+        "BBH": 0.3171,
+        "MATH Level 5": 0.0113,
+        "GPQA": 0.2685,
+        "MUSR": 0.346,
+        "MMLU-PRO": 0.1129
       }
     },
     {
@@ -48716,12 +48716,12 @@
       "name": "Llama-3-8B-ProLong-512k-Instruct",
       "developer": "princeton-nlp",
       "scores": {
-        "IFEval": 0.3978,
-        "BBH": 0.4983,
-        "MATH Level 5": 0.0582,
-        "GPQA": 0.281,
-        "MUSR": 0.425,
-        "MMLU-PRO": 0.3246
+        "IFEval": 0.5508,
+        "BBH": 0.5028,
+        "MATH Level 5": 0.0529,
+        "GPQA": 0.2861,
+        "MUSR": 0.4266,
+        "MMLU-PRO": 0.3231
       }
     },
     {
@@ -49431,12 +49431,12 @@
       "name": "Calcium-Opus-14B-Elite",
       "developer": "prithivMLmods",
       "scores": {
-        "IFEval": 0.6052,
-        "BBH": 0.6317,
-        "MATH Level 5": 0.4789,
-        "GPQA": 0.3742,
-        "MUSR": 0.486,
-        "MMLU-PRO": 0.5302
+        "IFEval": 0.6064,
+        "BBH": 0.6296,
+        "MATH Level 5": 0.3708,
+        "GPQA": 0.3733,
+        "MUSR": 0.4873,
+        "MMLU-PRO": 0.5307
       }
     },
     {
@@ -50861,12 +50861,12 @@
       "name": "Qwen2.5-Math-14B-Instruct",
       "developer": "qingy2019",
       "scores": {
-        "IFEval": 0.6005,
-        "BBH": 0.6356,
-        "MATH Level 5": 0.2764,
-        "GPQA": 0.3691,
+        "IFEval": 0.6066,
+        "BBH": 0.635,
+        "MATH Level 5": 0.3716,
+        "GPQA": 0.3725,
         "MUSR": 0.4757,
-        "MMLU-PRO": 0.5339
+        "MMLU-PRO": 0.5331
       }
     },
     {
@@ -51316,12 +51316,12 @@
       "name": "recoilme-gemma-2-9B-v0.2",
       "developer": "recoilme",
       "scores": {
-        "IFEval": 0.7592,
-        "BBH": 0.6026,
-        "MATH Level 5": 0.0529,
-        "GPQA": 0.3289,
-        "MUSR": 0.4099,
-        "MMLU-PRO": 0.4163
+        "IFEval": 0.2747,
+        "BBH": 0.6031,
+        "MATH Level 5": 0.0831,
+        "GPQA": 0.3305,
+        "MUSR": 0.4686,
+        "MMLU-PRO": 0.4122
       }
     },
     {
@@ -51329,12 +51329,12 @@
       "name": "recoilme-gemma-2-9B-v0.3",
       "developer": "recoilme",
       "scores": {
-        "IFEval": 0.5761,
-        "BBH": 0.602,
-        "MATH Level 5": 0.1888,
-        "GPQA": 0.3372,
-        "MUSR": 0.4632,
-        "MMLU-PRO": 0.4039
+        "IFEval": 0.7439,
+        "BBH": 0.5993,
+        "MATH Level 5": 0.0876,
+        "GPQA": 0.3238,
+        "MUSR": 0.4204,
+        "MMLU-PRO": 0.4072
       }
     },
     {
@@ -53188,12 +53188,12 @@
       "name": "Qwenvergence-14B-v3-Reason",
       "developer": "sometimesanotion",
       "scores": {
-        "IFEval": 0.5367,
-        "BBH": 0.6561,
-        "MATH Level 5": 0.358,
-        "GPQA": 0.3867,
-        "MUSR": 0.474,
-        "MMLU-PRO": 0.5395
+        "IFEval": 0.5278,
+        "BBH": 0.6557,
+        "MATH Level 5": 0.3119,
+        "GPQA": 0.3842,
+        "MUSR": 0.4754,
+        "MMLU-PRO": 0.5396
       }
     },
     {
@@ -54332,12 +54332,12 @@
       "name": "lambda-gemma-2-9b-dpo",
       "developer": "tanliboy",
       "scores": {
-        "IFEval": 0.4501,
-        "BBH": 0.5472,
-        "MATH Level 5": 0.0944,
-        "GPQA": 0.3138,
-        "MUSR": 0.4017,
-        "MMLU-PRO": 0.3792
+        "IFEval": 0.1829,
+        "BBH": 0.5488,
+        "MATH Level 5": 0.0,
+        "GPQA": 0.3104,
+        "MUSR": 0.4056,
+        "MMLU-PRO": 0.3805
       }
     },
     {
@@ -56932,12 +56932,12 @@
       "name": "Hebrew-Mistral-7B-200K",
       "developer": "yam-peleg",
       "scores": {
-        "IFEval": 0.1856,
-        "BBH": 0.4149,
-        "MATH Level 5": 0.0234,
-        "GPQA": 0.276,
-        "MUSR": 0.3765,
-        "MMLU-PRO": 0.2573
+        "IFEval": 0.177,
+        "BBH": 0.3411,
+        "MATH Level 5": 0.031,
+        "GPQA": 0.2534,
+        "MUSR": 0.374,
+        "MMLU-PRO": 0.2529
       }
     },
     {
diff --git a/data/benchmarks/livecodebenchpro.json b/data/benchmarks/livecodebenchpro.json
index 896b3c77b4f3fcb0324b8662401bdd6aa70bb19b..f8f77204727bc54bca1bbaaa204ca44d2b265f12 100644
--- a/data/benchmarks/livecodebenchpro.json
+++ b/data/benchmarks/livecodebenchpro.json
@@ -205,9 +205,9 @@
       "name": "gpt-5-2025-08-07",
       "developer": "OpenAI",
       "scores": {
-        "Hard Problems": 0.04225352112676056,
-        "Medium Problems": 0.4084507042253521,
-        "Easy Problems": 0.8873239436619719
+        "Hard Problems": 0.0423,
+        "Medium Problems": 0.4085,
+        "Easy Problems": 0.9014
       }
     },
     {
@@ -255,9 +255,9 @@
       "name": "o4-mini-2025-04-16",
       "developer": "OpenAI",
       "scores": {
-        "Hard Problems": 0.014084507042253521,
-        "Medium Problems": 0.30985915492957744,
-        "Easy Problems": 0.8873239436619719
+        "Hard Problems": 0.0143,
+        "Medium Problems": 0.2923,
+        "Easy Problems": 0.8571
       }
     },
     {
diff --git a/data/benchmarks/reward-bench.json b/data/benchmarks/reward-bench.json
index d41f3c4a1d71f52cfb866cd53b58580a0eae02dd..71717215bb28d07da86d76055db6b05b5dbcd648 100644
--- a/data/benchmarks/reward-bench.json
+++ b/data/benchmarks/reward-bench.json
@@ -81,17 +81,17 @@
       "name": "CIR-AMS/BTRM_Qwen2_7b_0613",
       "developer": "CIR-AMS",
       "scores": {
-        "Score": 0.8172,
+        "Score": 0.5736,
+        "Chat": 0.9749,
+        "Chat Hard": 0.5724,
+        "Safety": 0.7178,
+        "Reasoning": 0.8775,
+        "Prior Sets (0.5 weight)": 0.7029,
         "Factuality": 0.5347,
         "Precise IF": 0.3563,
         "Math": 0.6066,
-        "Safety": 0.9014,
         "Focus": 0.5737,
-        "Ties": 0.6527,
-        "Chat": 0.9749,
-        "Chat Hard": 0.5724,
-        "Reasoning": 0.8775,
-        "Prior Sets (0.5 weight)": 0.7029
+        "Ties": 0.6527
       }
     },
     {
@@ -453,16 +453,16 @@
       "name": "LxzGordon/URM-LLaMa-3.1-8B",
       "developer": "LxzGordon",
       "scores": {
-        "Score": 0.7394,
-        "Chat": 0.9553,
-        "Chat Hard": 0.8816,
-        "Safety": 0.9178,
-        "Reasoning": 0.9698,
+        "Score": 0.9294,
         "Factuality": 0.6884,
         "Precise IF": 0.45,
         "Math": 0.6393,
+        "Safety": 0.9108,
         "Focus": 0.9758,
-        "Ties": 0.7653
+        "Ties": 0.7653,
+        "Chat": 0.9553,
+        "Chat Hard": 0.8816,
+        "Reasoning": 0.9698
       }
     },
     {
@@ -555,17 +555,17 @@
       "name": "OpenAssistant/oasst-rm-2-pythia-6.9b-epoch-1",
       "developer": "OpenAssistant",
       "scores": {
-        "Score": 0.2653,
-        "Chat": 0.9246,
-        "Chat Hard": 0.3728,
-        "Safety": 0.3289,
-        "Reasoning": 0.5855,
-        "Prior Sets (0.5 weight)": 0.6801,
+        "Score": 0.615,
         "Factuality": 0.3979,
         "Precise IF": 0.2875,
         "Math": 0.377,
+        "Safety": 0.5446,
         "Focus": 0.1535,
-        "Ties": 0.047
+        "Ties": 0.047,
+        "Chat": 0.9246,
+        "Chat Hard": 0.3728,
+        "Reasoning": 0.5855,
+        "Prior Sets (0.5 weight)": 0.6801
       }
     },
     {
@@ -609,17 +609,17 @@
       "name": "PKU-Alignment/beaver-7b-v1.0-cost",
       "developer": "PKU-Alignment",
       "scores": {
-        "Score": 0.5798,
+        "Score": 0.3332,
+        "Chat": 0.6173,
+        "Chat Hard": 0.4232,
+        "Safety": 0.7589,
+        "Reasoning": 0.5482,
+        "Prior Sets (0.5 weight)": 0.57,
         "Factuality": 0.3263,
         "Precise IF": 0.2313,
         "Math": 0.3989,
-        "Safety": 0.7351,
         "Focus": 0.2939,
-        "Ties": -0.01,
-        "Chat": 0.6173,
-        "Chat Hard": 0.4232,
-        "Reasoning": 0.5482,
-        "Prior Sets (0.5 weight)": 0.57
+        "Ties": -0.01
       }
     },
     {
@@ -627,17 +627,17 @@
       "name": "PKU-Alignment/beaver-7b-v1.0-reward",
       "developer": "PKU-Alignment",
       "scores": {
-        "Score": 0.1606,
-        "Chat": 0.8184,
-        "Chat Hard": 0.2873,
-        "Safety": 0.1422,
-        "Reasoning": 0.346,
-        "Prior Sets (0.5 weight)": 0.5993,
+        "Score": 0.4727,
         "Factuality": 0.2105,
         "Precise IF": 0.2938,
         "Math": 0.2623,
+        "Safety": 0.3757,
         "Focus": 0.0646,
-        "Ties": -0.01
+        "Ties": -0.01,
+        "Chat": 0.8184,
+        "Chat Hard": 0.2873,
+        "Reasoning": 0.346,
+        "Prior Sets (0.5 weight)": 0.5993
       }
     },
     {
@@ -663,17 +663,17 @@
       "name": "PKU-Alignment/beaver-7b-v2.0-reward",
       "developer": "PKU-Alignment",
       "scores": {
-        "Score": 0.2544,
-        "Chat": 0.8994,
-        "Chat Hard": 0.364,
-        "Safety": 0.3156,
-        "Reasoning": 0.6887,
-        "Prior Sets (0.5 weight)": 0.6171,
+        "Score": 0.6366,
         "Factuality": 0.2168,
         "Precise IF": 0.2562,
         "Math": 0.3825,
+        "Safety": 0.6041,
         "Focus": 0.2606,
-        "Ties": 0.0944
+        "Ties": 0.0944,
+        "Chat": 0.8994,
+        "Chat Hard": 0.364,
+        "Reasoning": 0.6887,
+        "Prior Sets (0.5 weight)": 0.6171
       }
     },
     {
@@ -904,16 +904,16 @@
       "name": "Ray2333/GRM-Llama3-8B-rewardmodel-ft",
       "developer": "Ray2333",
       "scores": {
-        "Score": 0.6766,
-        "Chat": 0.9553,
-        "Chat Hard": 0.8618,
-        "Safety": 0.9222,
-        "Reasoning": 0.9362,
+        "Score": 0.9154,
         "Factuality": 0.6274,
         "Precise IF": 0.35,
         "Math": 0.5847,
+        "Safety": 0.9081,
         "Focus": 0.8929,
-        "Ties": 0.6824
+        "Ties": 0.6824,
+        "Chat": 0.9553,
+        "Chat Hard": 0.8618,
+        "Reasoning": 0.9362
       }
     },
     {
@@ -921,16 +921,16 @@
       "name": "Ray2333/GRM-gemma2-2B-rewardmodel-ft",
       "developer": "Ray2333",
       "scores": {
-        "Score": 0.5966,
-        "Chat": 0.9302,
-        "Chat Hard": 0.7719,
-        "Safety": 0.9222,
-        "Reasoning": 0.912,
+        "Score": 0.8839,
         "Factuality": 0.5305,
         "Precise IF": 0.3125,
         "Math": 0.5902,
+        "Safety": 0.9216,
         "Focus": 0.7455,
-        "Ties": 0.4788
+        "Ties": 0.4788,
+        "Chat": 0.9302,
+        "Chat Hard": 0.7719,
+        "Reasoning": 0.912
       }
     },
     {
@@ -956,17 +956,17 @@
       "name": "Ray2333/GRM-llama3-8B-sftreg",
       "developer": "Ray2333",
       "scores": {
-        "Score": 0.8542,
+        "Score": 0.6089,
+        "Chat": 0.986,
+        "Chat Hard": 0.6776,
+        "Safety": 0.7867,
+        "Reasoning": 0.9229,
+        "Prior Sets (0.5 weight)": 0.7309,
         "Factuality": 0.6189,
         "Precise IF": 0.3875,
         "Math": 0.5792,
-        "Safety": 0.8919,
         "Focus": 0.6828,
-        "Ties": 0.5981,
-        "Chat": 0.986,
-        "Chat Hard": 0.6776,
-        "Reasoning": 0.9229,
-        "Prior Sets (0.5 weight)": 0.7309
+        "Ties": 0.5981
       }
     },
     {
@@ -1098,16 +1098,16 @@
       "name": "ShikaiChen/LDL-Reward-Gemma-2-27B-v0.1",
       "developer": "ShikaiChen",
       "scores": {
-        "Score": 0.9499,
+        "Score": 0.7249,
+        "Chat": 0.9637,
+        "Chat Hard": 0.9079,
+        "Safety": 0.9222,
+        "Reasoning": 0.9903,
         "Factuality": 0.7558,
         "Precise IF": 0.35,
         "Math": 0.6448,
-        "Safety": 0.9378,
         "Focus": 0.9131,
-        "Ties": 0.7633,
-        "Chat": 0.9637,
-        "Chat Hard": 0.9079,
-        "Reasoning": 0.9903
+        "Ties": 0.7633
       }
     },
     {
@@ -1139,16 +1139,16 @@
       "name": "Skywork/Skywork-Reward-Gemma-2-27B",
       "developer": "Skywork",
       "scores": {
-        "Score": 0.7576,
-        "Chat": 0.9581,
-        "Chat Hard": 0.9145,
-        "Safety": 0.9422,
-        "Reasoning": 0.9606,
+        "Score": 0.938,
         "Factuality": 0.7368,
         "Precise IF": 0.4031,
         "Math": 0.7049,
+        "Safety": 0.9189,
         "Focus": 0.9323,
-        "Ties": 0.8261
+        "Ties": 0.8261,
+        "Chat": 0.9581,
+        "Chat Hard": 0.9145,
+        "Reasoning": 0.9606
       }
     },
     {
@@ -1305,16 +1305,16 @@
       "name": "Skywork/Skywork-VL-Reward-7B",
       "developer": "Skywork",
       "scores": {
-        "Score": 0.6885,
-        "Chat": 0.8994,
-        "Chat Hard": 0.875,
-        "Safety": 0.8911,
-        "Reasoning": 0.9176,
+        "Score": 0.9007,
         "Factuality": 0.6063,
         "Precise IF": 0.35,
         "Math": 0.6339,
+        "Safety": 0.9108,
         "Focus": 0.8909,
-        "Ties": 0.7586
+        "Ties": 0.7586,
+        "Chat": 0.8994,
+        "Chat Hard": 0.875,
+        "Reasoning": 0.9176
       }
     },
     {
@@ -1379,10 +1379,10 @@
       "name": "ai2/tulu-2-7b-rm-v0-nectar-binarized-3.8m-check...",
       "developer": "AI2",
       "scores": {
-        "Score": 0.6924,
-        "Chat": 0.9441,
-        "Chat Hard": 0.3575,
-        "Safety": 0.7757
+        "Score": 0.6895,
+        "Chat": 0.9385,
+        "Chat Hard": 0.3706,
+        "Safety": 0.7595
       }
     },
     {
@@ -1441,17 +1441,17 @@
       "name": "allenai/Llama-3.1-8B-Base-RM-RB2",
       "developer": "allenai",
       "scores": {
-        "Score": 0.649,
-        "Chat": 0.933,
-        "Chat Hard": 0.7785,
-        "Safety": 0.8267,
-        "Reasoning": 0.7886,
-        "Prior Sets (0.5 weight)": 0.0,
+        "Score": 0.8463,
         "Factuality": 0.72,
         "Precise IF": 0.3625,
         "Math": 0.612,
+        "Safety": 0.8851,
         "Focus": 0.8323,
-        "Ties": 0.5406
+        "Ties": 0.5406,
+        "Chat": 0.933,
+        "Chat Hard": 0.7785,
+        "Reasoning": 0.7886,
+        "Prior Sets (0.5 weight)": 0.0
       }
     },
     {
@@ -1477,17 +1477,17 @@
       "name": "allenai/Llama-3.1-Tulu-3-70B-SFT-RM-RB2",
       "developer": "allenai",
       "scores": {
-        "Score": 0.8892,
+        "Score": 0.722,
+        "Chat": 0.9693,
+        "Chat Hard": 0.8268,
+        "Safety": 0.8689,
+        "Reasoning": 0.8583,
+        "Prior Sets (0.5 weight)": 0.0,
         "Factuality": 0.8084,
         "Precise IF": 0.3688,
         "Math": 0.6776,
-        "Safety": 0.9027,
         "Focus": 0.7778,
-        "Ties": 0.8308,
-        "Chat": 0.9693,
-        "Chat Hard": 0.8268,
-        "Reasoning": 0.8583,
-        "Prior Sets (0.5 weight)": 0.0
+        "Ties": 0.8308
       }
     },
     {
@@ -1495,17 +1495,17 @@
       "name": "allenai/Llama-3.1-Tulu-3-8B-DPO-RM-RB2",
       "developer": "allenai",
       "scores": {
-        "Score": 0.8431,
+        "Score": 0.687,
+        "Chat": 0.9553,
+        "Chat Hard": 0.761,
+        "Safety": 0.86,
+        "Reasoning": 0.7898,
+        "Prior Sets (0.5 weight)": 0.0,
         "Factuality": 0.7516,
         "Precise IF": 0.3875,
         "Math": 0.6284,
-        "Safety": 0.8662,
         "Focus": 0.8545,
-        "Ties": 0.6397,
-        "Chat": 0.9553,
-        "Chat Hard": 0.761,
-        "Reasoning": 0.7898,
-        "Prior Sets (0.5 weight)": 0.0
+        "Ties": 0.6397
       }
     },
     {
@@ -2085,20 +2085,6 @@
         "Ties": 0.3534
       }
     },
-    {
-      "model_id": "allenai/open_instruct_dev-rm_1e-6_2_30pctflipped__1__1743325094",
-      "name": "allenai/open_instruct_dev-rm_1e-6_2_30pctflipped__1__1743325094",
-      "developer": "allenai",
-      "scores": {
-        "Score": 0.5151,
-        "Factuality": 0.6484,
-        "Precise IF": 0.3312,
-        "Math": 0.5574,
-        "Safety": 0.7289,
-        "Focus": 0.4889,
-        "Ties": 0.3357
-      }
-    },
     {
       "model_id": "allenai/open_instruct_dev-rm_1e-6_2_5pctflipped__1__1743444636",
       "name": "allenai/open_instruct_dev-rm_1e-6_2_5pctflipped__1__1743444636",
@@ -3486,17 +3472,17 @@
       "name": "Claude 3 Haiku 20240307",
       "developer": "Anthropic",
       "scores": {
-        "Score": 0.3711,
-        "Chat": 0.9274,
-        "Chat Hard": 0.5197,
-        "Safety": 0.595,
-        "Reasoning": 0.706,
-        "Prior Sets (0.5 weight)": 0.6635,
+        "Score": 0.7289,
         "Factuality": 0.4042,
         "Precise IF": 0.2812,
         "Math": 0.3552,
+        "Safety": 0.7953,
         "Focus": 0.501,
-        "Ties": 0.0899
+        "Ties": 0.0899,
+        "Chat": 0.9274,
+        "Chat Hard": 0.5197,
+        "Reasoning": 0.706,
+        "Prior Sets (0.5 weight)": 0.6635
       }
     },
     {
@@ -3504,16 +3490,16 @@
       "name": "Claude 3 Opus 20240229",
       "developer": "Anthropic",
       "scores": {
-        "Score": 0.5744,
-        "Chat": 0.9469,
-        "Chat Hard": 0.6031,
-        "Safety": 0.8378,
-        "Reasoning": 0.7868,
+        "Score": 0.8008,
         "Factuality": 0.5389,
         "Precise IF": 0.3312,
         "Math": 0.5137,
+        "Safety": 0.8662,
         "Focus": 0.6646,
-        "Ties": 0.5601
+        "Ties": 0.5601,
+        "Chat": 0.9469,
+        "Chat Hard": 0.6031,
+        "Reasoning": 0.7868
       }
     },
     {
@@ -3784,16 +3770,16 @@
       "name": "infly/INF-ORM-Llama3.1-70B",
       "developer": "infly",
       "scores": {
-        "Score": 0.9511,
+        "Score": 0.7648,
+        "Chat": 0.9665,
+        "Chat Hard": 0.9101,
+        "Safety": 0.9644,
+        "Reasoning": 0.9912,
         "Factuality": 0.7411,
         "Precise IF": 0.4188,
         "Math": 0.6995,
-        "Safety": 0.9365,
         "Focus": 0.903,
-        "Ties": 0.8622,
-        "Chat": 0.9665,
-        "Chat Hard": 0.9101,
-        "Reasoning": 0.9912
+        "Ties": 0.8622
       }
     },
     {
@@ -3801,16 +3787,16 @@
       "name": "internlm/internlm2-1_8b-reward",
       "developer": "internlm",
       "scores": {
-        "Score": 0.3902,
-        "Chat": 0.9358,
-        "Chat Hard": 0.6623,
-        "Safety": 0.4711,
-        "Reasoning": 0.8724,
+        "Score": 0.8217,
         "Factuality": 0.2758,
         "Precise IF": 0.3625,
         "Math": 0.4426,
+        "Safety": 0.8162,
         "Focus": 0.596,
-        "Ties": 0.1934
+        "Ties": 0.1934,
+        "Chat": 0.9358,
+        "Chat Hard": 0.6623,
+        "Reasoning": 0.8724
       }
     },
     {
@@ -3835,16 +3821,16 @@
       "name": "internlm/internlm2-7b-reward",
       "developer": "internlm",
       "scores": {
-        "Score": 0.5335,
-        "Chat": 0.9916,
-        "Chat Hard": 0.6952,
-        "Safety": 0.5956,
-        "Reasoning": 0.9453,
+        "Score": 0.8759,
         "Factuality": 0.4211,
         "Precise IF": 0.4,
         "Math": 0.5628,
+        "Safety": 0.8716,
         "Focus": 0.7051,
-        "Ties": 0.5164
+        "Ties": 0.5164,
+        "Chat": 0.9916,
+        "Chat Hard": 0.6952,
+        "Reasoning": 0.9453
       }
     },
     {
@@ -4014,16 +4000,16 @@
       "name": "nicolinho/QRM-Gemma-2-27B",
       "developer": "nicolinho",
       "scores": {
-        "Score": 0.7667,
-        "Chat": 0.9665,
-        "Chat Hard": 0.9013,
-        "Safety": 0.9578,
-        "Reasoning": 0.9826,
+        "Score": 0.9444,
         "Factuality": 0.7853,
         "Precise IF": 0.3719,
         "Math": 0.6995,
+        "Safety": 0.927,
         "Focus": 0.9535,
-        "Ties": 0.8321
+        "Ties": 0.8321,
+        "Chat": 0.9665,
+        "Chat Hard": 0.9013,
+        "Reasoning": 0.9826
       }
     },
     {
@@ -4055,16 +4041,16 @@
       "name": "nicolinho/QRM-Llama3.1-8B-v2",
       "developer": "nicolinho",
       "scores": {
-        "Score": 0.7074,
-        "Chat": 0.9637,
-        "Chat Hard": 0.8684,
-        "Safety": 0.9467,
-        "Reasoning": 0.9677,
+        "Score": 0.9314,
         "Factuality": 0.6653,
         "Precise IF": 0.4062,
         "Math": 0.612,
+        "Safety": 0.9257,
         "Focus": 0.8909,
-        "Ties": 0.7234
+        "Ties": 0.7234,
+        "Chat": 0.9637,
+        "Chat Hard": 0.8684,
+        "Reasoning": 0.9677
       }
     },
     {
@@ -4202,16 +4188,16 @@
       "name": "GPT-4o 2024-08-06",
       "developer": "OpenAI",
       "scores": {
-        "Score": 0.8673,
+        "Score": 0.6493,
+        "Chat": 0.9609,
+        "Chat Hard": 0.761,
+        "Safety": 0.8619,
+        "Reasoning": 0.8661,
         "Factuality": 0.5684,
         "Precise IF": 0.3312,
         "Math": 0.623,
-        "Safety": 0.8811,
         "Focus": 0.7293,
-        "Ties": 0.7819,
-        "Chat": 0.9609,
-        "Chat Hard": 0.761,
-        "Reasoning": 0.8661
+        "Ties": 0.7819
       }
     },
     {
@@ -4219,16 +4205,16 @@
       "name": "GPT-4o mini 2024-07-18",
       "developer": "OpenAI",
       "scores": {
-        "Score": 0.8007,
+        "Score": 0.5796,
+        "Chat": 0.9497,
+        "Chat Hard": 0.6075,
+        "Safety": 0.7667,
+        "Reasoning": 0.8374,
         "Factuality": 0.4105,
         "Precise IF": 0.3438,
         "Math": 0.5191,
-        "Safety": 0.8081,
         "Focus": 0.7414,
-        "Ties": 0.6962,
-        "Chat": 0.9497,
-        "Chat Hard": 0.6075,
-        "Reasoning": 0.8374
+        "Ties": 0.6962
       }
     },
     {
@@ -4280,17 +4266,17 @@
       "name": "openbmb/UltraRM-13b",
       "developer": "openbmb",
       "scores": {
-        "Score": 0.4683,
-        "Chat": 0.9637,
-        "Chat Hard": 0.5548,
-        "Safety": 0.5089,
-        "Reasoning": 0.6244,
-        "Prior Sets (0.5 weight)": 0.7294,
+        "Score": 0.6903,
         "Factuality": 0.5063,
         "Precise IF": 0.3312,
         "Math": 0.5519,
+        "Safety": 0.5986,
         "Focus": 0.6081,
-        "Ties": 0.3036
+        "Ties": 0.3036,
+        "Chat": 0.9637,
+        "Chat Hard": 0.5548,
+        "Reasoning": 0.6244,
+        "Prior Sets (0.5 weight)": 0.7294
       }
     },
     {
@@ -4370,17 +4356,17 @@
       "name": "sfairXC/FsfairX-LLaMA3-RM-v0.1",
       "developer": "sfairXC",
       "scores": {
-        "Score": 0.8338,
+        "Score": 0.6292,
+        "Chat": 0.9944,
+        "Chat Hard": 0.6513,
+        "Safety": 0.7667,
+        "Reasoning": 0.8644,
+        "Prior Sets (0.5 weight)": 0.7492,
         "Factuality": 0.5916,
         "Precise IF": 0.4188,
         "Math": 0.6284,
-        "Safety": 0.8676,
         "Focus": 0.7051,
-        "Ties": 0.6647,
-        "Chat": 0.9944,
-        "Chat Hard": 0.6513,
-        "Reasoning": 0.8644,
-        "Prior Sets (0.5 weight)": 0.7492
+        "Ties": 0.6647
       }
     },
     {
@@ -4492,17 +4478,17 @@
       "name": "weqweasdas/RM-Gemma-2B",
       "developer": "weqweasdas",
       "scores": {
-        "Score": 0.6549,
+        "Score": 0.3057,
+        "Chat": 0.9441,
+        "Chat Hard": 0.4079,
+        "Safety": 0.3311,
+        "Reasoning": 0.7637,
+        "Prior Sets (0.5 weight)": 0.6652,
         "Factuality": 0.3705,
         "Precise IF": 0.2812,
         "Math": 0.4317,
-        "Safety": 0.4986,
         "Focus": 0.2343,
-        "Ties": 0.1851,
-        "Chat": 0.9441,
-        "Chat Hard": 0.4079,
-        "Reasoning": 0.7637,
-        "Prior Sets (0.5 weight)": 0.6652
+        "Ties": 0.1851
       }
     },
     {
@@ -4541,17 +4527,17 @@
       "name": "weqweasdas/RM-Mistral-7B",
       "developer": "weqweasdas",
       "scores": {
-        "Score": 0.7982,
+        "Score": 0.596,
+        "Chat": 0.9665,
+        "Chat Hard": 0.6053,
+        "Safety": 0.6911,
+        "Reasoning": 0.7736,
+        "Prior Sets (0.5 weight)": 0.753,
         "Factuality": 0.5937,
         "Precise IF": 0.3438,
         "Math": 0.5956,
-        "Safety": 0.8703,
         "Focus": 0.7293,
-        "Ties": 0.6226,
-        "Chat": 0.9665,
-        "Chat Hard": 0.6053,
-        "Reasoning": 0.7736,
-        "Prior Sets (0.5 weight)": 0.753
+        "Ties": 0.6226
       }
     },
     {
@@ -4559,17 +4545,17 @@
       "name": "weqweasdas/hh_rlhf_rm_open_llama_3b",
       "developer": "weqweasdas",
       "scores": {
-        "Score": 0.5027,
+        "Score": 0.2498,
+        "Chat": 0.8184,
+        "Chat Hard": 0.3728,
+        "Safety": 0.24,
+        "Reasoning": 0.3281,
+        "Prior Sets (0.5 weight)": 0.6564,
         "Factuality": 0.3642,
         "Precise IF": 0.275,
         "Math": 0.3497,
-        "Safety": 0.4149,
         "Focus": 0.2384,
-        "Ties": 0.0315,
-        "Chat": 0.8184,
-        "Chat Hard": 0.3728,
-        "Reasoning": 0.3281,
-        "Prior Sets (0.5 weight)": 0.6564
+        "Ties": 0.0315
       }
     }
   ]
diff --git a/data/benchmarks/swe-bench.json b/data/benchmarks/swe-bench.json
index c5ac3821d8cf33006a01a757ed86c4602272b367..88b6df39554e558930cdff771fd1ab7d2dd73e3a 100644
--- a/data/benchmarks/swe-bench.json
+++ b/data/benchmarks/swe-bench.json
@@ -21,7 +21,7 @@
       "name": "gpt-5.2-2025-12-11",
       "developer": "OpenAI",
       "scores": {
-        "swe-bench": 0.5455
+        "swe-bench": 0.57
       }
     }
   ]
diff --git a/data/benchmarks/tau-bench-2_airline.json b/data/benchmarks/tau-bench-2_airline.json
index f12d28637a77b58341be6f902aadfc1d22527d1a..3829696a07bc037642c69851a891e0aeb0e5febf 100644
--- a/data/benchmarks/tau-bench-2_airline.json
+++ b/data/benchmarks/tau-bench-2_airline.json
@@ -5,7 +5,7 @@
       "name": "claude-opus-4-5",
       "developer": "Anthropic",
       "scores": {
-        "tau-bench-2/airline": 0.66
+        "tau-bench-2/airline": 0.72
       }
     },
     {
diff --git a/data/benchmarks/tau-bench-2_retail.json b/data/benchmarks/tau-bench-2_retail.json
index 8567872e9ca3424b440aa66923f7ea7a010a7290..220f36fbae7a50d2d3974e0cd62ceacad728d0fd 100644
--- a/data/benchmarks/tau-bench-2_retail.json
+++ b/data/benchmarks/tau-bench-2_retail.json
@@ -5,7 +5,7 @@
       "name": "claude-opus-4-5",
       "developer": "Anthropic",
       "scores": {
-        "tau-bench-2/retail": 0.78
+        "tau-bench-2/retail": 0.85
       }
     },
     {
@@ -13,7 +13,7 @@
       "name": "gemini-3-pro-preview",
       "developer": "Google",
       "scores": {
-        "tau-bench-2/retail": 0.73
+        "tau-bench-2/retail": 0.7805
       }
     },
     {
@@ -21,7 +21,7 @@
       "name": "gpt-5.2-2025-12-11",
       "developer": "OpenAI",
       "scores": {
-        "tau-bench-2/retail": 0.73
+        "tau-bench-2/retail": 0.68
       }
     }
   ]
diff --git a/data/benchmarks/tau-bench-2_telecom.json b/data/benchmarks/tau-bench-2_telecom.json
index 717a8c139daad73d2bba1920f3f4fdded08dd42b..5e2e97c5a63c814404bfd0e936bb7f41ce63593e 100644
--- a/data/benchmarks/tau-bench-2_telecom.json
+++ b/data/benchmarks/tau-bench-2_telecom.json
@@ -5,7 +5,7 @@
       "name": "claude-opus-4-5",
       "developer": "Anthropic",
       "scores": {
-        "tau-bench-2/telecom": 0.84
+        "tau-bench-2/telecom": 0.76
       }
     },
     {
@@ -21,7 +21,7 @@
       "name": "gpt-5.2-2025-12-11",
       "developer": "OpenAI",
       "scores": {
-        "tau-bench-2/telecom": 0.71
+        "tau-bench-2/telecom": 0.5354
       }
     }
   ]
diff --git a/data/benchmarks/terminal-bench-2.0.json b/data/benchmarks/terminal-bench-2.0.json
index 10b4a1e53538ae0245444d9327835077907520b5..eedfc30dd08733e57be031879da03991ca05bc76 100644
--- a/data/benchmarks/terminal-bench-2.0.json
+++ b/data/benchmarks/terminal-bench-2.0.json
@@ -5,7 +5,7 @@
       "name": "Qwen 3 Coder 480B",
       "developer": "Alibaba",
       "scores": {
-        "terminal-bench-2.0": 27.2
+        "terminal-bench-2.0": 25.4
       }
     },
     {
@@ -13,7 +13,7 @@
       "name": "Claude Haiku 4.5",
       "developer": "Anthropic",
       "scores": {
-        "terminal-bench-2.0": 13.9
+        "terminal-bench-2.0": 27.5
       }
     },
     {
@@ -21,7 +21,7 @@
       "name": "Claude Opus 4.1",
       "developer": "Anthropic",
       "scores": {
-        "terminal-bench-2.0": 35.1
+        "terminal-bench-2.0": 34.8
       }
     },
     {
@@ -37,7 +37,7 @@
       "name": "Claude Opus 4.6",
       "developer": "Anthropic",
       "scores": {
-        "terminal-bench-2.0": 62.9
+        "terminal-bench-2.0": 74.7
       }
     },
     {
@@ -45,7 +45,7 @@
       "name": "Claude Sonnet 4.5",
       "developer": "Anthropic",
       "scores": {
-        "terminal-bench-2.0": 42.6
+        "terminal-bench-2.0": 42.5
       }
     },
     {
@@ -77,7 +77,7 @@
       "name": "Gemini 3 Flash",
       "developer": "Google",
       "scores": {
-        "terminal-bench-2.0": 47.4
+        "terminal-bench-2.0": 51.0
       }
     },
     {
@@ -85,7 +85,7 @@
       "name": "Gemini 3 Pro",
       "developer": "Google",
       "scores": {
-        "terminal-bench-2.0": 56.0
+        "terminal-bench-2.0": 56.9
       }
     },
     {
@@ -109,7 +109,7 @@
       "name": "MiniMax M2.1",
       "developer": "MiniMax",
       "scores": {
-        "terminal-bench-2.0": 36.6
+        "terminal-bench-2.0": 29.2
       }
     },
     {
@@ -125,7 +125,7 @@
       "name": "Kimi K2 Instruct",
       "developer": "Moonshot AI",
       "scores": {
-        "terminal-bench-2.0": 27.8
+        "terminal-bench-2.0": 26.7
       }
     },
     {
@@ -149,7 +149,7 @@
       "name": "Multiple",
       "developer": "Multiple",
       "scores": {
-        "terminal-bench-2.0": 72.4
+        "terminal-bench-2.0": 71.0
       }
     },
     {
@@ -173,7 +173,7 @@
       "name": "GPT-5-Mini",
       "developer": "OpenAI",
       "scores": {
-        "terminal-bench-2.0": 24.0
+        "terminal-bench-2.0": 31.9
       }
     },
     {
@@ -181,7 +181,7 @@
       "name": "GPT-5-Nano",
       "developer": "OpenAI",
       "scores": {
-        "terminal-bench-2.0": 11.5
+        "terminal-bench-2.0": 7.0
       }
     },
     {
@@ -197,7 +197,7 @@
       "name": "GPT-5.1-Codex",
       "developer": "OpenAI",
       "scores": {
-        "terminal-bench-2.0": 57.8
+        "terminal-bench-2.0": 53.5
       }
     },
     {
@@ -221,7 +221,7 @@
       "name": "GPT-5.2",
       "developer": "OpenAI",
       "scores": {
-        "terminal-bench-2.0": 62.9
+        "terminal-bench-2.0": 60.7
       }
     },
     {
@@ -237,7 +237,7 @@
       "name": "GPT-5.3-Codex",
       "developer": "OpenAI",
       "scores": {
-        "terminal-bench-2.0": 77.3
+        "terminal-bench-2.0": 74.6
       }
     },
     {
@@ -245,7 +245,7 @@
       "name": "GPT-OSS-120B",
       "developer": "OpenAI",
       "scores": {
-        "terminal-bench-2.0": 18.7
+        "terminal-bench-2.0": 14.2
       }
     },
     {
@@ -285,7 +285,7 @@
       "name": "GLM 4.7",
       "developer": "Z-AI",
       "scores": {
-        "terminal-bench-2.0": 33.3
+        "terminal-bench-2.0": 33.4
       }
     },
     {
diff --git a/data/developers.json b/data/developers.json
index f579192a07283e4405b9950165cfa67af8d0dcda..013b8e244887bf6c63a6c680ce52cd50fedc7ed7 100644
--- a/data/developers.json
+++ b/data/developers.json
@@ -173,7 +173,7 @@
   },
   {
     "developer": "allenai",
-    "model_count": 162
+    "model_count": 161
   },
   {
     "developer": "allknowingroger",
@@ -1097,7 +1097,7 @@
   },
   {
     "developer": "icefog72",
-    "model_count": 62
+    "model_count": 61
   },
   {
     "developer": "IDEA-CCNL",
@@ -1917,7 +1917,7 @@
   },
   {
     "developer": "NousResearch",
-    "model_count": 18
+    "model_count": 19
   },
   {
     "developer": "Novaciano",
diff --git a/data/developers/abhishek.json b/data/developers/abhishek.json
index 4a990668962b400e2663f06544d4986dc1420d7b..93669d3c565d1e56b0d776cadd09cc45571db057 100644
--- a/data/developers/abhishek.json
+++ b/data/developers/abhishek.json
@@ -7,12 +7,12 @@
       "developer": "abhishek",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "hfopenllm_v2/IFEval": 0.1952,
-        "hfopenllm_v2/BBH": 0.3127,
-        "hfopenllm_v2/MATH Level 5": 0.0128,
-        "hfopenllm_v2/GPQA": 0.2592,
-        "hfopenllm_v2/MUSR": 0.3584,
-        "hfopenllm_v2/MMLU-PRO": 0.1144
+        "hfopenllm_v2/IFEval": 0.1957,
+        "hfopenllm_v2/BBH": 0.3135,
+        "hfopenllm_v2/MATH Level 5": 0.0,
+        "hfopenllm_v2/GPQA": 0.2517,
+        "hfopenllm_v2/MUSR": 0.365,
+        "hfopenllm_v2/MMLU-PRO": 0.1151
       }
     },
     {
diff --git a/data/developers/adriszmar.json b/data/developers/adriszmar.json
index 1f1d39916960942963a9c3c265196aea3657be38..acb90d745752909d8f96f323acb9caa9b19061ae 100644
--- a/data/developers/adriszmar.json
+++ b/data/developers/adriszmar.json
@@ -7,12 +7,12 @@
       "developer": "adriszmar",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "hfopenllm_v2/IFEval": 0.1746,
-        "hfopenllm_v2/BBH": 0.3126,
-        "hfopenllm_v2/MATH Level 5": 0.0,
-        "hfopenllm_v2/GPQA": 0.245,
-        "hfopenllm_v2/MUSR": 0.4096,
-        "hfopenllm_v2/MMLU-PRO": 0.1087
+        "hfopenllm_v2/IFEval": 0.1685,
+        "hfopenllm_v2/BBH": 0.3124,
+        "hfopenllm_v2/MATH Level 5": 0.0015,
+        "hfopenllm_v2/GPQA": 0.2492,
+        "hfopenllm_v2/MUSR": 0.3963,
+        "hfopenllm_v2/MMLU-PRO": 0.1066
       }
     }
   ]
diff --git a/data/developers/ai2.json b/data/developers/ai2.json
index 6ae2e91a5d501e1d313c59819f3bee806d5615b0..498b6154facf655073d48826dd02116d29e34e45 100644
--- a/data/developers/ai2.json
+++ b/data/developers/ai2.json
@@ -43,10 +43,10 @@
       "developer": "AI2",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "reward-bench/Score": 0.6924,
-        "reward-bench/Chat": 0.9441,
-        "reward-bench/Chat Hard": 0.3575,
-        "reward-bench/Safety": 0.7757
+        "reward-bench/Score": 0.6895,
+        "reward-bench/Chat": 0.9385,
+        "reward-bench/Chat Hard": 0.3706,
+        "reward-bench/Safety": 0.7595
       }
     },
     {
diff --git a/data/developers/akjindal53244.json b/data/developers/akjindal53244.json
index 86acdd918ca996450aa81c0111cbad62da1b8b17..237ea0357d953fdc2d416f7c27241c406836e723 100644
--- a/data/developers/akjindal53244.json
+++ b/data/developers/akjindal53244.json
@@ -7,12 +7,12 @@
       "developer": "akjindal53244",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "hfopenllm_v2/IFEval": 0.8033,
-        "hfopenllm_v2/BBH": 0.5196,
-        "hfopenllm_v2/MATH Level 5": 0.1624,
-        "hfopenllm_v2/GPQA": 0.3096,
+        "hfopenllm_v2/IFEval": 0.8051,
+        "hfopenllm_v2/BBH": 0.5189,
+        "hfopenllm_v2/MATH Level 5": 0.1722,
+        "hfopenllm_v2/GPQA": 0.3263,
         "hfopenllm_v2/MUSR": 0.4028,
-        "hfopenllm_v2/MMLU-PRO": 0.3812
+        "hfopenllm_v2/MMLU-PRO": 0.3803
       }
     }
   ]
diff --git a/data/developers/alibaba.json b/data/developers/alibaba.json
index 844401e341e9e7b7e568fb2e5cdb8d2481e4039c..8efe41024b181a324827f30ff358f0234de7b987 100644
--- a/data/developers/alibaba.json
+++ b/data/developers/alibaba.json
@@ -7,7 +7,7 @@
       "developer": "Alibaba",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "terminal-bench-2.0/terminal-bench-2.0": 27.2
+        "terminal-bench-2.0/terminal-bench-2.0": 25.4
       }
     },
     {
diff --git a/data/developers/allenai.json b/data/developers/allenai.json
index 4d8014825fe4883af161e8da92543c33ea544e4b..1c85dbe2cfcc674683235ce774bcd2bc78253288 100644
--- a/data/developers/allenai.json
+++ b/data/developers/allenai.json
@@ -82,17 +82,17 @@
       "developer": "allenai",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "reward-bench/Score": 0.649,
-        "reward-bench/Chat": 0.933,
-        "reward-bench/Chat Hard": 0.7785,
-        "reward-bench/Safety": 0.8267,
-        "reward-bench/Reasoning": 0.7886,
-        "reward-bench/Prior Sets (0.5 weight)": 0.0,
+        "reward-bench/Score": 0.8463,
         "reward-bench/Factuality": 0.72,
         "reward-bench/Precise IF": 0.3625,
         "reward-bench/Math": 0.612,
+        "reward-bench/Safety": 0.8851,
         "reward-bench/Focus": 0.8323,
-        "reward-bench/Ties": 0.5406
+        "reward-bench/Ties": 0.5406,
+        "reward-bench/Chat": 0.933,
+        "reward-bench/Chat Hard": 0.7785,
+        "reward-bench/Reasoning": 0.7886,
+        "reward-bench/Prior Sets (0.5 weight)": 0.0
       }
     },
     {
@@ -120,12 +120,12 @@
       "developer": "allenai",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "hfopenllm_v2/IFEval": 0.8291,
-        "hfopenllm_v2/BBH": 0.6164,
-        "hfopenllm_v2/MATH Level 5": 0.4502,
+        "hfopenllm_v2/IFEval": 0.8379,
+        "hfopenllm_v2/BBH": 0.6157,
+        "hfopenllm_v2/MATH Level 5": 0.3829,
         "hfopenllm_v2/GPQA": 0.3733,
-        "hfopenllm_v2/MUSR": 0.4948,
-        "hfopenllm_v2/MMLU-PRO": 0.4645
+        "hfopenllm_v2/MUSR": 0.4988,
+        "hfopenllm_v2/MMLU-PRO": 0.4656
       }
     },
     {
@@ -162,17 +162,17 @@
       "developer": "allenai",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "reward-bench/Score": 0.8892,
+        "reward-bench/Score": 0.722,
+        "reward-bench/Chat": 0.9693,
+        "reward-bench/Chat Hard": 0.8268,
+        "reward-bench/Safety": 0.8689,
+        "reward-bench/Reasoning": 0.8583,
+        "reward-bench/Prior Sets (0.5 weight)": 0.0,
         "reward-bench/Factuality": 0.8084,
         "reward-bench/Precise IF": 0.3688,
         "reward-bench/Math": 0.6776,
-        "reward-bench/Safety": 0.9027,
         "reward-bench/Focus": 0.7778,
-        "reward-bench/Ties": 0.8308,
-        "reward-bench/Chat": 0.9693,
-        "reward-bench/Chat Hard": 0.8268,
-        "reward-bench/Reasoning": 0.8583,
-        "reward-bench/Prior Sets (0.5 weight)": 0.0
+        "reward-bench/Ties": 0.8308
       }
     },
     {
@@ -181,12 +181,12 @@
       "developer": "allenai",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "hfopenllm_v2/IFEval": 0.8267,
-        "hfopenllm_v2/BBH": 0.405,
-        "hfopenllm_v2/MATH Level 5": 0.1964,
-        "hfopenllm_v2/GPQA": 0.2987,
+        "hfopenllm_v2/IFEval": 0.8255,
+        "hfopenllm_v2/BBH": 0.4061,
+        "hfopenllm_v2/MATH Level 5": 0.2115,
+        "hfopenllm_v2/GPQA": 0.297,
         "hfopenllm_v2/MUSR": 0.4175,
-        "hfopenllm_v2/MMLU-PRO": 0.2827
+        "hfopenllm_v2/MMLU-PRO": 0.2821
       }
     },
     {
@@ -209,17 +209,17 @@
       "developer": "allenai",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "reward-bench/Score": 0.8431,
+        "reward-bench/Score": 0.687,
+        "reward-bench/Chat": 0.9553,
+        "reward-bench/Chat Hard": 0.761,
+        "reward-bench/Safety": 0.86,
+        "reward-bench/Reasoning": 0.7898,
+        "reward-bench/Prior Sets (0.5 weight)": 0.0,
         "reward-bench/Factuality": 0.7516,
         "reward-bench/Precise IF": 0.3875,
         "reward-bench/Math": 0.6284,
-        "reward-bench/Safety": 0.8662,
         "reward-bench/Focus": 0.8545,
-        "reward-bench/Ties": 0.6397,
-        "reward-bench/Chat": 0.9553,
-        "reward-bench/Chat Hard": 0.761,
-        "reward-bench/Reasoning": 0.7898,
-        "reward-bench/Prior Sets (0.5 weight)": 0.0
+        "reward-bench/Ties": 0.6397
       }
     },
     {
@@ -1054,21 +1054,6 @@
         "reward-bench/Ties": 0.3534
       }
     },
-    {
-      "id": "allenai/open_instruct_dev-rm_1e-6_2_30pctflipped__1__1743325094",
-      "name": "allenai/open_instruct_dev-rm_1e-6_2_30pctflipped__1__1743325094",
-      "developer": "allenai",
-      "evaluator_relationship": null,
-      "benchmark_scores": {
-        "reward-bench/Score": 0.5151,
-        "reward-bench/Factuality": 0.6484,
-        "reward-bench/Precise IF": 0.3312,
-        "reward-bench/Math": 0.5574,
-        "reward-bench/Safety": 0.7289,
-        "reward-bench/Focus": 0.4889,
-        "reward-bench/Ties": 0.3357
-      }
-    },
     {
       "id": "allenai/open_instruct_dev-rm_1e-6_2_5pctflipped__1__1743444636",
       "name": "allenai/open_instruct_dev-rm_1e-6_2_5pctflipped__1__1743444636",
diff --git a/data/developers/anthropic.json b/data/developers/anthropic.json
index e348f58bb2289a52a6840206a2b95ae3acade6c2..819a852f845410b5f7876451b1dcb93ba59f6701 100644
--- a/data/developers/anthropic.json
+++ b/data/developers/anthropic.json
@@ -371,17 +371,17 @@
         "helm_mmlu/Virology": 0.542,
         "helm_mmlu/World Religions": 0.871,
         "helm_mmlu/Mean win rate": 0.28,
-        "reward-bench/Score": 0.3711,
-        "reward-bench/Chat": 0.9274,
-        "reward-bench/Chat Hard": 0.5197,
-        "reward-bench/Safety": 0.595,
-        "reward-bench/Reasoning": 0.706,
-        "reward-bench/Prior Sets (0.5 weight)": 0.6635,
+        "reward-bench/Score": 0.7289,
         "reward-bench/Factuality": 0.4042,
         "reward-bench/Precise IF": 0.2812,
         "reward-bench/Math": 0.3552,
+        "reward-bench/Safety": 0.7953,
         "reward-bench/Focus": 0.501,
-        "reward-bench/Ties": 0.0899
+        "reward-bench/Ties": 0.0899,
+        "reward-bench/Chat": 0.9274,
+        "reward-bench/Chat Hard": 0.5197,
+        "reward-bench/Reasoning": 0.706,
+        "reward-bench/Prior Sets (0.5 weight)": 0.6635
       }
     },
     {
@@ -436,16 +436,16 @@
         "helm_mmlu/Virology": 0.578,
         "helm_mmlu/World Religions": 0.901,
         "helm_mmlu/Mean win rate": 0.014,
-        "reward-bench/Score": 0.5744,
-        "reward-bench/Chat": 0.9469,
-        "reward-bench/Chat Hard": 0.6031,
-        "reward-bench/Safety": 0.8378,
-        "reward-bench/Reasoning": 0.7868,
+        "reward-bench/Score": 0.8008,
         "reward-bench/Factuality": 0.5389,
         "reward-bench/Precise IF": 0.3312,
         "reward-bench/Math": 0.5137,
+        "reward-bench/Safety": 0.8662,
         "reward-bench/Focus": 0.6646,
-        "reward-bench/Ties": 0.5601
+        "reward-bench/Ties": 0.5601,
+        "reward-bench/Chat": 0.9469,
+        "reward-bench/Chat Hard": 0.6031,
+        "reward-bench/Reasoning": 0.7868
       }
     },
     {
@@ -525,7 +525,7 @@
       "developer": "Anthropic",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "terminal-bench-2.0/terminal-bench-2.0": 13.9
+        "terminal-bench-2.0/terminal-bench-2.0": 27.5
       }
     },
     {
@@ -650,12 +650,12 @@
       "developer": "Anthropic",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "appworld_test_normal/appworld/test_normal": 0.7,
+        "appworld_test_normal/appworld/test_normal": 0.64,
         "browsecompplus/browsecompplus": 0.61,
         "swe-bench/swe-bench": 0.6061,
-        "tau-bench-2_airline/tau-bench-2/airline": 0.66,
-        "tau-bench-2_retail/tau-bench-2/retail": 0.78,
-        "tau-bench-2_telecom/tau-bench-2/telecom": 0.84
+        "tau-bench-2_airline/tau-bench-2/airline": 0.72,
+        "tau-bench-2_retail/tau-bench-2/retail": 0.85,
+        "tau-bench-2_telecom/tau-bench-2/telecom": 0.76
       }
     },
     {
@@ -664,7 +664,7 @@
       "developer": "Anthropic",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "terminal-bench-2.0/terminal-bench-2.0": 35.1
+        "terminal-bench-2.0/terminal-bench-2.0": 34.8
       }
     },
     {
@@ -682,7 +682,7 @@
       "developer": "Anthropic",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "terminal-bench-2.0/terminal-bench-2.0": 62.9
+        "terminal-bench-2.0/terminal-bench-2.0": 74.7
       }
     },
     {
@@ -756,7 +756,7 @@
       "developer": "Anthropic",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "terminal-bench-2.0/terminal-bench-2.0": 42.6
+        "terminal-bench-2.0/terminal-bench-2.0": 42.5
       }
     },
     {
diff --git a/data/developers/boltmonkey.json b/data/developers/boltmonkey.json
index d93c347b80733b690b666d77f058a8e36708eee2..93a1093c0cbb01b9a84ae22cf6063fc50d8793cb 100644
--- a/data/developers/boltmonkey.json
+++ b/data/developers/boltmonkey.json
@@ -21,12 +21,12 @@
       "developer": "BoltMonkey",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "hfopenllm_v2/IFEval": 0.459,
-        "hfopenllm_v2/BBH": 0.5185,
-        "hfopenllm_v2/MATH Level 5": 0.0937,
-        "hfopenllm_v2/GPQA": 0.2743,
-        "hfopenllm_v2/MUSR": 0.4083,
-        "hfopenllm_v2/MMLU-PRO": 0.3631
+        "hfopenllm_v2/IFEval": 0.7999,
+        "hfopenllm_v2/BBH": 0.5152,
+        "hfopenllm_v2/MATH Level 5": 0.1193,
+        "hfopenllm_v2/GPQA": 0.281,
+        "hfopenllm_v2/MUSR": 0.4019,
+        "hfopenllm_v2/MMLU-PRO": 0.3733
       }
     },
     {
diff --git a/data/developers/bunnycore.json b/data/developers/bunnycore.json
index 153064e2dea6c3626cb6deb17e2d3191b25ec406..069b8a9f0214975725e28f414b82b07e73072c0f 100644
--- a/data/developers/bunnycore.json
+++ b/data/developers/bunnycore.json
@@ -287,12 +287,12 @@
       "developer": "bunnycore",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "hfopenllm_v2/IFEval": 0.1775,
-        "hfopenllm_v2/BBH": 0.295,
-        "hfopenllm_v2/MATH Level 5": 0.0,
-        "hfopenllm_v2/GPQA": 0.2517,
-        "hfopenllm_v2/MUSR": 0.3647,
-        "hfopenllm_v2/MMLU-PRO": 0.1049
+        "hfopenllm_v2/IFEval": 0.4652,
+        "hfopenllm_v2/BBH": 0.4531,
+        "hfopenllm_v2/MATH Level 5": 0.1284,
+        "hfopenllm_v2/GPQA": 0.2643,
+        "hfopenllm_v2/MUSR": 0.3394,
+        "hfopenllm_v2/MMLU-PRO": 0.3152
       }
     },
     {
diff --git a/data/developers/cir-ams.json b/data/developers/cir-ams.json
index df9dcecb6f8fae5d901c2496b58813341797427e..09d0cc390a2584b96dbfe9a5acec25171fe175fa 100644
--- a/data/developers/cir-ams.json
+++ b/data/developers/cir-ams.json
@@ -7,17 +7,17 @@
       "developer": "CIR-AMS",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "reward-bench/Score": 0.8172,
+        "reward-bench/Score": 0.5736,
+        "reward-bench/Chat": 0.9749,
+        "reward-bench/Chat Hard": 0.5724,
+        "reward-bench/Safety": 0.7178,
+        "reward-bench/Reasoning": 0.8775,
+        "reward-bench/Prior Sets (0.5 weight)": 0.7029,
         "reward-bench/Factuality": 0.5347,
         "reward-bench/Precise IF": 0.3563,
         "reward-bench/Math": 0.6066,
-        "reward-bench/Safety": 0.9014,
         "reward-bench/Focus": 0.5737,
-        "reward-bench/Ties": 0.6527,
-        "reward-bench/Chat": 0.9749,
-        "reward-bench/Chat Hard": 0.5724,
-        "reward-bench/Reasoning": 0.8775,
-        "reward-bench/Prior Sets (0.5 weight)": 0.7029
+        "reward-bench/Ties": 0.6527
       }
     }
   ]
diff --git a/data/developers/columbia-nlp.json b/data/developers/columbia-nlp.json
index 11f5fed45eb39522787aef4e964f3d3e28d320c0..b04d1f97bca6939c03a53d86cd396214edf82f72 100644
--- a/data/developers/columbia-nlp.json
+++ b/data/developers/columbia-nlp.json
@@ -7,12 +7,12 @@
       "developer": "Columbia-NLP",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "hfopenllm_v2/IFEval": 0.3102,
-        "hfopenllm_v2/BBH": 0.3881,
-        "hfopenllm_v2/MATH Level 5": 0.0536,
-        "hfopenllm_v2/GPQA": 0.2534,
-        "hfopenllm_v2/MUSR": 0.4081,
-        "hfopenllm_v2/MMLU-PRO": 0.1665
+        "hfopenllm_v2/IFEval": 0.3278,
+        "hfopenllm_v2/BBH": 0.392,
+        "hfopenllm_v2/MATH Level 5": 0.0431,
+        "hfopenllm_v2/GPQA": 0.2492,
+        "hfopenllm_v2/MUSR": 0.412,
+        "hfopenllm_v2/MMLU-PRO": 0.1666
       }
     },
     {
diff --git a/data/developers/daemontatox.json b/data/developers/daemontatox.json
index 3de1c87bc255ec29e11a7fcd9434ebc4d17ff27a..09a88a4f4f23ea30a1c40f4893201987d0954b30 100644
--- a/data/developers/daemontatox.json
+++ b/data/developers/daemontatox.json
@@ -231,12 +231,12 @@
       "developer": "Daemontatox",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "hfopenllm_v2/IFEval": 0.4855,
-        "hfopenllm_v2/BBH": 0.6627,
-        "hfopenllm_v2/MATH Level 5": 0.4841,
-        "hfopenllm_v2/GPQA": 0.3096,
-        "hfopenllm_v2/MUSR": 0.4256,
-        "hfopenllm_v2/MMLU-PRO": 0.5542
+        "hfopenllm_v2/IFEval": 0.3745,
+        "hfopenllm_v2/BBH": 0.6668,
+        "hfopenllm_v2/MATH Level 5": 0.4758,
+        "hfopenllm_v2/GPQA": 0.3943,
+        "hfopenllm_v2/MUSR": 0.4858,
+        "hfopenllm_v2/MMLU-PRO": 0.5593
       }
     },
     {
diff --git a/data/developers/davielion.json b/data/developers/davielion.json
index ffdc7de10295de8981ccb0c2da137caa37979e5b..d2a3ca1471ea06bca721c18d505591908b22252e 100644
--- a/data/developers/davielion.json
+++ b/data/developers/davielion.json
@@ -7,12 +7,12 @@
       "developer": "DavieLion",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "hfopenllm_v2/IFEval": 0.1507,
-        "hfopenllm_v2/BBH": 0.293,
-        "hfopenllm_v2/MATH Level 5": 0.0,
-        "hfopenllm_v2/GPQA": 0.2534,
+        "hfopenllm_v2/IFEval": 0.1549,
+        "hfopenllm_v2/BBH": 0.2937,
+        "hfopenllm_v2/MATH Level 5": 0.006,
+        "hfopenllm_v2/GPQA": 0.2576,
         "hfopenllm_v2/MUSR": 0.3565,
-        "hfopenllm_v2/MMLU-PRO": 0.1125
+        "hfopenllm_v2/MMLU-PRO": 0.1128
       }
     },
     {
@@ -49,12 +49,12 @@
       "developer": "DavieLion",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "hfopenllm_v2/IFEval": 0.1336,
-        "hfopenllm_v2/BBH": 0.2975,
-        "hfopenllm_v2/MATH Level 5": 0.0068,
-        "hfopenllm_v2/GPQA": 0.2534,
-        "hfopenllm_v2/MUSR": 0.35,
-        "hfopenllm_v2/MMLU-PRO": 0.1128
+        "hfopenllm_v2/IFEval": 0.1324,
+        "hfopenllm_v2/BBH": 0.2972,
+        "hfopenllm_v2/MATH Level 5": 0.0,
+        "hfopenllm_v2/GPQA": 0.2643,
+        "hfopenllm_v2/MUSR": 0.3527,
+        "hfopenllm_v2/MMLU-PRO": 0.1129
       }
     },
     {
diff --git a/data/developers/deepmount00.json b/data/developers/deepmount00.json
index e898074e4a61782e05002f7b47eb2ee0411313aa..5505c28134c7ac10ef3a27978dd2745253c793a1 100644
--- a/data/developers/deepmount00.json
+++ b/data/developers/deepmount00.json
@@ -63,12 +63,12 @@
       "developer": "DeepMount00",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "hfopenllm_v2/IFEval": 0.5365,
-        "hfopenllm_v2/BBH": 0.517,
-        "hfopenllm_v2/MATH Level 5": 0.1707,
-        "hfopenllm_v2/GPQA": 0.3062,
-        "hfopenllm_v2/MUSR": 0.4487,
-        "hfopenllm_v2/MMLU-PRO": 0.396
+        "hfopenllm_v2/IFEval": 0.7917,
+        "hfopenllm_v2/BBH": 0.5109,
+        "hfopenllm_v2/MATH Level 5": 0.1088,
+        "hfopenllm_v2/GPQA": 0.2878,
+        "hfopenllm_v2/MUSR": 0.4136,
+        "hfopenllm_v2/MMLU-PRO": 0.3876
       }
     },
     {
diff --git a/data/developers/dfurman.json b/data/developers/dfurman.json
index 7e28f4da929deb69b4028e08d70bcf7cf516d943..2947dc3ef503295f24886c787e729305dcebb026 100644
--- a/data/developers/dfurman.json
+++ b/data/developers/dfurman.json
@@ -35,12 +35,12 @@
       "developer": "dfurman",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "hfopenllm_v2/IFEval": 0.3,
-        "hfopenllm_v2/BBH": 0.3853,
-        "hfopenllm_v2/MATH Level 5": 0.0415,
-        "hfopenllm_v2/GPQA": 0.2617,
-        "hfopenllm_v2/MUSR": 0.3579,
-        "hfopenllm_v2/MMLU-PRO": 0.2281
+        "hfopenllm_v2/IFEval": 0.2835,
+        "hfopenllm_v2/BBH": 0.3842,
+        "hfopenllm_v2/MATH Level 5": 0.0521,
+        "hfopenllm_v2/GPQA": 0.2609,
+        "hfopenllm_v2/MUSR": 0.3566,
+        "hfopenllm_v2/MMLU-PRO": 0.2298
       }
     },
     {
diff --git a/data/developers/epistemeai.json b/data/developers/epistemeai.json
index ae59684b2ae8edda61f6033386c80ae35c1570fc..11b25cd31eead1ba78e7fde536703493137e208b 100644
--- a/data/developers/epistemeai.json
+++ b/data/developers/epistemeai.json
@@ -231,12 +231,12 @@
       "developer": "EpistemeAI",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "hfopenllm_v2/IFEval": 0.7305,
-        "hfopenllm_v2/BBH": 0.4649,
-        "hfopenllm_v2/MATH Level 5": 0.1397,
-        "hfopenllm_v2/GPQA": 0.2659,
-        "hfopenllm_v2/MUSR": 0.3209,
-        "hfopenllm_v2/MMLU-PRO": 0.348
+        "hfopenllm_v2/IFEval": 0.7207,
+        "hfopenllm_v2/BBH": 0.461,
+        "hfopenllm_v2/MATH Level 5": 0.1314,
+        "hfopenllm_v2/GPQA": 0.2701,
+        "hfopenllm_v2/MUSR": 0.3432,
+        "hfopenllm_v2/MMLU-PRO": 0.3354
       }
     },
     {
diff --git a/data/developers/etherll.json b/data/developers/etherll.json
index 6a72dd37a279f4d76a8244a057714c910854bcd2..2be2455f8558b72fcbd342c72cc671c443f3155e 100644
--- a/data/developers/etherll.json
+++ b/data/developers/etherll.json
@@ -35,12 +35,12 @@
       "developer": "Etherll",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "hfopenllm_v2/IFEval": 0.6106,
-        "hfopenllm_v2/BBH": 0.5347,
-        "hfopenllm_v2/MATH Level 5": 0.1548,
-        "hfopenllm_v2/GPQA": 0.3146,
-        "hfopenllm_v2/MUSR": 0.3991,
-        "hfopenllm_v2/MMLU-PRO": 0.3752
+        "hfopenllm_v2/IFEval": 0.4672,
+        "hfopenllm_v2/BBH": 0.5013,
+        "hfopenllm_v2/MATH Level 5": 0.0279,
+        "hfopenllm_v2/GPQA": 0.2861,
+        "hfopenllm_v2/MUSR": 0.386,
+        "hfopenllm_v2/MMLU-PRO": 0.3482
       }
     },
     {
diff --git a/data/developers/goekdeniz-guelmez.json b/data/developers/goekdeniz-guelmez.json
index e903240eb11157a57a20b31274250b901066286d..e3a743ff451afc2206e344fc708fd30240018483 100644
--- a/data/developers/goekdeniz-guelmez.json
+++ b/data/developers/goekdeniz-guelmez.json
@@ -63,12 +63,12 @@
       "developer": "Goekdeniz-Guelmez",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "hfopenllm_v2/IFEval": 0.3472,
-        "hfopenllm_v2/BBH": 0.3268,
-        "hfopenllm_v2/MATH Level 5": 0.0891,
-        "hfopenllm_v2/GPQA": 0.2517,
-        "hfopenllm_v2/MUSR": 0.3262,
-        "hfopenllm_v2/MMLU-PRO": 0.1641
+        "hfopenllm_v2/IFEval": 0.3417,
+        "hfopenllm_v2/BBH": 0.3292,
+        "hfopenllm_v2/MATH Level 5": 0.0023,
+        "hfopenllm_v2/GPQA": 0.2576,
+        "hfopenllm_v2/MUSR": 0.3249,
+        "hfopenllm_v2/MMLU-PRO": 0.1638
       }
     },
     {
diff --git a/data/developers/google.json b/data/developers/google.json
index a447ddbc58f3e10c0347885b529d40f4033f2cb3..d2c89d05cf05ad4bda3e0747fb0e85f41c1968c7 100644
--- a/data/developers/google.json
+++ b/data/developers/google.json
@@ -157,8 +157,6 @@
       "developer": "Google",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "ace/Overall Score": 0.47,
-        "ace/Gaming Score": 0.509,
         "apex-agents/Overall Pass@1": 0.184,
         "apex-agents/Overall Pass@8": 0.373,
         "apex-agents/Overall Mean Score": 0.341,
@@ -166,6 +164,8 @@
         "apex-agents/Management Consulting Pass@1": 0.124,
         "apex-agents/Corporate Law Pass@1": 0.239,
         "apex-agents/Corporate Lawyer Mean Score": 0.487,
+        "ace/Overall Score": 0.47,
+        "ace/Gaming Score": 0.509,
         "apex-v1/Overall Score": 0.643,
         "apex-v1/Consulting Score": 0.64,
         "apex-v1/Investment Banking Score": 0.63
@@ -861,7 +861,7 @@
       "developer": "Google",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "terminal-bench-2.0/terminal-bench-2.0": 47.4
+        "terminal-bench-2.0/terminal-bench-2.0": 51.0
       }
     },
     {
@@ -870,7 +870,7 @@
       "developer": "Google",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "terminal-bench-2.0/terminal-bench-2.0": 56.0
+        "terminal-bench-2.0/terminal-bench-2.0": 56.9
       }
     },
     {
@@ -879,8 +879,8 @@
       "developer": "Google",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "appworld_test_normal/appworld/test_normal": 0.55,
-        "browsecompplus/browsecompplus": 0.3333,
+        "appworld_test_normal/appworld/test_normal": 0.36,
+        "browsecompplus/browsecompplus": 0.48,
         "global-mmlu-lite/Global MMLU Lite": 0.9453,
         "global-mmlu-lite/Culturally Sensitive": 0.9397,
         "global-mmlu-lite/Culturally Agnostic": 0.9509,
@@ -902,7 +902,7 @@
         "global-mmlu-lite/Burmese": 0.9425,
         "swe-bench/swe-bench": 0.71,
         "tau-bench-2_airline/tau-bench-2/airline": 0.68,
-        "tau-bench-2_retail/tau-bench-2/retail": 0.73,
+        "tau-bench-2_retail/tau-bench-2/retail": 0.7805,
         "tau-bench-2_telecom/tau-bench-2/telecom": 0.73
       }
     },
diff --git a/data/developers/guilhermenaturaumana.json b/data/developers/guilhermenaturaumana.json
index bc6bb765fac527e1a43413f17dc37f0bfd85ba71..42443971cc3612439e60073a685d6fc6ddf14fe4 100644
--- a/data/developers/guilhermenaturaumana.json
+++ b/data/developers/guilhermenaturaumana.json
@@ -7,12 +7,12 @@
       "developer": "GuilhermeNaturaUmana",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "hfopenllm_v2/IFEval": 0.4985,
-        "hfopenllm_v2/BBH": 0.5645,
-        "hfopenllm_v2/MATH Level 5": 0.2576,
-        "hfopenllm_v2/GPQA": 0.3003,
-        "hfopenllm_v2/MUSR": 0.4373,
-        "hfopenllm_v2/MMLU-PRO": 0.4429
+        "hfopenllm_v2/IFEval": 0.4791,
+        "hfopenllm_v2/BBH": 0.5649,
+        "hfopenllm_v2/MATH Level 5": 0.25,
+        "hfopenllm_v2/GPQA": 0.2995,
+        "hfopenllm_v2/MUSR": 0.4439,
+        "hfopenllm_v2/MMLU-PRO": 0.4408
       }
     }
   ]
diff --git a/data/developers/huggingfacetb.json b/data/developers/huggingfacetb.json
index 1df25de945ccaf98a06fb9f3b47618bba05613d9..912c5d4a2004a890736a0d6051d6fabe190615d4 100644
--- a/data/developers/huggingfacetb.json
+++ b/data/developers/huggingfacetb.json
@@ -161,12 +161,12 @@
       "developer": "HuggingFaceTB",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "hfopenllm_v2/IFEval": 0.083,
-        "hfopenllm_v2/BBH": 0.3053,
-        "hfopenllm_v2/MATH Level 5": 0.0083,
-        "hfopenllm_v2/GPQA": 0.2651,
-        "hfopenllm_v2/MUSR": 0.3423,
-        "hfopenllm_v2/MMLU-PRO": 0.1126
+        "hfopenllm_v2/IFEval": 0.3842,
+        "hfopenllm_v2/BBH": 0.3144,
+        "hfopenllm_v2/MATH Level 5": 0.0151,
+        "hfopenllm_v2/GPQA": 0.255,
+        "hfopenllm_v2/MUSR": 0.3461,
+        "hfopenllm_v2/MMLU-PRO": 0.1117
       }
     }
   ]
diff --git a/data/developers/icefog72.json b/data/developers/icefog72.json
index 0ea5ae912613ba6349dc7eed95da5f8d3afd5dbe..7e3fc1f7a7c9a270611dd8a76e50d06bd5496253 100644
--- a/data/developers/icefog72.json
+++ b/data/developers/icefog72.json
@@ -813,20 +813,6 @@
         "hfopenllm_v2/MMLU-PRO": 0.3103
       }
     },
-    {
-      "id": "icefog72/IceSakeV6RP-7b",
-      "name": "IceSakeV6RP-7b",
-      "developer": "icefog72",
-      "evaluator_relationship": null,
-      "benchmark_scores": {
-        "hfopenllm_v2/IFEval": 0.5033,
-        "hfopenllm_v2/BBH": 0.4976,
-        "hfopenllm_v2/MATH Level 5": 0.0619,
-        "hfopenllm_v2/GPQA": 0.2911,
-        "hfopenllm_v2/MUSR": 0.42,
-        "hfopenllm_v2/MMLU-PRO": 0.3093
-      }
-    },
     {
       "id": "icefog72/IceSakeV8RP-7b",
       "name": "IceSakeV8RP-7b",
diff --git a/data/developers/infly.json b/data/developers/infly.json
index d497bf1e2632542284e99f21127cba81c8ed1b97..fe3f0dc6f7a4b2c08dd2895544fd05de4f16df3c 100644
--- a/data/developers/infly.json
+++ b/data/developers/infly.json
@@ -7,16 +7,16 @@
       "developer": "infly",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "reward-bench/Score": 0.9511,
+        "reward-bench/Score": 0.7648,
+        "reward-bench/Chat": 0.9665,
+        "reward-bench/Chat Hard": 0.9101,
+        "reward-bench/Safety": 0.9644,
+        "reward-bench/Reasoning": 0.9912,
         "reward-bench/Factuality": 0.7411,
         "reward-bench/Precise IF": 0.4188,
         "reward-bench/Math": 0.6995,
-        "reward-bench/Safety": 0.9365,
         "reward-bench/Focus": 0.903,
-        "reward-bench/Ties": 0.8622,
-        "reward-bench/Chat": 0.9665,
-        "reward-bench/Chat Hard": 0.9101,
-        "reward-bench/Reasoning": 0.9912
+        "reward-bench/Ties": 0.8622
       }
     }
   ]
diff --git a/data/developers/internlm.json b/data/developers/internlm.json
index fbcc7249ad65cfb92e1e09809d6765ef54a982e2..3995d91bd1934deb8a0118739d074676cf30299b 100644
--- a/data/developers/internlm.json
+++ b/data/developers/internlm.json
@@ -21,16 +21,16 @@
       "developer": "internlm",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "reward-bench/Score": 0.3902,
-        "reward-bench/Chat": 0.9358,
-        "reward-bench/Chat Hard": 0.6623,
-        "reward-bench/Safety": 0.4711,
-        "reward-bench/Reasoning": 0.8724,
+        "reward-bench/Score": 0.8217,
         "reward-bench/Factuality": 0.2758,
         "reward-bench/Precise IF": 0.3625,
         "reward-bench/Math": 0.4426,
+        "reward-bench/Safety": 0.8162,
         "reward-bench/Focus": 0.596,
-        "reward-bench/Ties": 0.1934
+        "reward-bench/Ties": 0.1934,
+        "reward-bench/Chat": 0.9358,
+        "reward-bench/Chat Hard": 0.6623,
+        "reward-bench/Reasoning": 0.8724
       }
     },
     {
@@ -71,16 +71,16 @@
       "developer": "internlm",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "reward-bench/Score": 0.5335,
-        "reward-bench/Chat": 0.9916,
-        "reward-bench/Chat Hard": 0.6952,
-        "reward-bench/Safety": 0.5956,
-        "reward-bench/Reasoning": 0.9453,
+        "reward-bench/Score": 0.8759,
         "reward-bench/Factuality": 0.4211,
         "reward-bench/Precise IF": 0.4,
         "reward-bench/Math": 0.5628,
+        "reward-bench/Safety": 0.8716,
         "reward-bench/Focus": 0.7051,
-        "reward-bench/Ties": 0.5164
+        "reward-bench/Ties": 0.5164,
+        "reward-bench/Chat": 0.9916,
+        "reward-bench/Chat Hard": 0.6952,
+        "reward-bench/Reasoning": 0.9453
       }
     },
     {
diff --git a/data/developers/jaspionjader.json b/data/developers/jaspionjader.json
index 9d9d1e268e56a9945ae657deca0493de6a22ce3d..053d128582b4aa02040ae51cd0577288669f17e5 100644
--- a/data/developers/jaspionjader.json
+++ b/data/developers/jaspionjader.json
@@ -1477,12 +1477,12 @@
       "developer": "jaspionjader",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "hfopenllm_v2/IFEval": 0.4418,
-        "hfopenllm_v2/BBH": 0.5406,
-        "hfopenllm_v2/MATH Level 5": 0.1352,
-        "hfopenllm_v2/GPQA": 0.3062,
+        "hfopenllm_v2/IFEval": 0.4345,
+        "hfopenllm_v2/BBH": 0.5419,
+        "hfopenllm_v2/MATH Level 5": 0.1292,
+        "hfopenllm_v2/GPQA": 0.3087,
         "hfopenllm_v2/MUSR": 0.4277,
-        "hfopenllm_v2/MMLU-PRO": 0.386
+        "hfopenllm_v2/MMLU-PRO": 0.3854
       }
     },
     {
diff --git a/data/developers/leroydyer.json b/data/developers/leroydyer.json
index 119d29bab457804b8d64637d339b1f72d7389de3..7fdecb6a1e65adfe5948ae6f60f4bc236a803ac7 100644
--- a/data/developers/leroydyer.json
+++ b/data/developers/leroydyer.json
@@ -679,12 +679,12 @@
       "developer": "LeroyDyer",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "hfopenllm_v2/IFEval": 0.3036,
-        "hfopenllm_v2/BBH": 0.4575,
+        "hfopenllm_v2/IFEval": 0.3066,
+        "hfopenllm_v2/BBH": 0.4577,
         "hfopenllm_v2/MATH Level 5": 0.0446,
-        "hfopenllm_v2/GPQA": 0.3012,
-        "hfopenllm_v2/MUSR": 0.4253,
-        "hfopenllm_v2/MMLU-PRO": 0.2329
+        "hfopenllm_v2/GPQA": 0.2995,
+        "hfopenllm_v2/MUSR": 0.4254,
+        "hfopenllm_v2/MMLU-PRO": 0.2318
       }
     },
     {
@@ -707,12 +707,12 @@
       "developer": "LeroyDyer",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "hfopenllm_v2/IFEval": 0.3798,
-        "hfopenllm_v2/BBH": 0.4483,
-        "hfopenllm_v2/MATH Level 5": 0.04,
-        "hfopenllm_v2/GPQA": 0.3129,
-        "hfopenllm_v2/MUSR": 0.4148,
-        "hfopenllm_v2/MMLU-PRO": 0.2389
+        "hfopenllm_v2/IFEval": 0.3579,
+        "hfopenllm_v2/BBH": 0.4477,
+        "hfopenllm_v2/MATH Level 5": 0.0423,
+        "hfopenllm_v2/GPQA": 0.3096,
+        "hfopenllm_v2/MUSR": 0.4134,
+        "hfopenllm_v2/MMLU-PRO": 0.2376
       }
     },
     {
diff --git a/data/developers/lxzgordon.json b/data/developers/lxzgordon.json
index 7f802cf733857054e01537f3ecf745a3fdb38a05..e4ace3cc8f7193c8c711403c980535ee73fdd6d3 100644
--- a/data/developers/lxzgordon.json
+++ b/data/developers/lxzgordon.json
@@ -20,16 +20,16 @@
       "developer": "LxzGordon",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "reward-bench/Score": 0.7394,
-        "reward-bench/Chat": 0.9553,
-        "reward-bench/Chat Hard": 0.8816,
-        "reward-bench/Safety": 0.9178,
-        "reward-bench/Reasoning": 0.9698,
+        "reward-bench/Score": 0.9294,
         "reward-bench/Factuality": 0.6884,
         "reward-bench/Precise IF": 0.45,
         "reward-bench/Math": 0.6393,
+        "reward-bench/Safety": 0.9108,
         "reward-bench/Focus": 0.9758,
-        "reward-bench/Ties": 0.7653
+        "reward-bench/Ties": 0.7653,
+        "reward-bench/Chat": 0.9553,
+        "reward-bench/Chat Hard": 0.8816,
+        "reward-bench/Reasoning": 0.9698
       }
     }
   ]
diff --git a/data/developers/magpie-align.json b/data/developers/magpie-align.json
index 0dc0a43e89bb456a61006caa30051add55effb08..155a416e715db19186e6af681f6736ea9ed101d1 100644
--- a/data/developers/magpie-align.json
+++ b/data/developers/magpie-align.json
@@ -35,12 +35,12 @@
       "developer": "Magpie-Align",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "hfopenllm_v2/IFEval": 0.4027,
-        "hfopenllm_v2/BBH": 0.4789,
-        "hfopenllm_v2/MATH Level 5": 0.0461,
-        "hfopenllm_v2/GPQA": 0.2768,
-        "hfopenllm_v2/MUSR": 0.3087,
-        "hfopenllm_v2/MMLU-PRO": 0.3001
+        "hfopenllm_v2/IFEval": 0.4118,
+        "hfopenllm_v2/BBH": 0.4811,
+        "hfopenllm_v2/MATH Level 5": 0.034,
+        "hfopenllm_v2/GPQA": 0.2752,
+        "hfopenllm_v2/MUSR": 0.3047,
+        "hfopenllm_v2/MMLU-PRO": 0.3006
       }
     },
     {
diff --git a/data/developers/microsoft.json b/data/developers/microsoft.json
index 5b22c3abc624b7d65a825afffb8ded406b5eb203..ac7ddab4c9378bc179c9df1d82dca24687067465 100644
--- a/data/developers/microsoft.json
+++ b/data/developers/microsoft.json
@@ -225,12 +225,12 @@
       "developer": "microsoft",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "hfopenllm_v2/IFEval": 0.5477,
-        "hfopenllm_v2/BBH": 0.5491,
-        "hfopenllm_v2/MATH Level 5": 0.1639,
-        "hfopenllm_v2/GPQA": 0.3322,
-        "hfopenllm_v2/MUSR": 0.4284,
-        "hfopenllm_v2/MMLU-PRO": 0.4022
+        "hfopenllm_v2/IFEval": 0.5613,
+        "hfopenllm_v2/BBH": 0.5676,
+        "hfopenllm_v2/MATH Level 5": 0.1163,
+        "hfopenllm_v2/GPQA": 0.3196,
+        "hfopenllm_v2/MUSR": 0.395,
+        "hfopenllm_v2/MMLU-PRO": 0.3866
       }
     },
     {
@@ -341,12 +341,12 @@
       "developer": "microsoft",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "hfopenllm_v2/IFEval": 0.0585,
-        "hfopenllm_v2/BBH": 0.6691,
-        "hfopenllm_v2/MATH Level 5": 0.3165,
-        "hfopenllm_v2/GPQA": 0.406,
+        "hfopenllm_v2/IFEval": 0.0488,
+        "hfopenllm_v2/BBH": 0.6703,
+        "hfopenllm_v2/MATH Level 5": 0.2787,
+        "hfopenllm_v2/GPQA": 0.401,
         "hfopenllm_v2/MUSR": 0.5034,
-        "hfopenllm_v2/MMLU-PRO": 0.5287
+        "hfopenllm_v2/MMLU-PRO": 0.5295
       }
     },
     {
diff --git a/data/developers/minimax.json b/data/developers/minimax.json
index 3eb98fb6a6609e5f1cc4d74a47ecc2b74aaa9bb0..b575a16ccd7fb272ceb4b3067b0a9e48f65cff08 100644
--- a/data/developers/minimax.json
+++ b/data/developers/minimax.json
@@ -25,7 +25,7 @@
       "developer": "MiniMax",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "terminal-bench-2.0/terminal-bench-2.0": 36.6
+        "terminal-bench-2.0/terminal-bench-2.0": 29.2
       }
     },
     {
diff --git a/data/developers/mistralai.json b/data/developers/mistralai.json
index 168bb98ff1b313fc7d40f024df899fec3a02671f..14d2f60be9e807210d185f950d2f81080246d7d7 100644
--- a/data/developers/mistralai.json
+++ b/data/developers/mistralai.json
@@ -513,12 +513,12 @@
       "developer": "mistralai",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "hfopenllm_v2/IFEval": 0.667,
-        "hfopenllm_v2/BBH": 0.5213,
-        "hfopenllm_v2/MATH Level 5": 0.1435,
-        "hfopenllm_v2/GPQA": 0.3238,
-        "hfopenllm_v2/MUSR": 0.3632,
-        "hfopenllm_v2/MMLU-PRO": 0.396
+        "hfopenllm_v2/IFEval": 0.6283,
+        "hfopenllm_v2/BBH": 0.583,
+        "hfopenllm_v2/MATH Level 5": 0.2039,
+        "hfopenllm_v2/GPQA": 0.3331,
+        "hfopenllm_v2/MUSR": 0.4063,
+        "hfopenllm_v2/MMLU-PRO": 0.4099
       }
     },
     {
@@ -718,12 +718,12 @@
       "developer": "mistralai",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "hfopenllm_v2/IFEval": 0.2415,
-        "hfopenllm_v2/BBH": 0.5087,
-        "hfopenllm_v2/MATH Level 5": 0.102,
-        "hfopenllm_v2/GPQA": 0.3138,
-        "hfopenllm_v2/MUSR": 0.4321,
-        "hfopenllm_v2/MMLU-PRO": 0.385
+        "hfopenllm_v2/IFEval": 0.2326,
+        "hfopenllm_v2/BBH": 0.5098,
+        "hfopenllm_v2/MATH Level 5": 0.0937,
+        "hfopenllm_v2/GPQA": 0.3205,
+        "hfopenllm_v2/MUSR": 0.4413,
+        "hfopenllm_v2/MMLU-PRO": 0.3871
       }
     },
     {
diff --git a/data/developers/mlabonne.json b/data/developers/mlabonne.json
index 2620a8c4e8931697abdcd44e4a4aae7c1e430da5..be86bd7fe732025f133b06dc7c412aa5e56b7119 100644
--- a/data/developers/mlabonne.json
+++ b/data/developers/mlabonne.json
@@ -161,12 +161,12 @@
       "developer": "mlabonne",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "hfopenllm_v2/IFEval": 0.7561,
-        "hfopenllm_v2/BBH": 0.5111,
-        "hfopenllm_v2/MATH Level 5": 0.0906,
-        "hfopenllm_v2/GPQA": 0.3062,
-        "hfopenllm_v2/MUSR": 0.4019,
-        "hfopenllm_v2/MMLU-PRO": 0.3841
+        "hfopenllm_v2/IFEval": 0.4162,
+        "hfopenllm_v2/BBH": 0.5124,
+        "hfopenllm_v2/MATH Level 5": 0.0853,
+        "hfopenllm_v2/GPQA": 0.3029,
+        "hfopenllm_v2/MUSR": 0.415,
+        "hfopenllm_v2/MMLU-PRO": 0.3802
       }
     },
     {
diff --git a/data/developers/moonshot_ai.json b/data/developers/moonshot_ai.json
index 746185ce773a539bd025922ab856fdcf2f8a1d9f..d83f11402fcca0c39c33d09eed495f2aefd69384 100644
--- a/data/developers/moonshot_ai.json
+++ b/data/developers/moonshot_ai.json
@@ -7,7 +7,7 @@
       "developer": "Moonshot AI",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "terminal-bench-2.0/terminal-bench-2.0": 27.8
+        "terminal-bench-2.0/terminal-bench-2.0": 26.7
       }
     },
     {
diff --git a/data/developers/multiple.json b/data/developers/multiple.json
index 34cdb844d495e12fd3a3820204fbda313306e211..e235ffc0287578be5fd9fdf3ba4e4e1b232b5df8 100644
--- a/data/developers/multiple.json
+++ b/data/developers/multiple.json
@@ -7,7 +7,7 @@
       "developer": "Multiple",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "terminal-bench-2.0/terminal-bench-2.0": 72.4
+        "terminal-bench-2.0/terminal-bench-2.0": 71.0
       }
     }
   ]
diff --git a/data/developers/nicolinho.json b/data/developers/nicolinho.json
index 79bf445ae201aa8b9add0559d92e4abd4fd3bebb..551d4a5de698babd0e830b509f51bb11f4dd2ac7 100644
--- a/data/developers/nicolinho.json
+++ b/data/developers/nicolinho.json
@@ -7,16 +7,16 @@
       "developer": "nicolinho",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "reward-bench/Score": 0.7667,
-        "reward-bench/Chat": 0.9665,
-        "reward-bench/Chat Hard": 0.9013,
-        "reward-bench/Safety": 0.9578,
-        "reward-bench/Reasoning": 0.9826,
+        "reward-bench/Score": 0.9444,
         "reward-bench/Factuality": 0.7853,
         "reward-bench/Precise IF": 0.3719,
         "reward-bench/Math": 0.6995,
+        "reward-bench/Safety": 0.927,
         "reward-bench/Focus": 0.9535,
-        "reward-bench/Ties": 0.8321
+        "reward-bench/Ties": 0.8321,
+        "reward-bench/Chat": 0.9665,
+        "reward-bench/Chat Hard": 0.9013,
+        "reward-bench/Reasoning": 0.9826
       }
     },
     {
@@ -51,16 +51,16 @@
       "developer": "nicolinho",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "reward-bench/Score": 0.7074,
-        "reward-bench/Chat": 0.9637,
-        "reward-bench/Chat Hard": 0.8684,
-        "reward-bench/Safety": 0.9467,
-        "reward-bench/Reasoning": 0.9677,
+        "reward-bench/Score": 0.9314,
         "reward-bench/Factuality": 0.6653,
         "reward-bench/Precise IF": 0.4062,
         "reward-bench/Math": 0.612,
+        "reward-bench/Safety": 0.9257,
         "reward-bench/Focus": 0.8909,
-        "reward-bench/Ties": 0.7234
+        "reward-bench/Ties": 0.7234,
+        "reward-bench/Chat": 0.9637,
+        "reward-bench/Chat Hard": 0.8684,
+        "reward-bench/Reasoning": 0.9677
       }
     }
   ]
diff --git a/data/developers/nousresearch.json b/data/developers/nousresearch.json
index 68e17c3374e0831b38026cc5c7fe37546bb1fc55..5eca3534d830aded2e15a419e7392ebd605b4769 100644
--- a/data/developers/nousresearch.json
+++ b/data/developers/nousresearch.json
@@ -200,6 +200,20 @@
         "hfopenllm_v2/MMLU-PRO": 0.232
       }
     },
+    {
+      "id": "NousResearch/Yarn-Llama-2-7b-128k",
+      "name": "Yarn-Llama-2-7b-128k",
+      "developer": "NousResearch",
+      "evaluator_relationship": null,
+      "benchmark_scores": {
+        "hfopenllm_v2/IFEval": 0.1485,
+        "hfopenllm_v2/BBH": 0.3248,
+        "hfopenllm_v2/MATH Level 5": 0.0151,
+        "hfopenllm_v2/GPQA": 0.2601,
+        "hfopenllm_v2/MUSR": 0.3967,
+        "hfopenllm_v2/MMLU-PRO": 0.1791
+      }
+    },
     {
       "id": "NousResearch/Yarn-Llama-2-7b-64k",
       "name": "Yarn-Llama-2-7b-64k",
diff --git a/data/developers/ontocord.json b/data/developers/ontocord.json
index add41dbe183800ebed90c916e0b704c974dd50e7..c16f4cbacdda3485b721f459b079923a6793a670 100644
--- a/data/developers/ontocord.json
+++ b/data/developers/ontocord.json
@@ -273,12 +273,12 @@
       "developer": "ontocord",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "hfopenllm_v2/IFEval": 0.1162,
-        "hfopenllm_v2/BBH": 0.3184,
-        "hfopenllm_v2/MATH Level 5": 0.0076,
-        "hfopenllm_v2/GPQA": 0.2634,
-        "hfopenllm_v2/MUSR": 0.3447,
-        "hfopenllm_v2/MMLU-PRO": 0.1124
+        "hfopenllm_v2/IFEval": 0.1128,
+        "hfopenllm_v2/BBH": 0.3171,
+        "hfopenllm_v2/MATH Level 5": 0.0113,
+        "hfopenllm_v2/GPQA": 0.2685,
+        "hfopenllm_v2/MUSR": 0.346,
+        "hfopenllm_v2/MMLU-PRO": 0.1129
       }
     },
     {
diff --git a/data/developers/openai.json b/data/developers/openai.json
index 463a516253b52dd581eb26a0054c21d8f415cdc5..1d144bd538c9cee7f94220b8970cc16ed56fa6ae 100644
--- a/data/developers/openai.json
+++ b/data/developers/openai.json
@@ -772,16 +772,16 @@
         "helm_mmlu/Virology": 0.578,
         "helm_mmlu/World Religions": 0.883,
         "helm_mmlu/Mean win rate": 0.52,
-        "reward-bench/Score": 0.8673,
+        "reward-bench/Score": 0.6493,
+        "reward-bench/Chat": 0.9609,
+        "reward-bench/Chat Hard": 0.761,
+        "reward-bench/Safety": 0.8619,
+        "reward-bench/Reasoning": 0.8661,
         "reward-bench/Factuality": 0.5684,
         "reward-bench/Precise IF": 0.3312,
         "reward-bench/Math": 0.623,
-        "reward-bench/Safety": 0.8811,
         "reward-bench/Focus": 0.7293,
-        "reward-bench/Ties": 0.7819,
-        "reward-bench/Chat": 0.9609,
-        "reward-bench/Chat Hard": 0.761,
-        "reward-bench/Reasoning": 0.8661
+        "reward-bench/Ties": 0.7819
       }
     },
     {
@@ -859,16 +859,16 @@
         "helm_mmlu/Virology": 0.536,
         "helm_mmlu/World Religions": 0.86,
         "helm_mmlu/Mean win rate": 0.774,
-        "reward-bench/Score": 0.8007,
+        "reward-bench/Score": 0.5796,
+        "reward-bench/Chat": 0.9497,
+        "reward-bench/Chat Hard": 0.6075,
+        "reward-bench/Safety": 0.7667,
+        "reward-bench/Reasoning": 0.8374,
         "reward-bench/Factuality": 0.4105,
         "reward-bench/Precise IF": 0.3438,
         "reward-bench/Math": 0.5191,
-        "reward-bench/Safety": 0.8081,
         "reward-bench/Focus": 0.7414,
-        "reward-bench/Ties": 0.6962,
-        "reward-bench/Chat": 0.9497,
-        "reward-bench/Chat Hard": 0.6075,
-        "reward-bench/Reasoning": 0.8374
+        "reward-bench/Ties": 0.6962
       }
     },
     {
@@ -911,9 +911,9 @@
         "helm_capabilities/IFEval": 0.875,
         "helm_capabilities/WildBench": 0.857,
         "helm_capabilities/Omni-MATH": 0.647,
-        "livecodebenchpro/Hard Problems": 0.04225352112676056,
-        "livecodebenchpro/Medium Problems": 0.4084507042253521,
-        "livecodebenchpro/Easy Problems": 0.8873239436619719
+        "livecodebenchpro/Hard Problems": 0.0423,
+        "livecodebenchpro/Medium Problems": 0.4085,
+        "livecodebenchpro/Easy Problems": 0.9014
       }
     },
     {
@@ -931,7 +931,7 @@
       "developer": "OpenAI",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "terminal-bench-2.0/terminal-bench-2.0": 24.0
+        "terminal-bench-2.0/terminal-bench-2.0": 31.9
       }
     },
     {
@@ -954,7 +954,7 @@
       "developer": "OpenAI",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "terminal-bench-2.0/terminal-bench-2.0": 11.5
+        "terminal-bench-2.0/terminal-bench-2.0": 7.0
       }
     },
     {
@@ -986,7 +986,7 @@
       "developer": "OpenAI",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "terminal-bench-2.0/terminal-bench-2.0": 57.8
+        "terminal-bench-2.0/terminal-bench-2.0": 53.5
       }
     },
     {
@@ -1013,7 +1013,7 @@
       "developer": "OpenAI",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "terminal-bench-2.0/terminal-bench-2.0": 62.9
+        "terminal-bench-2.0/terminal-bench-2.0": 60.7
       }
     },
     {
@@ -1023,14 +1023,14 @@
       "evaluator_relationship": null,
       "benchmark_scores": {
         "appworld_test_normal/appworld/test_normal": 0.0,
-        "browsecompplus/browsecompplus": 0.43,
+        "browsecompplus/browsecompplus": 0.26,
         "livecodebenchpro/Hard Problems": 0.1594,
         "livecodebenchpro/Medium Problems": 0.5211,
         "livecodebenchpro/Easy Problems": 0.9014,
-        "swe-bench/swe-bench": 0.5455,
+        "swe-bench/swe-bench": 0.57,
         "tau-bench-2_airline/tau-bench-2/airline": 0.6,
-        "tau-bench-2_retail/tau-bench-2/retail": 0.73,
-        "tau-bench-2_telecom/tau-bench-2/telecom": 0.71
+        "tau-bench-2_retail/tau-bench-2/retail": 0.68,
+        "tau-bench-2_telecom/tau-bench-2/telecom": 0.5354
       }
     },
     {
@@ -1048,7 +1048,7 @@
       "developer": "OpenAI",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "terminal-bench-2.0/terminal-bench-2.0": 77.3
+        "terminal-bench-2.0/terminal-bench-2.0": 74.6
       }
     },
     {
@@ -1112,7 +1112,7 @@
         "livecodebenchpro/Hard Problems": 0.0,
         "livecodebenchpro/Medium Problems": 0.11267605633802817,
         "livecodebenchpro/Easy Problems": 0.6619718309859155,
-        "terminal-bench-2.0/terminal-bench-2.0": 18.7
+        "terminal-bench-2.0/terminal-bench-2.0": 14.2
       }
     },
     {
@@ -1233,9 +1233,9 @@
         "helm_capabilities/IFEval": 0.929,
         "helm_capabilities/WildBench": 0.854,
         "helm_capabilities/Omni-MATH": 0.72,
-        "livecodebenchpro/Hard Problems": 0.014084507042253521,
-        "livecodebenchpro/Medium Problems": 0.30985915492957744,
-        "livecodebenchpro/Easy Problems": 0.8873239436619719
+        "livecodebenchpro/Hard Problems": 0.0143,
+        "livecodebenchpro/Medium Problems": 0.2923,
+        "livecodebenchpro/Easy Problems": 0.8571
       }
     },
     {
diff --git a/data/developers/openassistant.json b/data/developers/openassistant.json
index 7e4cf042377b82fe85282ade845062094d3d9218..0d3e3f32693fa46354d7063e0615e0d45e8641c5 100644
--- a/data/developers/openassistant.json
+++ b/data/developers/openassistant.json
@@ -7,17 +7,17 @@
       "developer": "OpenAssistant",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "reward-bench/Score": 0.2653,
-        "reward-bench/Chat": 0.9246,
-        "reward-bench/Chat Hard": 0.3728,
-        "reward-bench/Safety": 0.3289,
-        "reward-bench/Reasoning": 0.5855,
-        "reward-bench/Prior Sets (0.5 weight)": 0.6801,
+        "reward-bench/Score": 0.615,
         "reward-bench/Factuality": 0.3979,
         "reward-bench/Precise IF": 0.2875,
         "reward-bench/Math": 0.377,
+        "reward-bench/Safety": 0.5446,
         "reward-bench/Focus": 0.1535,
-        "reward-bench/Ties": 0.047
+        "reward-bench/Ties": 0.047,
+        "reward-bench/Chat": 0.9246,
+        "reward-bench/Chat Hard": 0.3728,
+        "reward-bench/Reasoning": 0.5855,
+        "reward-bench/Prior Sets (0.5 weight)": 0.6801
       }
     },
     {
diff --git a/data/developers/openbmb.json b/data/developers/openbmb.json
index d8dae84054074ce01b5c47fc58b69a148fdc99c0..d6a398c44a61b95d325c54de1768af4a13c46f1f 100644
--- a/data/developers/openbmb.json
+++ b/data/developers/openbmb.json
@@ -68,17 +68,17 @@
       "developer": "openbmb",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "reward-bench/Score": 0.4683,
-        "reward-bench/Chat": 0.9637,
-        "reward-bench/Chat Hard": 0.5548,
-        "reward-bench/Safety": 0.5089,
-        "reward-bench/Reasoning": 0.6244,
-        "reward-bench/Prior Sets (0.5 weight)": 0.7294,
+        "reward-bench/Score": 0.6903,
         "reward-bench/Factuality": 0.5063,
         "reward-bench/Precise IF": 0.3312,
         "reward-bench/Math": 0.5519,
+        "reward-bench/Safety": 0.5986,
         "reward-bench/Focus": 0.6081,
-        "reward-bench/Ties": 0.3036
+        "reward-bench/Ties": 0.3036,
+        "reward-bench/Chat": 0.9637,
+        "reward-bench/Chat Hard": 0.5548,
+        "reward-bench/Reasoning": 0.6244,
+        "reward-bench/Prior Sets (0.5 weight)": 0.7294
       }
     }
   ]
diff --git a/data/developers/pku-alignment.json b/data/developers/pku-alignment.json
index 76e1f41b6171c4fd2a3d35d25df175a75a77a416..0ae80803f93980ecd8558a983e84a1646a1bd7d6 100644
--- a/data/developers/pku-alignment.json
+++ b/data/developers/pku-alignment.json
@@ -7,17 +7,17 @@
       "developer": "PKU-Alignment",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "reward-bench/Score": 0.5798,
+        "reward-bench/Score": 0.3332,
+        "reward-bench/Chat": 0.6173,
+        "reward-bench/Chat Hard": 0.4232,
+        "reward-bench/Safety": 0.7589,
+        "reward-bench/Reasoning": 0.5482,
+        "reward-bench/Prior Sets (0.5 weight)": 0.57,
         "reward-bench/Factuality": 0.3263,
         "reward-bench/Precise IF": 0.2313,
         "reward-bench/Math": 0.3989,
-        "reward-bench/Safety": 0.7351,
         "reward-bench/Focus": 0.2939,
-        "reward-bench/Ties": -0.01,
-        "reward-bench/Chat": 0.6173,
-        "reward-bench/Chat Hard": 0.4232,
-        "reward-bench/Reasoning": 0.5482,
-        "reward-bench/Prior Sets (0.5 weight)": 0.57
+        "reward-bench/Ties": -0.01
       }
     },
     {
@@ -26,17 +26,17 @@
       "developer": "PKU-Alignment",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "reward-bench/Score": 0.1606,
-        "reward-bench/Chat": 0.8184,
-        "reward-bench/Chat Hard": 0.2873,
-        "reward-bench/Safety": 0.1422,
-        "reward-bench/Reasoning": 0.346,
-        "reward-bench/Prior Sets (0.5 weight)": 0.5993,
+        "reward-bench/Score": 0.4727,
         "reward-bench/Factuality": 0.2105,
         "reward-bench/Precise IF": 0.2938,
         "reward-bench/Math": 0.2623,
+        "reward-bench/Safety": 0.3757,
         "reward-bench/Focus": 0.0646,
-        "reward-bench/Ties": -0.01
+        "reward-bench/Ties": -0.01,
+        "reward-bench/Chat": 0.8184,
+        "reward-bench/Chat Hard": 0.2873,
+        "reward-bench/Reasoning": 0.346,
+        "reward-bench/Prior Sets (0.5 weight)": 0.5993
       }
     },
     {
@@ -64,17 +64,17 @@
       "developer": "PKU-Alignment",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "reward-bench/Score": 0.2544,
-        "reward-bench/Chat": 0.8994,
-        "reward-bench/Chat Hard": 0.364,
-        "reward-bench/Safety": 0.3156,
-        "reward-bench/Reasoning": 0.6887,
-        "reward-bench/Prior Sets (0.5 weight)": 0.6171,
+        "reward-bench/Score": 0.6366,
         "reward-bench/Factuality": 0.2168,
         "reward-bench/Precise IF": 0.2562,
         "reward-bench/Math": 0.3825,
+        "reward-bench/Safety": 0.6041,
         "reward-bench/Focus": 0.2606,
-        "reward-bench/Ties": 0.0944
+        "reward-bench/Ties": 0.0944,
+        "reward-bench/Chat": 0.8994,
+        "reward-bench/Chat Hard": 0.364,
+        "reward-bench/Reasoning": 0.6887,
+        "reward-bench/Prior Sets (0.5 weight)": 0.6171
       }
     }
   ]
diff --git a/data/developers/primeintellect.json b/data/developers/primeintellect.json
index 160722785b06f80d9b220dee435fad1245d45495..674a0e3b141480d7e0d33d0a2fe9b205b710216f 100644
--- a/data/developers/primeintellect.json
+++ b/data/developers/primeintellect.json
@@ -8,11 +8,11 @@
       "evaluator_relationship": null,
       "benchmark_scores": {
         "hfopenllm_v2/IFEval": 0.1757,
-        "hfopenllm_v2/BBH": 0.274,
+        "hfopenllm_v2/BBH": 0.276,
         "hfopenllm_v2/MATH Level 5": 0.0,
-        "hfopenllm_v2/GPQA": 0.25,
-        "hfopenllm_v2/MUSR": 0.3753,
-        "hfopenllm_v2/MMLU-PRO": 0.112
+        "hfopenllm_v2/GPQA": 0.2534,
+        "hfopenllm_v2/MUSR": 0.3339,
+        "hfopenllm_v2/MMLU-PRO": 0.1123
       }
     },
     {
diff --git a/data/developers/princeton-nlp.json b/data/developers/princeton-nlp.json
index 10775d33e9c59e099c9bb1a2b84aa429c8a82f44..c2ef64ee6de3b0368749e3cc226eadfed8e75e4e 100644
--- a/data/developers/princeton-nlp.json
+++ b/data/developers/princeton-nlp.json
@@ -49,12 +49,12 @@
       "developer": "princeton-nlp",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "hfopenllm_v2/IFEval": 0.3978,
-        "hfopenllm_v2/BBH": 0.4983,
-        "hfopenllm_v2/MATH Level 5": 0.0582,
-        "hfopenllm_v2/GPQA": 0.281,
-        "hfopenllm_v2/MUSR": 0.425,
-        "hfopenllm_v2/MMLU-PRO": 0.3246
+        "hfopenllm_v2/IFEval": 0.5508,
+        "hfopenllm_v2/BBH": 0.5028,
+        "hfopenllm_v2/MATH Level 5": 0.0529,
+        "hfopenllm_v2/GPQA": 0.2861,
+        "hfopenllm_v2/MUSR": 0.4266,
+        "hfopenllm_v2/MMLU-PRO": 0.3231
       }
     },
     {
diff --git a/data/developers/prithivmlmods.json b/data/developers/prithivmlmods.json
index 88e743a4279f310dec935aed3968189a78be084e..f14f3864a910968b11c756eb8300bd4bd3eea36e 100644
--- a/data/developers/prithivmlmods.json
+++ b/data/developers/prithivmlmods.json
@@ -63,12 +63,12 @@
       "developer": "prithivMLmods",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "hfopenllm_v2/IFEval": 0.6052,
-        "hfopenllm_v2/BBH": 0.6317,
-        "hfopenllm_v2/MATH Level 5": 0.4789,
-        "hfopenllm_v2/GPQA": 0.3742,
-        "hfopenllm_v2/MUSR": 0.486,
-        "hfopenllm_v2/MMLU-PRO": 0.5302
+        "hfopenllm_v2/IFEval": 0.6064,
+        "hfopenllm_v2/BBH": 0.6296,
+        "hfopenllm_v2/MATH Level 5": 0.3708,
+        "hfopenllm_v2/GPQA": 0.3733,
+        "hfopenllm_v2/MUSR": 0.4873,
+        "hfopenllm_v2/MMLU-PRO": 0.5307
       }
     },
     {
diff --git a/data/developers/qingy2019.json b/data/developers/qingy2019.json
index 9e607d380bbf6837078a684f50c178b1c83bab9f..f93967ea7ea0a389f1379b7b85428b832b816fb9 100644
--- a/data/developers/qingy2019.json
+++ b/data/developers/qingy2019.json
@@ -49,12 +49,12 @@
       "developer": "qingy2019",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "hfopenllm_v2/IFEval": 0.6005,
-        "hfopenllm_v2/BBH": 0.6356,
-        "hfopenllm_v2/MATH Level 5": 0.2764,
-        "hfopenllm_v2/GPQA": 0.3691,
+        "hfopenllm_v2/IFEval": 0.6066,
+        "hfopenllm_v2/BBH": 0.635,
+        "hfopenllm_v2/MATH Level 5": 0.3716,
+        "hfopenllm_v2/GPQA": 0.3725,
         "hfopenllm_v2/MUSR": 0.4757,
-        "hfopenllm_v2/MMLU-PRO": 0.5339
+        "hfopenllm_v2/MMLU-PRO": 0.5331
       }
     },
     {
diff --git a/data/developers/quazim0t0.json b/data/developers/quazim0t0.json
index 496082d204a36ed57a388cd540f10080c702a420..135f1135e53ac7da23b4b9457344787d94d6e680 100644
--- a/data/developers/quazim0t0.json
+++ b/data/developers/quazim0t0.json
@@ -105,12 +105,12 @@
       "developer": "Quazim0t0",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "hfopenllm_v2/IFEval": 0.6654,
-        "hfopenllm_v2/BBH": 0.6901,
-        "hfopenllm_v2/MATH Level 5": 0.4698,
-        "hfopenllm_v2/GPQA": 0.3331,
-        "hfopenllm_v2/MUSR": 0.431,
-        "hfopenllm_v2/MMLU-PRO": 0.5426
+        "hfopenllm_v2/IFEval": 0.6718,
+        "hfopenllm_v2/BBH": 0.6891,
+        "hfopenllm_v2/MATH Level 5": 0.4985,
+        "hfopenllm_v2/GPQA": 0.3339,
+        "hfopenllm_v2/MUSR": 0.4323,
+        "hfopenllm_v2/MMLU-PRO": 0.5408
       }
     },
     {
@@ -637,12 +637,12 @@
       "developer": "Quazim0t0",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "hfopenllm_v2/IFEval": 0.2922,
-        "hfopenllm_v2/BBH": 0.6559,
-        "hfopenllm_v2/MATH Level 5": 0.2545,
-        "hfopenllm_v2/GPQA": 0.2659,
-        "hfopenllm_v2/MUSR": 0.3929,
-        "hfopenllm_v2/MMLU-PRO": 0.5207
+        "hfopenllm_v2/IFEval": 0.7016,
+        "hfopenllm_v2/BBH": 0.6942,
+        "hfopenllm_v2/MATH Level 5": 0.4116,
+        "hfopenllm_v2/GPQA": 0.3624,
+        "hfopenllm_v2/MUSR": 0.4571,
+        "hfopenllm_v2/MMLU-PRO": 0.5411
       }
     },
     {
diff --git a/data/developers/qwen.json b/data/developers/qwen.json
index 8996ee46a22c0193f6bf8577a319d9b66b681c8b..727516da8d72881c91634dd8fcd12326550fd1bf 100644
--- a/data/developers/qwen.json
+++ b/data/developers/qwen.json
@@ -775,12 +775,12 @@
       "developer": "Qwen",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "hfopenllm_v2/IFEval": 0.3071,
-        "hfopenllm_v2/BBH": 0.3341,
-        "hfopenllm_v2/MATH Level 5": 0.0,
-        "hfopenllm_v2/GPQA": 0.2576,
-        "hfopenllm_v2/MUSR": 0.3329,
-        "hfopenllm_v2/MMLU-PRO": 0.1697
+        "hfopenllm_v2/IFEval": 0.3153,
+        "hfopenllm_v2/BBH": 0.3322,
+        "hfopenllm_v2/MATH Level 5": 0.1035,
+        "hfopenllm_v2/GPQA": 0.2592,
+        "hfopenllm_v2/MUSR": 0.3342,
+        "hfopenllm_v2/MMLU-PRO": 0.172
       }
     },
     {
diff --git a/data/developers/ray2333.json b/data/developers/ray2333.json
index 0d33fd83045f7f1f2a0352b101b8f653545ad511..535b872cfc093237ac0d0dc85564191f8ac0a72c 100644
--- a/data/developers/ray2333.json
+++ b/data/developers/ray2333.json
@@ -61,16 +61,16 @@
       "developer": "Ray2333",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "reward-bench/Score": 0.5966,
-        "reward-bench/Chat": 0.9302,
-        "reward-bench/Chat Hard": 0.7719,
-        "reward-bench/Safety": 0.9222,
-        "reward-bench/Reasoning": 0.912,
+        "reward-bench/Score": 0.8839,
         "reward-bench/Factuality": 0.5305,
         "reward-bench/Precise IF": 0.3125,
         "reward-bench/Math": 0.5902,
+        "reward-bench/Safety": 0.9216,
         "reward-bench/Focus": 0.7455,
-        "reward-bench/Ties": 0.4788
+        "reward-bench/Ties": 0.4788,
+        "reward-bench/Chat": 0.9302,
+        "reward-bench/Chat Hard": 0.7719,
+        "reward-bench/Reasoning": 0.912
       }
     },
     {
@@ -98,16 +98,16 @@
       "developer": "Ray2333",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "reward-bench/Score": 0.6766,
-        "reward-bench/Chat": 0.9553,
-        "reward-bench/Chat Hard": 0.8618,
-        "reward-bench/Safety": 0.9222,
-        "reward-bench/Reasoning": 0.9362,
+        "reward-bench/Score": 0.9154,
         "reward-bench/Factuality": 0.6274,
         "reward-bench/Precise IF": 0.35,
         "reward-bench/Math": 0.5847,
+        "reward-bench/Safety": 0.9081,
         "reward-bench/Focus": 0.8929,
-        "reward-bench/Ties": 0.6824
+        "reward-bench/Ties": 0.6824,
+        "reward-bench/Chat": 0.9553,
+        "reward-bench/Chat Hard": 0.8618,
+        "reward-bench/Reasoning": 0.9362
       }
     },
     {
@@ -116,17 +116,17 @@
       "developer": "Ray2333",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "reward-bench/Score": 0.8542,
+        "reward-bench/Score": 0.6089,
+        "reward-bench/Chat": 0.986,
+        "reward-bench/Chat Hard": 0.6776,
+        "reward-bench/Safety": 0.7867,
+        "reward-bench/Reasoning": 0.9229,
+        "reward-bench/Prior Sets (0.5 weight)": 0.7309,
         "reward-bench/Factuality": 0.6189,
         "reward-bench/Precise IF": 0.3875,
         "reward-bench/Math": 0.5792,
-        "reward-bench/Safety": 0.8919,
         "reward-bench/Focus": 0.6828,
-        "reward-bench/Ties": 0.5981,
-        "reward-bench/Chat": 0.986,
-        "reward-bench/Chat Hard": 0.6776,
-        "reward-bench/Reasoning": 0.9229,
-        "reward-bench/Prior Sets (0.5 weight)": 0.7309
+        "reward-bench/Ties": 0.5981
       }
     },
     {
diff --git a/data/developers/recoilme.json b/data/developers/recoilme.json
index 862469c1653f0d1414e3f6dabd97ef04b6d4f9e2..50baa7f16a67b3ee26a355a9f5b41de814bc7e52 100644
--- a/data/developers/recoilme.json
+++ b/data/developers/recoilme.json
@@ -35,12 +35,12 @@
       "developer": "recoilme",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "hfopenllm_v2/IFEval": 0.7592,
-        "hfopenllm_v2/BBH": 0.6026,
-        "hfopenllm_v2/MATH Level 5": 0.0529,
-        "hfopenllm_v2/GPQA": 0.3289,
-        "hfopenllm_v2/MUSR": 0.4099,
-        "hfopenllm_v2/MMLU-PRO": 0.4163
+        "hfopenllm_v2/IFEval": 0.2747,
+        "hfopenllm_v2/BBH": 0.6031,
+        "hfopenllm_v2/MATH Level 5": 0.0831,
+        "hfopenllm_v2/GPQA": 0.3305,
+        "hfopenllm_v2/MUSR": 0.4686,
+        "hfopenllm_v2/MMLU-PRO": 0.4122
       }
     },
     {
@@ -49,12 +49,12 @@
       "developer": "recoilme",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "hfopenllm_v2/IFEval": 0.5761,
-        "hfopenllm_v2/BBH": 0.602,
-        "hfopenllm_v2/MATH Level 5": 0.1888,
-        "hfopenllm_v2/GPQA": 0.3372,
-        "hfopenllm_v2/MUSR": 0.4632,
-        "hfopenllm_v2/MMLU-PRO": 0.4039
+        "hfopenllm_v2/IFEval": 0.7439,
+        "hfopenllm_v2/BBH": 0.5993,
+        "hfopenllm_v2/MATH Level 5": 0.0876,
+        "hfopenllm_v2/GPQA": 0.3238,
+        "hfopenllm_v2/MUSR": 0.4204,
+        "hfopenllm_v2/MMLU-PRO": 0.4072
       }
     },
     {
diff --git a/data/developers/replete-ai.json b/data/developers/replete-ai.json
index 0f038b31b0c0cf28a02b6c25fb4fd9bd374c118c..dbb06f00736a7fcddf76b24a5c7673e098ecab57 100644
--- a/data/developers/replete-ai.json
+++ b/data/developers/replete-ai.json
@@ -91,12 +91,12 @@
       "developer": "Replete-AI",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "hfopenllm_v2/IFEval": 0.0905,
-        "hfopenllm_v2/BBH": 0.2985,
+        "hfopenllm_v2/IFEval": 0.0932,
+        "hfopenllm_v2/BBH": 0.2977,
         "hfopenllm_v2/MATH Level 5": 0.0,
-        "hfopenllm_v2/GPQA": 0.2534,
-        "hfopenllm_v2/MUSR": 0.3848,
-        "hfopenllm_v2/MMLU-PRO": 0.1158
+        "hfopenllm_v2/GPQA": 0.2475,
+        "hfopenllm_v2/MUSR": 0.3941,
+        "hfopenllm_v2/MMLU-PRO": 0.1157
       }
     },
     {
diff --git a/data/developers/sfairxc.json b/data/developers/sfairxc.json
index 0f83a5aa819fcf69906563e63fd5c5a7cc1f8ce0..f511504fa472f754b653d8fff6432038f2fa5642 100644
--- a/data/developers/sfairxc.json
+++ b/data/developers/sfairxc.json
@@ -7,17 +7,17 @@
       "developer": "sfairXC",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "reward-bench/Score": 0.8338,
+        "reward-bench/Score": 0.6292,
+        "reward-bench/Chat": 0.9944,
+        "reward-bench/Chat Hard": 0.6513,
+        "reward-bench/Safety": 0.7667,
+        "reward-bench/Reasoning": 0.8644,
+        "reward-bench/Prior Sets (0.5 weight)": 0.7492,
         "reward-bench/Factuality": 0.5916,
         "reward-bench/Precise IF": 0.4188,
         "reward-bench/Math": 0.6284,
-        "reward-bench/Safety": 0.8676,
         "reward-bench/Focus": 0.7051,
-        "reward-bench/Ties": 0.6647,
-        "reward-bench/Chat": 0.9944,
-        "reward-bench/Chat Hard": 0.6513,
-        "reward-bench/Reasoning": 0.8644,
-        "reward-bench/Prior Sets (0.5 weight)": 0.7492
+        "reward-bench/Ties": 0.6647
       }
     }
   ]
diff --git a/data/developers/shikaichen.json b/data/developers/shikaichen.json
index 6162cba6dec7eaed27af88272ffb98342af2522b..6502ef5b0e02cc85862537458f25816eb0826b7d 100644
--- a/data/developers/shikaichen.json
+++ b/data/developers/shikaichen.json
@@ -7,16 +7,16 @@
       "developer": "ShikaiChen",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "reward-bench/Score": 0.9499,
+        "reward-bench/Score": 0.7249,
+        "reward-bench/Chat": 0.9637,
+        "reward-bench/Chat Hard": 0.9079,
+        "reward-bench/Safety": 0.9222,
+        "reward-bench/Reasoning": 0.9903,
         "reward-bench/Factuality": 0.7558,
         "reward-bench/Precise IF": 0.35,
         "reward-bench/Math": 0.6448,
-        "reward-bench/Safety": 0.9378,
         "reward-bench/Focus": 0.9131,
-        "reward-bench/Ties": 0.7633,
-        "reward-bench/Chat": 0.9637,
-        "reward-bench/Chat Hard": 0.9079,
-        "reward-bench/Reasoning": 0.9903
+        "reward-bench/Ties": 0.7633
       }
     }
   ]
diff --git a/data/developers/skywork.json b/data/developers/skywork.json
index 310fc474921f3ff87a2e73d5f74077c21e25d2fe..15f843864c8bce10620ff0dcdbde98d85af98ac4 100644
--- a/data/developers/skywork.json
+++ b/data/developers/skywork.json
@@ -47,16 +47,16 @@
       "developer": "Skywork",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "reward-bench/Score": 0.7576,
-        "reward-bench/Chat": 0.9581,
-        "reward-bench/Chat Hard": 0.9145,
-        "reward-bench/Safety": 0.9422,
-        "reward-bench/Reasoning": 0.9606,
+        "reward-bench/Score": 0.938,
         "reward-bench/Factuality": 0.7368,
         "reward-bench/Precise IF": 0.4031,
         "reward-bench/Math": 0.7049,
+        "reward-bench/Safety": 0.9189,
         "reward-bench/Focus": 0.9323,
-        "reward-bench/Ties": 0.8261
+        "reward-bench/Ties": 0.8261,
+        "reward-bench/Chat": 0.9581,
+        "reward-bench/Chat Hard": 0.9145,
+        "reward-bench/Reasoning": 0.9606
       }
     },
     {
@@ -230,16 +230,16 @@
       "developer": "Skywork",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "reward-bench/Score": 0.6885,
-        "reward-bench/Chat": 0.8994,
-        "reward-bench/Chat Hard": 0.875,
-        "reward-bench/Safety": 0.8911,
-        "reward-bench/Reasoning": 0.9176,
+        "reward-bench/Score": 0.9007,
         "reward-bench/Factuality": 0.6063,
         "reward-bench/Precise IF": 0.35,
         "reward-bench/Math": 0.6339,
+        "reward-bench/Safety": 0.9108,
         "reward-bench/Focus": 0.8909,
-        "reward-bench/Ties": 0.7586
+        "reward-bench/Ties": 0.7586,
+        "reward-bench/Chat": 0.8994,
+        "reward-bench/Chat Hard": 0.875,
+        "reward-bench/Reasoning": 0.9176
       }
     }
   ]
diff --git a/data/developers/sometimesanotion.json b/data/developers/sometimesanotion.json
index b756bb971c60b6bcad2e85989edb63b8a758fe59..c020e85fc5c690d215cbd09f94a114e50c6a6936 100644
--- a/data/developers/sometimesanotion.json
+++ b/data/developers/sometimesanotion.json
@@ -749,12 +749,12 @@
       "developer": "sometimesanotion",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "hfopenllm_v2/IFEval": 0.5367,
-        "hfopenllm_v2/BBH": 0.6561,
-        "hfopenllm_v2/MATH Level 5": 0.358,
-        "hfopenllm_v2/GPQA": 0.3867,
-        "hfopenllm_v2/MUSR": 0.474,
-        "hfopenllm_v2/MMLU-PRO": 0.5395
+        "hfopenllm_v2/IFEval": 0.5278,
+        "hfopenllm_v2/BBH": 0.6557,
+        "hfopenllm_v2/MATH Level 5": 0.3119,
+        "hfopenllm_v2/GPQA": 0.3842,
+        "hfopenllm_v2/MUSR": 0.4754,
+        "hfopenllm_v2/MMLU-PRO": 0.5396
       }
     },
     {
diff --git a/data/developers/tanliboy.json b/data/developers/tanliboy.json
index daa17945601d8528cbfc7c883e4dc4315ea363fc..7b17e651b33310ae087a6456408950e1456ff623 100644
--- a/data/developers/tanliboy.json
+++ b/data/developers/tanliboy.json
@@ -7,12 +7,12 @@
       "developer": "tanliboy",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "hfopenllm_v2/IFEval": 0.4501,
-        "hfopenllm_v2/BBH": 0.5472,
-        "hfopenllm_v2/MATH Level 5": 0.0944,
-        "hfopenllm_v2/GPQA": 0.3138,
-        "hfopenllm_v2/MUSR": 0.4017,
-        "hfopenllm_v2/MMLU-PRO": 0.3792
+        "hfopenllm_v2/IFEval": 0.1829,
+        "hfopenllm_v2/BBH": 0.5488,
+        "hfopenllm_v2/MATH Level 5": 0.0,
+        "hfopenllm_v2/GPQA": 0.3104,
+        "hfopenllm_v2/MUSR": 0.4056,
+        "hfopenllm_v2/MMLU-PRO": 0.3805
       }
     },
     {
diff --git a/data/developers/valiantlabs.json b/data/developers/valiantlabs.json
index a0fc2b3d81b7ddfe31ae4c63f4f370e45c708501..b0b3adff2288383cd6923301f5751d53ee8ba504 100644
--- a/data/developers/valiantlabs.json
+++ b/data/developers/valiantlabs.json
@@ -49,12 +49,12 @@
       "developer": "ValiantLabs",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "hfopenllm_v2/IFEval": 0.7168,
-        "hfopenllm_v2/BBH": 0.4911,
-        "hfopenllm_v2/MATH Level 5": 0.1533,
-        "hfopenllm_v2/GPQA": 0.2861,
-        "hfopenllm_v2/MUSR": 0.3512,
-        "hfopenllm_v2/MMLU-PRO": 0.3663
+        "hfopenllm_v2/IFEval": 0.3496,
+        "hfopenllm_v2/BBH": 0.4947,
+        "hfopenllm_v2/MATH Level 5": 0.1269,
+        "hfopenllm_v2/GPQA": 0.3037,
+        "hfopenllm_v2/MUSR": 0.3959,
+        "hfopenllm_v2/MMLU-PRO": 0.3644
       }
     },
     {
diff --git a/data/developers/weqweasdas.json b/data/developers/weqweasdas.json
index fd061c03aa20db7f3ab1d7ab2e9b6a6249c65553..36aa4e34297ffab30b15be8c96f1b385a32071bf 100644
--- a/data/developers/weqweasdas.json
+++ b/data/developers/weqweasdas.json
@@ -7,17 +7,17 @@
       "developer": "weqweasdas",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "reward-bench/Score": 0.5027,
+        "reward-bench/Score": 0.2498,
+        "reward-bench/Chat": 0.8184,
+        "reward-bench/Chat Hard": 0.3728,
+        "reward-bench/Safety": 0.24,
+        "reward-bench/Reasoning": 0.3281,
+        "reward-bench/Prior Sets (0.5 weight)": 0.6564,
         "reward-bench/Factuality": 0.3642,
         "reward-bench/Precise IF": 0.275,
         "reward-bench/Math": 0.3497,
-        "reward-bench/Safety": 0.4149,
         "reward-bench/Focus": 0.2384,
-        "reward-bench/Ties": 0.0315,
-        "reward-bench/Chat": 0.8184,
-        "reward-bench/Chat Hard": 0.3728,
-        "reward-bench/Reasoning": 0.3281,
-        "reward-bench/Prior Sets (0.5 weight)": 0.6564
+        "reward-bench/Ties": 0.0315
       }
     },
     {
@@ -26,17 +26,17 @@
       "developer": "weqweasdas",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "reward-bench/Score": 0.6549,
+        "reward-bench/Score": 0.3057,
+        "reward-bench/Chat": 0.9441,
+        "reward-bench/Chat Hard": 0.4079,
+        "reward-bench/Safety": 0.3311,
+        "reward-bench/Reasoning": 0.7637,
+        "reward-bench/Prior Sets (0.5 weight)": 0.6652,
         "reward-bench/Factuality": 0.3705,
         "reward-bench/Precise IF": 0.2812,
         "reward-bench/Math": 0.4317,
-        "reward-bench/Safety": 0.4986,
         "reward-bench/Focus": 0.2343,
-        "reward-bench/Ties": 0.1851,
-        "reward-bench/Chat": 0.9441,
-        "reward-bench/Chat Hard": 0.4079,
-        "reward-bench/Reasoning": 0.7637,
-        "reward-bench/Prior Sets (0.5 weight)": 0.6652
+        "reward-bench/Ties": 0.1851
       }
     },
     {
@@ -78,17 +78,17 @@
       "developer": "weqweasdas",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "reward-bench/Score": 0.7982,
+        "reward-bench/Score": 0.596,
+        "reward-bench/Chat": 0.9665,
+        "reward-bench/Chat Hard": 0.6053,
+        "reward-bench/Safety": 0.6911,
+        "reward-bench/Reasoning": 0.7736,
+        "reward-bench/Prior Sets (0.5 weight)": 0.753,
         "reward-bench/Factuality": 0.5937,
         "reward-bench/Precise IF": 0.3438,
         "reward-bench/Math": 0.5956,
-        "reward-bench/Safety": 0.8703,
         "reward-bench/Focus": 0.7293,
-        "reward-bench/Ties": 0.6226,
-        "reward-bench/Chat": 0.9665,
-        "reward-bench/Chat Hard": 0.6053,
-        "reward-bench/Reasoning": 0.7736,
-        "reward-bench/Prior Sets (0.5 weight)": 0.753
+        "reward-bench/Ties": 0.6226
       }
     }
   ]
diff --git a/data/developers/yam-peleg.json b/data/developers/yam-peleg.json
index 3161f95274f1998cddb90c53a59dce4097dbe0fd..f415128b8e93253c12ae15436b68cf36d5f248bf 100644
--- a/data/developers/yam-peleg.json
+++ b/data/developers/yam-peleg.json
@@ -35,12 +35,12 @@
       "developer": "yam-peleg",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "hfopenllm_v2/IFEval": 0.1856,
-        "hfopenllm_v2/BBH": 0.4149,
-        "hfopenllm_v2/MATH Level 5": 0.0234,
-        "hfopenllm_v2/GPQA": 0.276,
-        "hfopenllm_v2/MUSR": 0.3765,
-        "hfopenllm_v2/MMLU-PRO": 0.2573
+        "hfopenllm_v2/IFEval": 0.177,
+        "hfopenllm_v2/BBH": 0.3411,
+        "hfopenllm_v2/MATH Level 5": 0.031,
+        "hfopenllm_v2/GPQA": 0.2534,
+        "hfopenllm_v2/MUSR": 0.374,
+        "hfopenllm_v2/MMLU-PRO": 0.2529
       }
     }
   ]
diff --git a/data/developers/z-ai.json b/data/developers/z-ai.json
index d4ada9599b117d1b4893fef821933bb44c4fb1d9..25c72391d11bee4c4ccdbee1d0c2cdded93b09ab 100644
--- a/data/developers/z-ai.json
+++ b/data/developers/z-ai.json
@@ -7,7 +7,7 @@
       "developer": "Z-AI",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "terminal-bench-2.0/terminal-bench-2.0": 33.3
+        "terminal-bench-2.0/terminal-bench-2.0": 33.4
       }
     },
     {
diff --git a/data/models.json b/data/models.json
index 2b93623cbdf71160760101030d0eb4a96cc29224..a4ab0a1994ca0a7faae8835c098ea436fc0ab99c 100644
--- a/data/models.json
+++ b/data/models.json
@@ -907,12 +907,12 @@
     "developer": "abhishek",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "hfopenllm_v2/IFEval": 0.1952,
-      "hfopenllm_v2/BBH": 0.3127,
-      "hfopenllm_v2/MATH Level 5": 0.0128,
-      "hfopenllm_v2/GPQA": 0.2592,
-      "hfopenllm_v2/MUSR": 0.3584,
-      "hfopenllm_v2/MMLU-PRO": 0.1144
+      "hfopenllm_v2/IFEval": 0.1957,
+      "hfopenllm_v2/BBH": 0.3135,
+      "hfopenllm_v2/MATH Level 5": 0.0,
+      "hfopenllm_v2/GPQA": 0.2517,
+      "hfopenllm_v2/MUSR": 0.365,
+      "hfopenllm_v2/MMLU-PRO": 0.1151
     }
   },
   {
@@ -1005,12 +1005,12 @@
     "developer": "adriszmar",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "hfopenllm_v2/IFEval": 0.1746,
-      "hfopenllm_v2/BBH": 0.3126,
-      "hfopenllm_v2/MATH Level 5": 0.0,
-      "hfopenllm_v2/GPQA": 0.245,
-      "hfopenllm_v2/MUSR": 0.4096,
-      "hfopenllm_v2/MMLU-PRO": 0.1087
+      "hfopenllm_v2/IFEval": 0.1685,
+      "hfopenllm_v2/BBH": 0.3124,
+      "hfopenllm_v2/MATH Level 5": 0.0015,
+      "hfopenllm_v2/GPQA": 0.2492,
+      "hfopenllm_v2/MUSR": 0.3963,
+      "hfopenllm_v2/MMLU-PRO": 0.1066
     }
   },
   {
@@ -1391,10 +1391,10 @@
     "developer": "AI2",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "reward-bench/Score": 0.6924,
-      "reward-bench/Chat": 0.9441,
-      "reward-bench/Chat Hard": 0.3575,
-      "reward-bench/Safety": 0.7757
+      "reward-bench/Score": 0.6895,
+      "reward-bench/Chat": 0.9385,
+      "reward-bench/Chat Hard": 0.3706,
+      "reward-bench/Safety": 0.7595
     }
   },
   {
@@ -2036,12 +2036,12 @@
     "developer": "akjindal53244",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "hfopenllm_v2/IFEval": 0.8033,
-      "hfopenllm_v2/BBH": 0.5196,
-      "hfopenllm_v2/MATH Level 5": 0.1624,
-      "hfopenllm_v2/GPQA": 0.3096,
+      "hfopenllm_v2/IFEval": 0.8051,
+      "hfopenllm_v2/BBH": 0.5189,
+      "hfopenllm_v2/MATH Level 5": 0.1722,
+      "hfopenllm_v2/GPQA": 0.3263,
       "hfopenllm_v2/MUSR": 0.4028,
-      "hfopenllm_v2/MMLU-PRO": 0.3812
+      "hfopenllm_v2/MMLU-PRO": 0.3803
     }
   },
   {
@@ -2243,7 +2243,7 @@
     "developer": "Alibaba",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "terminal-bench-2.0/terminal-bench-2.0": 27.2
+      "terminal-bench-2.0/terminal-bench-2.0": 25.4
     }
   },
   {
@@ -2409,17 +2409,17 @@
     "developer": "allenai",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "reward-bench/Score": 0.649,
-      "reward-bench/Chat": 0.933,
-      "reward-bench/Chat Hard": 0.7785,
-      "reward-bench/Safety": 0.8267,
-      "reward-bench/Reasoning": 0.7886,
-      "reward-bench/Prior Sets (0.5 weight)": 0.0,
+      "reward-bench/Score": 0.8463,
       "reward-bench/Factuality": 0.72,
       "reward-bench/Precise IF": 0.3625,
       "reward-bench/Math": 0.612,
+      "reward-bench/Safety": 0.8851,
       "reward-bench/Focus": 0.8323,
-      "reward-bench/Ties": 0.5406
+      "reward-bench/Ties": 0.5406,
+      "reward-bench/Chat": 0.933,
+      "reward-bench/Chat Hard": 0.7785,
+      "reward-bench/Reasoning": 0.7886,
+      "reward-bench/Prior Sets (0.5 weight)": 0.0
     }
   },
   {
@@ -2447,12 +2447,12 @@
     "developer": "allenai",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "hfopenllm_v2/IFEval": 0.8291,
-      "hfopenllm_v2/BBH": 0.6164,
-      "hfopenllm_v2/MATH Level 5": 0.4502,
+      "hfopenllm_v2/IFEval": 0.8379,
+      "hfopenllm_v2/BBH": 0.6157,
+      "hfopenllm_v2/MATH Level 5": 0.3829,
       "hfopenllm_v2/GPQA": 0.3733,
-      "hfopenllm_v2/MUSR": 0.4948,
-      "hfopenllm_v2/MMLU-PRO": 0.4645
+      "hfopenllm_v2/MUSR": 0.4988,
+      "hfopenllm_v2/MMLU-PRO": 0.4656
     }
   },
   {
@@ -2489,17 +2489,17 @@
     "developer": "allenai",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "reward-bench/Score": 0.8892,
+      "reward-bench/Score": 0.722,
+      "reward-bench/Chat": 0.9693,
+      "reward-bench/Chat Hard": 0.8268,
+      "reward-bench/Safety": 0.8689,
+      "reward-bench/Reasoning": 0.8583,
+      "reward-bench/Prior Sets (0.5 weight)": 0.0,
       "reward-bench/Factuality": 0.8084,
       "reward-bench/Precise IF": 0.3688,
       "reward-bench/Math": 0.6776,
-      "reward-bench/Safety": 0.9027,
       "reward-bench/Focus": 0.7778,
-      "reward-bench/Ties": 0.8308,
-      "reward-bench/Chat": 0.9693,
-      "reward-bench/Chat Hard": 0.8268,
-      "reward-bench/Reasoning": 0.8583,
-      "reward-bench/Prior Sets (0.5 weight)": 0.0
+      "reward-bench/Ties": 0.8308
     }
   },
   {
@@ -2508,12 +2508,12 @@
     "developer": "allenai",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "hfopenllm_v2/IFEval": 0.8267,
-      "hfopenllm_v2/BBH": 0.405,
-      "hfopenllm_v2/MATH Level 5": 0.1964,
-      "hfopenllm_v2/GPQA": 0.2987,
+      "hfopenllm_v2/IFEval": 0.8255,
+      "hfopenllm_v2/BBH": 0.4061,
+      "hfopenllm_v2/MATH Level 5": 0.2115,
+      "hfopenllm_v2/GPQA": 0.297,
       "hfopenllm_v2/MUSR": 0.4175,
-      "hfopenllm_v2/MMLU-PRO": 0.2827
+      "hfopenllm_v2/MMLU-PRO": 0.2821
     }
   },
   {
@@ -2536,17 +2536,17 @@
     "developer": "allenai",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "reward-bench/Score": 0.8431,
+      "reward-bench/Score": 0.687,
+      "reward-bench/Chat": 0.9553,
+      "reward-bench/Chat Hard": 0.761,
+      "reward-bench/Safety": 0.86,
+      "reward-bench/Reasoning": 0.7898,
+      "reward-bench/Prior Sets (0.5 weight)": 0.0,
       "reward-bench/Factuality": 0.7516,
       "reward-bench/Precise IF": 0.3875,
       "reward-bench/Math": 0.6284,
-      "reward-bench/Safety": 0.8662,
       "reward-bench/Focus": 0.8545,
-      "reward-bench/Ties": 0.6397,
-      "reward-bench/Chat": 0.9553,
-      "reward-bench/Chat Hard": 0.761,
-      "reward-bench/Reasoning": 0.7898,
-      "reward-bench/Prior Sets (0.5 weight)": 0.0
+      "reward-bench/Ties": 0.6397
     }
   },
   {
@@ -3381,21 +3381,6 @@
       "reward-bench/Ties": 0.3534
     }
   },
-  {
-    "id": "allenai/open_instruct_dev-rm_1e-6_2_30pctflipped__1__1743325094",
-    "name": "allenai/open_instruct_dev-rm_1e-6_2_30pctflipped__1__1743325094",
-    "developer": "allenai",
-    "evaluator_relationship": null,
-    "benchmark_scores": {
-      "reward-bench/Score": 0.5151,
-      "reward-bench/Factuality": 0.6484,
-      "reward-bench/Precise IF": 0.3312,
-      "reward-bench/Math": 0.5574,
-      "reward-bench/Safety": 0.7289,
-      "reward-bench/Focus": 0.4889,
-      "reward-bench/Ties": 0.3357
-    }
-  },
   {
     "id": "allenai/open_instruct_dev-rm_1e-6_2_5pctflipped__1__1743444636",
     "name": "allenai/open_instruct_dev-rm_1e-6_2_5pctflipped__1__1743444636",
@@ -7167,17 +7152,17 @@
       "helm_mmlu/Virology": 0.542,
       "helm_mmlu/World Religions": 0.871,
       "helm_mmlu/Mean win rate": 0.28,
-      "reward-bench/Score": 0.3711,
-      "reward-bench/Chat": 0.9274,
-      "reward-bench/Chat Hard": 0.5197,
-      "reward-bench/Safety": 0.595,
-      "reward-bench/Reasoning": 0.706,
-      "reward-bench/Prior Sets (0.5 weight)": 0.6635,
+      "reward-bench/Score": 0.7289,
       "reward-bench/Factuality": 0.4042,
       "reward-bench/Precise IF": 0.2812,
       "reward-bench/Math": 0.3552,
+      "reward-bench/Safety": 0.7953,
       "reward-bench/Focus": 0.501,
-      "reward-bench/Ties": 0.0899
+      "reward-bench/Ties": 0.0899,
+      "reward-bench/Chat": 0.9274,
+      "reward-bench/Chat Hard": 0.5197,
+      "reward-bench/Reasoning": 0.706,
+      "reward-bench/Prior Sets (0.5 weight)": 0.6635
     }
   },
   {
@@ -7232,16 +7217,16 @@
       "helm_mmlu/Virology": 0.578,
       "helm_mmlu/World Religions": 0.901,
       "helm_mmlu/Mean win rate": 0.014,
-      "reward-bench/Score": 0.5744,
-      "reward-bench/Chat": 0.9469,
-      "reward-bench/Chat Hard": 0.6031,
-      "reward-bench/Safety": 0.8378,
-      "reward-bench/Reasoning": 0.7868,
+      "reward-bench/Score": 0.8008,
       "reward-bench/Factuality": 0.5389,
       "reward-bench/Precise IF": 0.3312,
       "reward-bench/Math": 0.5137,
+      "reward-bench/Safety": 0.8662,
       "reward-bench/Focus": 0.6646,
-      "reward-bench/Ties": 0.5601
+      "reward-bench/Ties": 0.5601,
+      "reward-bench/Chat": 0.9469,
+      "reward-bench/Chat Hard": 0.6031,
+      "reward-bench/Reasoning": 0.7868
     }
   },
   {
@@ -7321,7 +7306,7 @@
     "developer": "Anthropic",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "terminal-bench-2.0/terminal-bench-2.0": 13.9
+      "terminal-bench-2.0/terminal-bench-2.0": 27.5
     }
   },
   {
@@ -7446,12 +7431,12 @@
     "developer": "Anthropic",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "appworld_test_normal/appworld/test_normal": 0.7,
+      "appworld_test_normal/appworld/test_normal": 0.64,
       "browsecompplus/browsecompplus": 0.61,
       "swe-bench/swe-bench": 0.6061,
-      "tau-bench-2_airline/tau-bench-2/airline": 0.66,
-      "tau-bench-2_retail/tau-bench-2/retail": 0.78,
-      "tau-bench-2_telecom/tau-bench-2/telecom": 0.84
+      "tau-bench-2_airline/tau-bench-2/airline": 0.72,
+      "tau-bench-2_retail/tau-bench-2/retail": 0.85,
+      "tau-bench-2_telecom/tau-bench-2/telecom": 0.76
     }
   },
   {
@@ -7460,7 +7445,7 @@
     "developer": "Anthropic",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "terminal-bench-2.0/terminal-bench-2.0": 35.1
+      "terminal-bench-2.0/terminal-bench-2.0": 34.8
     }
   },
   {
@@ -7478,7 +7463,7 @@
     "developer": "Anthropic",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "terminal-bench-2.0/terminal-bench-2.0": 62.9
+      "terminal-bench-2.0/terminal-bench-2.0": 74.7
     }
   },
   {
@@ -7552,7 +7537,7 @@
     "developer": "Anthropic",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "terminal-bench-2.0/terminal-bench-2.0": 42.6
+      "terminal-bench-2.0/terminal-bench-2.0": 42.5
     }
   },
   {
@@ -9843,12 +9828,12 @@
     "developer": "BoltMonkey",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "hfopenllm_v2/IFEval": 0.459,
-      "hfopenllm_v2/BBH": 0.5185,
-      "hfopenllm_v2/MATH Level 5": 0.0937,
-      "hfopenllm_v2/GPQA": 0.2743,
-      "hfopenllm_v2/MUSR": 0.4083,
-      "hfopenllm_v2/MMLU-PRO": 0.3631
+      "hfopenllm_v2/IFEval": 0.7999,
+      "hfopenllm_v2/BBH": 0.5152,
+      "hfopenllm_v2/MATH Level 5": 0.1193,
+      "hfopenllm_v2/GPQA": 0.281,
+      "hfopenllm_v2/MUSR": 0.4019,
+      "hfopenllm_v2/MMLU-PRO": 0.3733
     }
   },
   {
@@ -10599,12 +10584,12 @@
     "developer": "bunnycore",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "hfopenllm_v2/IFEval": 0.1775,
-      "hfopenllm_v2/BBH": 0.295,
-      "hfopenllm_v2/MATH Level 5": 0.0,
-      "hfopenllm_v2/GPQA": 0.2517,
-      "hfopenllm_v2/MUSR": 0.3647,
-      "hfopenllm_v2/MMLU-PRO": 0.1049
+      "hfopenllm_v2/IFEval": 0.4652,
+      "hfopenllm_v2/BBH": 0.4531,
+      "hfopenllm_v2/MATH Level 5": 0.1284,
+      "hfopenllm_v2/GPQA": 0.2643,
+      "hfopenllm_v2/MUSR": 0.3394,
+      "hfopenllm_v2/MMLU-PRO": 0.3152
     }
   },
   {
@@ -11828,17 +11813,17 @@
     "developer": "CIR-AMS",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "reward-bench/Score": 0.8172,
+      "reward-bench/Score": 0.5736,
+      "reward-bench/Chat": 0.9749,
+      "reward-bench/Chat Hard": 0.5724,
+      "reward-bench/Safety": 0.7178,
+      "reward-bench/Reasoning": 0.8775,
+      "reward-bench/Prior Sets (0.5 weight)": 0.7029,
       "reward-bench/Factuality": 0.5347,
       "reward-bench/Precise IF": 0.3563,
       "reward-bench/Math": 0.6066,
-      "reward-bench/Safety": 0.9014,
       "reward-bench/Focus": 0.5737,
-      "reward-bench/Ties": 0.6527,
-      "reward-bench/Chat": 0.9749,
-      "reward-bench/Chat Hard": 0.5724,
-      "reward-bench/Reasoning": 0.8775,
-      "reward-bench/Prior Sets (0.5 weight)": 0.7029
+      "reward-bench/Ties": 0.6527
     }
   },
   {
@@ -12852,12 +12837,12 @@
     "developer": "Columbia-NLP",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "hfopenllm_v2/IFEval": 0.3102,
-      "hfopenllm_v2/BBH": 0.3881,
-      "hfopenllm_v2/MATH Level 5": 0.0536,
-      "hfopenllm_v2/GPQA": 0.2534,
-      "hfopenllm_v2/MUSR": 0.4081,
-      "hfopenllm_v2/MMLU-PRO": 0.1665
+      "hfopenllm_v2/IFEval": 0.3278,
+      "hfopenllm_v2/BBH": 0.392,
+      "hfopenllm_v2/MATH Level 5": 0.0431,
+      "hfopenllm_v2/GPQA": 0.2492,
+      "hfopenllm_v2/MUSR": 0.412,
+      "hfopenllm_v2/MMLU-PRO": 0.1666
     }
   },
   {
@@ -14338,12 +14323,12 @@
     "developer": "Daemontatox",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "hfopenllm_v2/IFEval": 0.4855,
-      "hfopenllm_v2/BBH": 0.6627,
-      "hfopenllm_v2/MATH Level 5": 0.4841,
-      "hfopenllm_v2/GPQA": 0.3096,
-      "hfopenllm_v2/MUSR": 0.4256,
-      "hfopenllm_v2/MMLU-PRO": 0.5542
+      "hfopenllm_v2/IFEval": 0.3745,
+      "hfopenllm_v2/BBH": 0.6668,
+      "hfopenllm_v2/MATH Level 5": 0.4758,
+      "hfopenllm_v2/GPQA": 0.3943,
+      "hfopenllm_v2/MUSR": 0.4858,
+      "hfopenllm_v2/MMLU-PRO": 0.5593
     }
   },
   {
@@ -15393,12 +15378,12 @@
     "developer": "DavieLion",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "hfopenllm_v2/IFEval": 0.1507,
-      "hfopenllm_v2/BBH": 0.293,
-      "hfopenllm_v2/MATH Level 5": 0.0,
-      "hfopenllm_v2/GPQA": 0.2534,
+      "hfopenllm_v2/IFEval": 0.1549,
+      "hfopenllm_v2/BBH": 0.2937,
+      "hfopenllm_v2/MATH Level 5": 0.006,
+      "hfopenllm_v2/GPQA": 0.2576,
       "hfopenllm_v2/MUSR": 0.3565,
-      "hfopenllm_v2/MMLU-PRO": 0.1125
+      "hfopenllm_v2/MMLU-PRO": 0.1128
     }
   },
   {
@@ -15435,12 +15420,12 @@
     "developer": "DavieLion",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "hfopenllm_v2/IFEval": 0.1336,
-      "hfopenllm_v2/BBH": 0.2975,
-      "hfopenllm_v2/MATH Level 5": 0.0068,
-      "hfopenllm_v2/GPQA": 0.2534,
-      "hfopenllm_v2/MUSR": 0.35,
-      "hfopenllm_v2/MMLU-PRO": 0.1128
+      "hfopenllm_v2/IFEval": 0.1324,
+      "hfopenllm_v2/BBH": 0.2972,
+      "hfopenllm_v2/MATH Level 5": 0.0,
+      "hfopenllm_v2/GPQA": 0.2643,
+      "hfopenllm_v2/MUSR": 0.3527,
+      "hfopenllm_v2/MMLU-PRO": 0.1129
     }
   },
   {
@@ -15729,12 +15714,12 @@
     "developer": "DeepMount00",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "hfopenllm_v2/IFEval": 0.5365,
-      "hfopenllm_v2/BBH": 0.517,
-      "hfopenllm_v2/MATH Level 5": 0.1707,
-      "hfopenllm_v2/GPQA": 0.3062,
-      "hfopenllm_v2/MUSR": 0.4487,
-      "hfopenllm_v2/MMLU-PRO": 0.396
+      "hfopenllm_v2/IFEval": 0.7917,
+      "hfopenllm_v2/BBH": 0.5109,
+      "hfopenllm_v2/MATH Level 5": 0.1088,
+      "hfopenllm_v2/GPQA": 0.2878,
+      "hfopenllm_v2/MUSR": 0.4136,
+      "hfopenllm_v2/MMLU-PRO": 0.3876
     }
   },
   {
@@ -16376,12 +16361,12 @@
     "developer": "dfurman",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "hfopenllm_v2/IFEval": 0.3,
-      "hfopenllm_v2/BBH": 0.3853,
-      "hfopenllm_v2/MATH Level 5": 0.0415,
-      "hfopenllm_v2/GPQA": 0.2617,
-      "hfopenllm_v2/MUSR": 0.3579,
-      "hfopenllm_v2/MMLU-PRO": 0.2281
+      "hfopenllm_v2/IFEval": 0.2835,
+      "hfopenllm_v2/BBH": 0.3842,
+      "hfopenllm_v2/MATH Level 5": 0.0521,
+      "hfopenllm_v2/GPQA": 0.2609,
+      "hfopenllm_v2/MUSR": 0.3566,
+      "hfopenllm_v2/MMLU-PRO": 0.2298
     }
   },
   {
@@ -20340,12 +20325,12 @@
     "developer": "EpistemeAI",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "hfopenllm_v2/IFEval": 0.7305,
-      "hfopenllm_v2/BBH": 0.4649,
-      "hfopenllm_v2/MATH Level 5": 0.1397,
-      "hfopenllm_v2/GPQA": 0.2659,
-      "hfopenllm_v2/MUSR": 0.3209,
-      "hfopenllm_v2/MMLU-PRO": 0.348
+      "hfopenllm_v2/IFEval": 0.7207,
+      "hfopenllm_v2/BBH": 0.461,
+      "hfopenllm_v2/MATH Level 5": 0.1314,
+      "hfopenllm_v2/GPQA": 0.2701,
+      "hfopenllm_v2/MUSR": 0.3432,
+      "hfopenllm_v2/MMLU-PRO": 0.3354
     }
   },
   {
@@ -21040,12 +21025,12 @@
     "developer": "Etherll",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "hfopenllm_v2/IFEval": 0.6106,
-      "hfopenllm_v2/BBH": 0.5347,
-      "hfopenllm_v2/MATH Level 5": 0.1548,
-      "hfopenllm_v2/GPQA": 0.3146,
-      "hfopenllm_v2/MUSR": 0.3991,
-      "hfopenllm_v2/MMLU-PRO": 0.3752
+      "hfopenllm_v2/IFEval": 0.4672,
+      "hfopenllm_v2/BBH": 0.5013,
+      "hfopenllm_v2/MATH Level 5": 0.0279,
+      "hfopenllm_v2/GPQA": 0.2861,
+      "hfopenllm_v2/MUSR": 0.386,
+      "hfopenllm_v2/MMLU-PRO": 0.3482
     }
   },
   {
@@ -23303,12 +23288,12 @@
     "developer": "Goekdeniz-Guelmez",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "hfopenllm_v2/IFEval": 0.3472,
-      "hfopenllm_v2/BBH": 0.3268,
-      "hfopenllm_v2/MATH Level 5": 0.0891,
-      "hfopenllm_v2/GPQA": 0.2517,
-      "hfopenllm_v2/MUSR": 0.3262,
-      "hfopenllm_v2/MMLU-PRO": 0.1641
+      "hfopenllm_v2/IFEval": 0.3417,
+      "hfopenllm_v2/BBH": 0.3292,
+      "hfopenllm_v2/MATH Level 5": 0.0023,
+      "hfopenllm_v2/GPQA": 0.2576,
+      "hfopenllm_v2/MUSR": 0.3249,
+      "hfopenllm_v2/MMLU-PRO": 0.1638
     }
   },
   {
@@ -23537,8 +23522,6 @@
     "developer": "Google",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "ace/Overall Score": 0.47,
-      "ace/Gaming Score": 0.509,
       "apex-agents/Overall Pass@1": 0.184,
       "apex-agents/Overall Pass@8": 0.373,
       "apex-agents/Overall Mean Score": 0.341,
@@ -23546,6 +23529,8 @@
       "apex-agents/Management Consulting Pass@1": 0.124,
       "apex-agents/Corporate Law Pass@1": 0.239,
       "apex-agents/Corporate Lawyer Mean Score": 0.487,
+      "ace/Overall Score": 0.47,
+      "ace/Gaming Score": 0.509,
       "apex-v1/Overall Score": 0.643,
       "apex-v1/Consulting Score": 0.64,
       "apex-v1/Investment Banking Score": 0.63
@@ -24241,7 +24226,7 @@
     "developer": "Google",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "terminal-bench-2.0/terminal-bench-2.0": 47.4
+      "terminal-bench-2.0/terminal-bench-2.0": 51.0
     }
   },
   {
@@ -24250,7 +24235,7 @@
     "developer": "Google",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "terminal-bench-2.0/terminal-bench-2.0": 56.0
+      "terminal-bench-2.0/terminal-bench-2.0": 56.9
     }
   },
   {
@@ -24259,8 +24244,8 @@
     "developer": "Google",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "appworld_test_normal/appworld/test_normal": 0.55,
-      "browsecompplus/browsecompplus": 0.3333,
+      "appworld_test_normal/appworld/test_normal": 0.36,
+      "browsecompplus/browsecompplus": 0.48,
       "global-mmlu-lite/Global MMLU Lite": 0.9453,
       "global-mmlu-lite/Culturally Sensitive": 0.9397,
       "global-mmlu-lite/Culturally Agnostic": 0.9509,
@@ -24282,7 +24267,7 @@
       "global-mmlu-lite/Burmese": 0.9425,
       "swe-bench/swe-bench": 0.71,
       "tau-bench-2_airline/tau-bench-2/airline": 0.68,
-      "tau-bench-2_retail/tau-bench-2/retail": 0.73,
+      "tau-bench-2_retail/tau-bench-2/retail": 0.7805,
       "tau-bench-2_telecom/tau-bench-2/telecom": 0.73
     }
   },
@@ -25530,12 +25515,12 @@
     "developer": "GuilhermeNaturaUmana",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "hfopenllm_v2/IFEval": 0.4985,
-      "hfopenllm_v2/BBH": 0.5645,
-      "hfopenllm_v2/MATH Level 5": 0.2576,
-      "hfopenllm_v2/GPQA": 0.3003,
-      "hfopenllm_v2/MUSR": 0.4373,
-      "hfopenllm_v2/MMLU-PRO": 0.4429
+      "hfopenllm_v2/IFEval": 0.4791,
+      "hfopenllm_v2/BBH": 0.5649,
+      "hfopenllm_v2/MATH Level 5": 0.25,
+      "hfopenllm_v2/GPQA": 0.2995,
+      "hfopenllm_v2/MUSR": 0.4439,
+      "hfopenllm_v2/MMLU-PRO": 0.4408
     }
   },
   {
@@ -26814,12 +26799,12 @@
     "developer": "HuggingFaceTB",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "hfopenllm_v2/IFEval": 0.083,
-      "hfopenllm_v2/BBH": 0.3053,
-      "hfopenllm_v2/MATH Level 5": 0.0083,
-      "hfopenllm_v2/GPQA": 0.2651,
-      "hfopenllm_v2/MUSR": 0.3423,
-      "hfopenllm_v2/MMLU-PRO": 0.1126
+      "hfopenllm_v2/IFEval": 0.3842,
+      "hfopenllm_v2/BBH": 0.3144,
+      "hfopenllm_v2/MATH Level 5": 0.0151,
+      "hfopenllm_v2/GPQA": 0.255,
+      "hfopenllm_v2/MUSR": 0.3461,
+      "hfopenllm_v2/MMLU-PRO": 0.1117
     }
   },
   {
@@ -28221,20 +28206,6 @@
       "hfopenllm_v2/MMLU-PRO": 0.3103
     }
   },
-  {
-    "id": "icefog72/IceSakeV6RP-7b",
-    "name": "IceSakeV6RP-7b",
-    "developer": "icefog72",
-    "evaluator_relationship": null,
-    "benchmark_scores": {
-      "hfopenllm_v2/IFEval": 0.5033,
-      "hfopenllm_v2/BBH": 0.4976,
-      "hfopenllm_v2/MATH Level 5": 0.0619,
-      "hfopenllm_v2/GPQA": 0.2911,
-      "hfopenllm_v2/MUSR": 0.42,
-      "hfopenllm_v2/MMLU-PRO": 0.3093
-    }
-  },
   {
     "id": "icefog72/IceSakeV8RP-7b",
     "name": "IceSakeV8RP-7b",
@@ -28507,16 +28478,16 @@
     "developer": "infly",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "reward-bench/Score": 0.9511,
+      "reward-bench/Score": 0.7648,
+      "reward-bench/Chat": 0.9665,
+      "reward-bench/Chat Hard": 0.9101,
+      "reward-bench/Safety": 0.9644,
+      "reward-bench/Reasoning": 0.9912,
       "reward-bench/Factuality": 0.7411,
       "reward-bench/Precise IF": 0.4188,
       "reward-bench/Math": 0.6995,
-      "reward-bench/Safety": 0.9365,
       "reward-bench/Focus": 0.903,
-      "reward-bench/Ties": 0.8622,
-      "reward-bench/Chat": 0.9665,
-      "reward-bench/Chat Hard": 0.9101,
-      "reward-bench/Reasoning": 0.9912
+      "reward-bench/Ties": 0.8622
     }
   },
   {
@@ -28651,16 +28622,16 @@
     "developer": "internlm",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "reward-bench/Score": 0.3902,
-      "reward-bench/Chat": 0.9358,
-      "reward-bench/Chat Hard": 0.6623,
-      "reward-bench/Safety": 0.4711,
-      "reward-bench/Reasoning": 0.8724,
+      "reward-bench/Score": 0.8217,
       "reward-bench/Factuality": 0.2758,
       "reward-bench/Precise IF": 0.3625,
       "reward-bench/Math": 0.4426,
+      "reward-bench/Safety": 0.8162,
       "reward-bench/Focus": 0.596,
-      "reward-bench/Ties": 0.1934
+      "reward-bench/Ties": 0.1934,
+      "reward-bench/Chat": 0.9358,
+      "reward-bench/Chat Hard": 0.6623,
+      "reward-bench/Reasoning": 0.8724
     }
   },
   {
@@ -28701,16 +28672,16 @@
     "developer": "internlm",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "reward-bench/Score": 0.5335,
-      "reward-bench/Chat": 0.9916,
-      "reward-bench/Chat Hard": 0.6952,
-      "reward-bench/Safety": 0.5956,
-      "reward-bench/Reasoning": 0.9453,
+      "reward-bench/Score": 0.8759,
       "reward-bench/Factuality": 0.4211,
       "reward-bench/Precise IF": 0.4,
       "reward-bench/Math": 0.5628,
+      "reward-bench/Safety": 0.8716,
       "reward-bench/Focus": 0.7051,
-      "reward-bench/Ties": 0.5164
+      "reward-bench/Ties": 0.5164,
+      "reward-bench/Chat": 0.9916,
+      "reward-bench/Chat Hard": 0.6952,
+      "reward-bench/Reasoning": 0.9453
     }
   },
   {
@@ -30623,12 +30594,12 @@
     "developer": "jaspionjader",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "hfopenllm_v2/IFEval": 0.4418,
-      "hfopenllm_v2/BBH": 0.5406,
-      "hfopenllm_v2/MATH Level 5": 0.1352,
-      "hfopenllm_v2/GPQA": 0.3062,
+      "hfopenllm_v2/IFEval": 0.4345,
+      "hfopenllm_v2/BBH": 0.5419,
+      "hfopenllm_v2/MATH Level 5": 0.1292,
+      "hfopenllm_v2/GPQA": 0.3087,
       "hfopenllm_v2/MUSR": 0.4277,
-      "hfopenllm_v2/MMLU-PRO": 0.386
+      "hfopenllm_v2/MMLU-PRO": 0.3854
     }
   },
   {
@@ -37984,12 +37955,12 @@
     "developer": "LeroyDyer",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "hfopenllm_v2/IFEval": 0.3036,
-      "hfopenllm_v2/BBH": 0.4575,
+      "hfopenllm_v2/IFEval": 0.3066,
+      "hfopenllm_v2/BBH": 0.4577,
       "hfopenllm_v2/MATH Level 5": 0.0446,
-      "hfopenllm_v2/GPQA": 0.3012,
-      "hfopenllm_v2/MUSR": 0.4253,
-      "hfopenllm_v2/MMLU-PRO": 0.2329
+      "hfopenllm_v2/GPQA": 0.2995,
+      "hfopenllm_v2/MUSR": 0.4254,
+      "hfopenllm_v2/MMLU-PRO": 0.2318
     }
   },
   {
@@ -38012,12 +37983,12 @@
     "developer": "LeroyDyer",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "hfopenllm_v2/IFEval": 0.3798,
-      "hfopenllm_v2/BBH": 0.4483,
-      "hfopenllm_v2/MATH Level 5": 0.04,
-      "hfopenllm_v2/GPQA": 0.3129,
-      "hfopenllm_v2/MUSR": 0.4148,
-      "hfopenllm_v2/MMLU-PRO": 0.2389
+      "hfopenllm_v2/IFEval": 0.3579,
+      "hfopenllm_v2/BBH": 0.4477,
+      "hfopenllm_v2/MATH Level 5": 0.0423,
+      "hfopenllm_v2/GPQA": 0.3096,
+      "hfopenllm_v2/MUSR": 0.4134,
+      "hfopenllm_v2/MMLU-PRO": 0.2376
     }
   },
   {
@@ -39569,16 +39540,16 @@
     "developer": "LxzGordon",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "reward-bench/Score": 0.7394,
-      "reward-bench/Chat": 0.9553,
-      "reward-bench/Chat Hard": 0.8816,
-      "reward-bench/Safety": 0.9178,
-      "reward-bench/Reasoning": 0.9698,
+      "reward-bench/Score": 0.9294,
       "reward-bench/Factuality": 0.6884,
       "reward-bench/Precise IF": 0.45,
       "reward-bench/Math": 0.6393,
+      "reward-bench/Safety": 0.9108,
       "reward-bench/Focus": 0.9758,
-      "reward-bench/Ties": 0.7653
+      "reward-bench/Ties": 0.7653,
+      "reward-bench/Chat": 0.9553,
+      "reward-bench/Chat Hard": 0.8816,
+      "reward-bench/Reasoning": 0.9698
     }
   },
   {
@@ -39741,12 +39712,12 @@
     "developer": "Magpie-Align",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "hfopenllm_v2/IFEval": 0.4027,
-      "hfopenllm_v2/BBH": 0.4789,
-      "hfopenllm_v2/MATH Level 5": 0.0461,
-      "hfopenllm_v2/GPQA": 0.2768,
-      "hfopenllm_v2/MUSR": 0.3087,
-      "hfopenllm_v2/MMLU-PRO": 0.3001
+      "hfopenllm_v2/IFEval": 0.4118,
+      "hfopenllm_v2/BBH": 0.4811,
+      "hfopenllm_v2/MATH Level 5": 0.034,
+      "hfopenllm_v2/GPQA": 0.2752,
+      "hfopenllm_v2/MUSR": 0.3047,
+      "hfopenllm_v2/MMLU-PRO": 0.3006
     }
   },
   {
@@ -43235,12 +43206,12 @@
     "developer": "microsoft",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "hfopenllm_v2/IFEval": 0.5477,
-      "hfopenllm_v2/BBH": 0.5491,
-      "hfopenllm_v2/MATH Level 5": 0.1639,
-      "hfopenllm_v2/GPQA": 0.3322,
-      "hfopenllm_v2/MUSR": 0.4284,
-      "hfopenllm_v2/MMLU-PRO": 0.4022
+      "hfopenllm_v2/IFEval": 0.5613,
+      "hfopenllm_v2/BBH": 0.5676,
+      "hfopenllm_v2/MATH Level 5": 0.1163,
+      "hfopenllm_v2/GPQA": 0.3196,
+      "hfopenllm_v2/MUSR": 0.395,
+      "hfopenllm_v2/MMLU-PRO": 0.3866
     }
   },
   {
@@ -43351,12 +43322,12 @@
     "developer": "microsoft",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "hfopenllm_v2/IFEval": 0.0585,
-      "hfopenllm_v2/BBH": 0.6691,
-      "hfopenllm_v2/MATH Level 5": 0.3165,
-      "hfopenllm_v2/GPQA": 0.406,
+      "hfopenllm_v2/IFEval": 0.0488,
+      "hfopenllm_v2/BBH": 0.6703,
+      "hfopenllm_v2/MATH Level 5": 0.2787,
+      "hfopenllm_v2/GPQA": 0.401,
       "hfopenllm_v2/MUSR": 0.5034,
-      "hfopenllm_v2/MMLU-PRO": 0.5287
+      "hfopenllm_v2/MMLU-PRO": 0.5295
     }
   },
   {
@@ -43667,7 +43638,7 @@
     "developer": "MiniMax",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "terminal-bench-2.0/terminal-bench-2.0": 36.6
+      "terminal-bench-2.0/terminal-bench-2.0": 29.2
     }
   },
   {
@@ -44247,12 +44218,12 @@
     "developer": "mistralai",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "hfopenllm_v2/IFEval": 0.667,
-      "hfopenllm_v2/BBH": 0.5213,
-      "hfopenllm_v2/MATH Level 5": 0.1435,
-      "hfopenllm_v2/GPQA": 0.3238,
-      "hfopenllm_v2/MUSR": 0.3632,
-      "hfopenllm_v2/MMLU-PRO": 0.396
+      "hfopenllm_v2/IFEval": 0.6283,
+      "hfopenllm_v2/BBH": 0.583,
+      "hfopenllm_v2/MATH Level 5": 0.2039,
+      "hfopenllm_v2/GPQA": 0.3331,
+      "hfopenllm_v2/MUSR": 0.4063,
+      "hfopenllm_v2/MMLU-PRO": 0.4099
     }
   },
   {
@@ -44452,12 +44423,12 @@
     "developer": "mistralai",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "hfopenllm_v2/IFEval": 0.2415,
-      "hfopenllm_v2/BBH": 0.5087,
-      "hfopenllm_v2/MATH Level 5": 0.102,
-      "hfopenllm_v2/GPQA": 0.3138,
-      "hfopenllm_v2/MUSR": 0.4321,
-      "hfopenllm_v2/MMLU-PRO": 0.385
+      "hfopenllm_v2/IFEval": 0.2326,
+      "hfopenllm_v2/BBH": 0.5098,
+      "hfopenllm_v2/MATH Level 5": 0.0937,
+      "hfopenllm_v2/GPQA": 0.3205,
+      "hfopenllm_v2/MUSR": 0.4413,
+      "hfopenllm_v2/MMLU-PRO": 0.3871
     }
   },
   {
@@ -44758,12 +44729,12 @@
     "developer": "mlabonne",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "hfopenllm_v2/IFEval": 0.7561,
-      "hfopenllm_v2/BBH": 0.5111,
-      "hfopenllm_v2/MATH Level 5": 0.0906,
-      "hfopenllm_v2/GPQA": 0.3062,
-      "hfopenllm_v2/MUSR": 0.4019,
-      "hfopenllm_v2/MMLU-PRO": 0.3841
+      "hfopenllm_v2/IFEval": 0.4162,
+      "hfopenllm_v2/BBH": 0.5124,
+      "hfopenllm_v2/MATH Level 5": 0.0853,
+      "hfopenllm_v2/GPQA": 0.3029,
+      "hfopenllm_v2/MUSR": 0.415,
+      "hfopenllm_v2/MMLU-PRO": 0.3802
     }
   },
   {
@@ -44996,7 +44967,7 @@
     "developer": "Moonshot AI",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "terminal-bench-2.0/terminal-bench-2.0": 27.8
+      "terminal-bench-2.0/terminal-bench-2.0": 26.7
     }
   },
   {
@@ -45317,7 +45288,7 @@
     "developer": "Multiple",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "terminal-bench-2.0/terminal-bench-2.0": 72.4
+      "terminal-bench-2.0/terminal-bench-2.0": 71.0
     }
   },
   {
@@ -48273,16 +48244,16 @@
     "developer": "nicolinho",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "reward-bench/Score": 0.7667,
-      "reward-bench/Chat": 0.9665,
-      "reward-bench/Chat Hard": 0.9013,
-      "reward-bench/Safety": 0.9578,
-      "reward-bench/Reasoning": 0.9826,
+      "reward-bench/Score": 0.9444,
       "reward-bench/Factuality": 0.7853,
       "reward-bench/Precise IF": 0.3719,
       "reward-bench/Math": 0.6995,
+      "reward-bench/Safety": 0.927,
       "reward-bench/Focus": 0.9535,
-      "reward-bench/Ties": 0.8321
+      "reward-bench/Ties": 0.8321,
+      "reward-bench/Chat": 0.9665,
+      "reward-bench/Chat Hard": 0.9013,
+      "reward-bench/Reasoning": 0.9826
     }
   },
   {
@@ -48317,16 +48288,16 @@
     "developer": "nicolinho",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "reward-bench/Score": 0.7074,
-      "reward-bench/Chat": 0.9637,
-      "reward-bench/Chat Hard": 0.8684,
-      "reward-bench/Safety": 0.9467,
-      "reward-bench/Reasoning": 0.9677,
+      "reward-bench/Score": 0.9314,
       "reward-bench/Factuality": 0.6653,
       "reward-bench/Precise IF": 0.4062,
       "reward-bench/Math": 0.612,
+      "reward-bench/Safety": 0.9257,
       "reward-bench/Focus": 0.8909,
-      "reward-bench/Ties": 0.7234
+      "reward-bench/Ties": 0.7234,
+      "reward-bench/Chat": 0.9637,
+      "reward-bench/Chat Hard": 0.8684,
+      "reward-bench/Reasoning": 0.9677
     }
   },
   {
@@ -49326,6 +49297,20 @@
       "hfopenllm_v2/MMLU-PRO": 0.232
     }
   },
+  {
+    "id": "NousResearch/Yarn-Llama-2-7b-128k",
+    "name": "Yarn-Llama-2-7b-128k",
+    "developer": "NousResearch",
+    "evaluator_relationship": null,
+    "benchmark_scores": {
+      "hfopenllm_v2/IFEval": 0.1485,
+      "hfopenllm_v2/BBH": 0.3248,
+      "hfopenllm_v2/MATH Level 5": 0.0151,
+      "hfopenllm_v2/GPQA": 0.2601,
+      "hfopenllm_v2/MUSR": 0.3967,
+      "hfopenllm_v2/MMLU-PRO": 0.1791
+    }
+  },
   {
     "id": "NousResearch/Yarn-Llama-2-7b-64k",
     "name": "Yarn-Llama-2-7b-64k",
@@ -50379,12 +50364,12 @@
     "developer": "ontocord",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "hfopenllm_v2/IFEval": 0.1162,
-      "hfopenllm_v2/BBH": 0.3184,
-      "hfopenllm_v2/MATH Level 5": 0.0076,
-      "hfopenllm_v2/GPQA": 0.2634,
-      "hfopenllm_v2/MUSR": 0.3447,
-      "hfopenllm_v2/MMLU-PRO": 0.1124
+      "hfopenllm_v2/IFEval": 0.1128,
+      "hfopenllm_v2/BBH": 0.3171,
+      "hfopenllm_v2/MATH Level 5": 0.0113,
+      "hfopenllm_v2/GPQA": 0.2685,
+      "hfopenllm_v2/MUSR": 0.346,
+      "hfopenllm_v2/MMLU-PRO": 0.1129
     }
   },
   {
@@ -51606,16 +51591,16 @@
       "helm_mmlu/Virology": 0.578,
       "helm_mmlu/World Religions": 0.883,
       "helm_mmlu/Mean win rate": 0.52,
-      "reward-bench/Score": 0.8673,
+      "reward-bench/Score": 0.6493,
+      "reward-bench/Chat": 0.9609,
+      "reward-bench/Chat Hard": 0.761,
+      "reward-bench/Safety": 0.8619,
+      "reward-bench/Reasoning": 0.8661,
       "reward-bench/Factuality": 0.5684,
       "reward-bench/Precise IF": 0.3312,
       "reward-bench/Math": 0.623,
-      "reward-bench/Safety": 0.8811,
       "reward-bench/Focus": 0.7293,
-      "reward-bench/Ties": 0.7819,
-      "reward-bench/Chat": 0.9609,
-      "reward-bench/Chat Hard": 0.761,
-      "reward-bench/Reasoning": 0.8661
+      "reward-bench/Ties": 0.7819
     }
   },
   {
@@ -51693,16 +51678,16 @@
       "helm_mmlu/Virology": 0.536,
       "helm_mmlu/World Religions": 0.86,
       "helm_mmlu/Mean win rate": 0.774,
-      "reward-bench/Score": 0.8007,
+      "reward-bench/Score": 0.5796,
+      "reward-bench/Chat": 0.9497,
+      "reward-bench/Chat Hard": 0.6075,
+      "reward-bench/Safety": 0.7667,
+      "reward-bench/Reasoning": 0.8374,
       "reward-bench/Factuality": 0.4105,
       "reward-bench/Precise IF": 0.3438,
       "reward-bench/Math": 0.5191,
-      "reward-bench/Safety": 0.8081,
       "reward-bench/Focus": 0.7414,
-      "reward-bench/Ties": 0.6962,
-      "reward-bench/Chat": 0.9497,
-      "reward-bench/Chat Hard": 0.6075,
-      "reward-bench/Reasoning": 0.8374
+      "reward-bench/Ties": 0.6962
     }
   },
   {
@@ -51745,9 +51730,9 @@
       "helm_capabilities/IFEval": 0.875,
       "helm_capabilities/WildBench": 0.857,
       "helm_capabilities/Omni-MATH": 0.647,
-      "livecodebenchpro/Hard Problems": 0.04225352112676056,
-      "livecodebenchpro/Medium Problems": 0.4084507042253521,
-      "livecodebenchpro/Easy Problems": 0.8873239436619719
+      "livecodebenchpro/Hard Problems": 0.0423,
+      "livecodebenchpro/Medium Problems": 0.4085,
+      "livecodebenchpro/Easy Problems": 0.9014
     }
   },
   {
@@ -51765,7 +51750,7 @@
     "developer": "OpenAI",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "terminal-bench-2.0/terminal-bench-2.0": 24.0
+      "terminal-bench-2.0/terminal-bench-2.0": 31.9
     }
   },
   {
@@ -51788,7 +51773,7 @@
     "developer": "OpenAI",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "terminal-bench-2.0/terminal-bench-2.0": 11.5
+      "terminal-bench-2.0/terminal-bench-2.0": 7.0
     }
   },
   {
@@ -51820,7 +51805,7 @@
     "developer": "OpenAI",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "terminal-bench-2.0/terminal-bench-2.0": 57.8
+      "terminal-bench-2.0/terminal-bench-2.0": 53.5
     }
   },
   {
@@ -51847,7 +51832,7 @@
     "developer": "OpenAI",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "terminal-bench-2.0/terminal-bench-2.0": 62.9
+      "terminal-bench-2.0/terminal-bench-2.0": 60.7
     }
   },
   {
@@ -51857,14 +51842,14 @@
     "evaluator_relationship": null,
     "benchmark_scores": {
       "appworld_test_normal/appworld/test_normal": 0.0,
-      "browsecompplus/browsecompplus": 0.43,
+      "browsecompplus/browsecompplus": 0.26,
       "livecodebenchpro/Hard Problems": 0.1594,
       "livecodebenchpro/Medium Problems": 0.5211,
       "livecodebenchpro/Easy Problems": 0.9014,
-      "swe-bench/swe-bench": 0.5455,
+      "swe-bench/swe-bench": 0.57,
       "tau-bench-2_airline/tau-bench-2/airline": 0.6,
-      "tau-bench-2_retail/tau-bench-2/retail": 0.73,
-      "tau-bench-2_telecom/tau-bench-2/telecom": 0.71
+      "tau-bench-2_retail/tau-bench-2/retail": 0.68,
+      "tau-bench-2_telecom/tau-bench-2/telecom": 0.5354
     }
   },
   {
@@ -51882,7 +51867,7 @@
     "developer": "OpenAI",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "terminal-bench-2.0/terminal-bench-2.0": 77.3
+      "terminal-bench-2.0/terminal-bench-2.0": 74.6
     }
   },
   {
@@ -51946,7 +51931,7 @@
       "livecodebenchpro/Hard Problems": 0.0,
       "livecodebenchpro/Medium Problems": 0.11267605633802817,
       "livecodebenchpro/Easy Problems": 0.6619718309859155,
-      "terminal-bench-2.0/terminal-bench-2.0": 18.7
+      "terminal-bench-2.0/terminal-bench-2.0": 14.2
     }
   },
   {
@@ -52067,9 +52052,9 @@
       "helm_capabilities/IFEval": 0.929,
       "helm_capabilities/WildBench": 0.854,
       "helm_capabilities/Omni-MATH": 0.72,
-      "livecodebenchpro/Hard Problems": 0.014084507042253521,
-      "livecodebenchpro/Medium Problems": 0.30985915492957744,
-      "livecodebenchpro/Easy Problems": 0.8873239436619719
+      "livecodebenchpro/Hard Problems": 0.0143,
+      "livecodebenchpro/Medium Problems": 0.2923,
+      "livecodebenchpro/Easy Problems": 0.8571
     }
   },
   {
@@ -52213,17 +52198,17 @@
     "developer": "OpenAssistant",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "reward-bench/Score": 0.2653,
-      "reward-bench/Chat": 0.9246,
-      "reward-bench/Chat Hard": 0.3728,
-      "reward-bench/Safety": 0.3289,
-      "reward-bench/Reasoning": 0.5855,
-      "reward-bench/Prior Sets (0.5 weight)": 0.6801,
+      "reward-bench/Score": 0.615,
       "reward-bench/Factuality": 0.3979,
       "reward-bench/Precise IF": 0.2875,
       "reward-bench/Math": 0.377,
+      "reward-bench/Safety": 0.5446,
       "reward-bench/Focus": 0.1535,
-      "reward-bench/Ties": 0.047
+      "reward-bench/Ties": 0.047,
+      "reward-bench/Chat": 0.9246,
+      "reward-bench/Chat Hard": 0.3728,
+      "reward-bench/Reasoning": 0.5855,
+      "reward-bench/Prior Sets (0.5 weight)": 0.6801
     }
   },
   {
@@ -52345,17 +52330,17 @@
     "developer": "openbmb",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "reward-bench/Score": 0.4683,
-      "reward-bench/Chat": 0.9637,
-      "reward-bench/Chat Hard": 0.5548,
-      "reward-bench/Safety": 0.5089,
-      "reward-bench/Reasoning": 0.6244,
-      "reward-bench/Prior Sets (0.5 weight)": 0.7294,
+      "reward-bench/Score": 0.6903,
       "reward-bench/Factuality": 0.5063,
       "reward-bench/Precise IF": 0.3312,
       "reward-bench/Math": 0.5519,
+      "reward-bench/Safety": 0.5986,
       "reward-bench/Focus": 0.6081,
-      "reward-bench/Ties": 0.3036
+      "reward-bench/Ties": 0.3036,
+      "reward-bench/Chat": 0.9637,
+      "reward-bench/Chat Hard": 0.5548,
+      "reward-bench/Reasoning": 0.6244,
+      "reward-bench/Prior Sets (0.5 weight)": 0.7294
     }
   },
   {
@@ -53816,17 +53801,17 @@
     "developer": "PKU-Alignment",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "reward-bench/Score": 0.5798,
+      "reward-bench/Score": 0.3332,
+      "reward-bench/Chat": 0.6173,
+      "reward-bench/Chat Hard": 0.4232,
+      "reward-bench/Safety": 0.7589,
+      "reward-bench/Reasoning": 0.5482,
+      "reward-bench/Prior Sets (0.5 weight)": 0.57,
       "reward-bench/Factuality": 0.3263,
       "reward-bench/Precise IF": 0.2313,
       "reward-bench/Math": 0.3989,
-      "reward-bench/Safety": 0.7351,
       "reward-bench/Focus": 0.2939,
-      "reward-bench/Ties": -0.01,
-      "reward-bench/Chat": 0.6173,
-      "reward-bench/Chat Hard": 0.4232,
-      "reward-bench/Reasoning": 0.5482,
-      "reward-bench/Prior Sets (0.5 weight)": 0.57
+      "reward-bench/Ties": -0.01
     }
   },
   {
@@ -53835,17 +53820,17 @@
     "developer": "PKU-Alignment",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "reward-bench/Score": 0.1606,
-      "reward-bench/Chat": 0.8184,
-      "reward-bench/Chat Hard": 0.2873,
-      "reward-bench/Safety": 0.1422,
-      "reward-bench/Reasoning": 0.346,
-      "reward-bench/Prior Sets (0.5 weight)": 0.5993,
+      "reward-bench/Score": 0.4727,
       "reward-bench/Factuality": 0.2105,
       "reward-bench/Precise IF": 0.2938,
       "reward-bench/Math": 0.2623,
+      "reward-bench/Safety": 0.3757,
       "reward-bench/Focus": 0.0646,
-      "reward-bench/Ties": -0.01
+      "reward-bench/Ties": -0.01,
+      "reward-bench/Chat": 0.8184,
+      "reward-bench/Chat Hard": 0.2873,
+      "reward-bench/Reasoning": 0.346,
+      "reward-bench/Prior Sets (0.5 weight)": 0.5993
     }
   },
   {
@@ -53873,17 +53858,17 @@
     "developer": "PKU-Alignment",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "reward-bench/Score": 0.2544,
-      "reward-bench/Chat": 0.8994,
-      "reward-bench/Chat Hard": 0.364,
-      "reward-bench/Safety": 0.3156,
-      "reward-bench/Reasoning": 0.6887,
-      "reward-bench/Prior Sets (0.5 weight)": 0.6171,
+      "reward-bench/Score": 0.6366,
       "reward-bench/Factuality": 0.2168,
       "reward-bench/Precise IF": 0.2562,
       "reward-bench/Math": 0.3825,
+      "reward-bench/Safety": 0.6041,
       "reward-bench/Focus": 0.2606,
-      "reward-bench/Ties": 0.0944
+      "reward-bench/Ties": 0.0944,
+      "reward-bench/Chat": 0.8994,
+      "reward-bench/Chat Hard": 0.364,
+      "reward-bench/Reasoning": 0.6887,
+      "reward-bench/Prior Sets (0.5 weight)": 0.6171
     }
   },
   {
@@ -54158,11 +54143,11 @@
     "evaluator_relationship": null,
     "benchmark_scores": {
       "hfopenllm_v2/IFEval": 0.1757,
-      "hfopenllm_v2/BBH": 0.274,
+      "hfopenllm_v2/BBH": 0.276,
       "hfopenllm_v2/MATH Level 5": 0.0,
-      "hfopenllm_v2/GPQA": 0.25,
-      "hfopenllm_v2/MUSR": 0.3753,
-      "hfopenllm_v2/MMLU-PRO": 0.112
+      "hfopenllm_v2/GPQA": 0.2534,
+      "hfopenllm_v2/MUSR": 0.3339,
+      "hfopenllm_v2/MMLU-PRO": 0.1123
     }
   },
   {
@@ -54241,12 +54226,12 @@
     "developer": "princeton-nlp",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "hfopenllm_v2/IFEval": 0.3978,
-      "hfopenllm_v2/BBH": 0.4983,
-      "hfopenllm_v2/MATH Level 5": 0.0582,
-      "hfopenllm_v2/GPQA": 0.281,
-      "hfopenllm_v2/MUSR": 0.425,
-      "hfopenllm_v2/MMLU-PRO": 0.3246
+      "hfopenllm_v2/IFEval": 0.5508,
+      "hfopenllm_v2/BBH": 0.5028,
+      "hfopenllm_v2/MATH Level 5": 0.0529,
+      "hfopenllm_v2/GPQA": 0.2861,
+      "hfopenllm_v2/MUSR": 0.4266,
+      "hfopenllm_v2/MMLU-PRO": 0.3231
     }
   },
   {
@@ -54969,12 +54954,12 @@
     "developer": "prithivMLmods",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "hfopenllm_v2/IFEval": 0.6052,
-      "hfopenllm_v2/BBH": 0.6317,
-      "hfopenllm_v2/MATH Level 5": 0.4789,
-      "hfopenllm_v2/GPQA": 0.3742,
-      "hfopenllm_v2/MUSR": 0.486,
-      "hfopenllm_v2/MMLU-PRO": 0.5302
+      "hfopenllm_v2/IFEval": 0.6064,
+      "hfopenllm_v2/BBH": 0.6296,
+      "hfopenllm_v2/MATH Level 5": 0.3708,
+      "hfopenllm_v2/GPQA": 0.3733,
+      "hfopenllm_v2/MUSR": 0.4873,
+      "hfopenllm_v2/MMLU-PRO": 0.5307
     }
   },
   {
@@ -56591,12 +56576,12 @@
     "developer": "qingy2019",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "hfopenllm_v2/IFEval": 0.6005,
-      "hfopenllm_v2/BBH": 0.6356,
-      "hfopenllm_v2/MATH Level 5": 0.2764,
-      "hfopenllm_v2/GPQA": 0.3691,
+      "hfopenllm_v2/IFEval": 0.6066,
+      "hfopenllm_v2/BBH": 0.635,
+      "hfopenllm_v2/MATH Level 5": 0.3716,
+      "hfopenllm_v2/GPQA": 0.3725,
       "hfopenllm_v2/MUSR": 0.4757,
-      "hfopenllm_v2/MMLU-PRO": 0.5339
+      "hfopenllm_v2/MMLU-PRO": 0.5331
     }
   },
   {
@@ -56997,12 +56982,12 @@
     "developer": "Quazim0t0",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "hfopenllm_v2/IFEval": 0.6654,
-      "hfopenllm_v2/BBH": 0.6901,
-      "hfopenllm_v2/MATH Level 5": 0.4698,
-      "hfopenllm_v2/GPQA": 0.3331,
-      "hfopenllm_v2/MUSR": 0.431,
-      "hfopenllm_v2/MMLU-PRO": 0.5426
+      "hfopenllm_v2/IFEval": 0.6718,
+      "hfopenllm_v2/BBH": 0.6891,
+      "hfopenllm_v2/MATH Level 5": 0.4985,
+      "hfopenllm_v2/GPQA": 0.3339,
+      "hfopenllm_v2/MUSR": 0.4323,
+      "hfopenllm_v2/MMLU-PRO": 0.5408
     }
   },
   {
@@ -57529,12 +57514,12 @@
     "developer": "Quazim0t0",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "hfopenllm_v2/IFEval": 0.2922,
-      "hfopenllm_v2/BBH": 0.6559,
-      "hfopenllm_v2/MATH Level 5": 0.2545,
-      "hfopenllm_v2/GPQA": 0.2659,
-      "hfopenllm_v2/MUSR": 0.3929,
-      "hfopenllm_v2/MMLU-PRO": 0.5207
+      "hfopenllm_v2/IFEval": 0.7016,
+      "hfopenllm_v2/BBH": 0.6942,
+      "hfopenllm_v2/MATH Level 5": 0.4116,
+      "hfopenllm_v2/GPQA": 0.3624,
+      "hfopenllm_v2/MUSR": 0.4571,
+      "hfopenllm_v2/MMLU-PRO": 0.5411
     }
   },
   {
@@ -58633,12 +58618,12 @@
     "developer": "Qwen",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "hfopenllm_v2/IFEval": 0.3071,
-      "hfopenllm_v2/BBH": 0.3341,
-      "hfopenllm_v2/MATH Level 5": 0.0,
-      "hfopenllm_v2/GPQA": 0.2576,
-      "hfopenllm_v2/MUSR": 0.3329,
-      "hfopenllm_v2/MMLU-PRO": 0.1697
+      "hfopenllm_v2/IFEval": 0.3153,
+      "hfopenllm_v2/BBH": 0.3322,
+      "hfopenllm_v2/MATH Level 5": 0.1035,
+      "hfopenllm_v2/GPQA": 0.2592,
+      "hfopenllm_v2/MUSR": 0.3342,
+      "hfopenllm_v2/MMLU-PRO": 0.172
     }
   },
   {
@@ -59368,16 +59353,16 @@
     "developer": "Ray2333",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "reward-bench/Score": 0.5966,
-      "reward-bench/Chat": 0.9302,
-      "reward-bench/Chat Hard": 0.7719,
-      "reward-bench/Safety": 0.9222,
-      "reward-bench/Reasoning": 0.912,
+      "reward-bench/Score": 0.8839,
       "reward-bench/Factuality": 0.5305,
       "reward-bench/Precise IF": 0.3125,
       "reward-bench/Math": 0.5902,
+      "reward-bench/Safety": 0.9216,
       "reward-bench/Focus": 0.7455,
-      "reward-bench/Ties": 0.4788
+      "reward-bench/Ties": 0.4788,
+      "reward-bench/Chat": 0.9302,
+      "reward-bench/Chat Hard": 0.7719,
+      "reward-bench/Reasoning": 0.912
     }
   },
   {
@@ -59405,16 +59390,16 @@
     "developer": "Ray2333",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "reward-bench/Score": 0.6766,
-      "reward-bench/Chat": 0.9553,
-      "reward-bench/Chat Hard": 0.8618,
-      "reward-bench/Safety": 0.9222,
-      "reward-bench/Reasoning": 0.9362,
+      "reward-bench/Score": 0.9154,
       "reward-bench/Factuality": 0.6274,
       "reward-bench/Precise IF": 0.35,
       "reward-bench/Math": 0.5847,
+      "reward-bench/Safety": 0.9081,
       "reward-bench/Focus": 0.8929,
-      "reward-bench/Ties": 0.6824
+      "reward-bench/Ties": 0.6824,
+      "reward-bench/Chat": 0.9553,
+      "reward-bench/Chat Hard": 0.8618,
+      "reward-bench/Reasoning": 0.9362
     }
   },
   {
@@ -59423,17 +59408,17 @@
     "developer": "Ray2333",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "reward-bench/Score": 0.8542,
+      "reward-bench/Score": 0.6089,
+      "reward-bench/Chat": 0.986,
+      "reward-bench/Chat Hard": 0.6776,
+      "reward-bench/Safety": 0.7867,
+      "reward-bench/Reasoning": 0.9229,
+      "reward-bench/Prior Sets (0.5 weight)": 0.7309,
       "reward-bench/Factuality": 0.6189,
       "reward-bench/Precise IF": 0.3875,
       "reward-bench/Math": 0.5792,
-      "reward-bench/Safety": 0.8919,
       "reward-bench/Focus": 0.6828,
-      "reward-bench/Ties": 0.5981,
-      "reward-bench/Chat": 0.986,
-      "reward-bench/Chat Hard": 0.6776,
-      "reward-bench/Reasoning": 0.9229,
-      "reward-bench/Prior Sets (0.5 weight)": 0.7309
+      "reward-bench/Ties": 0.5981
     }
   },
   {
@@ -59525,12 +59510,12 @@
     "developer": "recoilme",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "hfopenllm_v2/IFEval": 0.7592,
-      "hfopenllm_v2/BBH": 0.6026,
-      "hfopenllm_v2/MATH Level 5": 0.0529,
-      "hfopenllm_v2/GPQA": 0.3289,
-      "hfopenllm_v2/MUSR": 0.4099,
-      "hfopenllm_v2/MMLU-PRO": 0.4163
+      "hfopenllm_v2/IFEval": 0.2747,
+      "hfopenllm_v2/BBH": 0.6031,
+      "hfopenllm_v2/MATH Level 5": 0.0831,
+      "hfopenllm_v2/GPQA": 0.3305,
+      "hfopenllm_v2/MUSR": 0.4686,
+      "hfopenllm_v2/MMLU-PRO": 0.4122
     }
   },
   {
@@ -59539,12 +59524,12 @@
     "developer": "recoilme",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "hfopenllm_v2/IFEval": 0.5761,
-      "hfopenllm_v2/BBH": 0.602,
-      "hfopenllm_v2/MATH Level 5": 0.1888,
-      "hfopenllm_v2/GPQA": 0.3372,
-      "hfopenllm_v2/MUSR": 0.4632,
-      "hfopenllm_v2/MMLU-PRO": 0.4039
+      "hfopenllm_v2/IFEval": 0.7439,
+      "hfopenllm_v2/BBH": 0.5993,
+      "hfopenllm_v2/MATH Level 5": 0.0876,
+      "hfopenllm_v2/GPQA": 0.3238,
+      "hfopenllm_v2/MUSR": 0.4204,
+      "hfopenllm_v2/MMLU-PRO": 0.4072
     }
   },
   {
@@ -59707,12 +59692,12 @@
     "developer": "Replete-AI",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "hfopenllm_v2/IFEval": 0.0905,
-      "hfopenllm_v2/BBH": 0.2985,
+      "hfopenllm_v2/IFEval": 0.0932,
+      "hfopenllm_v2/BBH": 0.2977,
       "hfopenllm_v2/MATH Level 5": 0.0,
-      "hfopenllm_v2/GPQA": 0.2534,
-      "hfopenllm_v2/MUSR": 0.3848,
-      "hfopenllm_v2/MMLU-PRO": 0.1158
+      "hfopenllm_v2/GPQA": 0.2475,
+      "hfopenllm_v2/MUSR": 0.3941,
+      "hfopenllm_v2/MMLU-PRO": 0.1157
     }
   },
   {
@@ -62478,17 +62463,17 @@
     "developer": "sfairXC",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "reward-bench/Score": 0.8338,
+      "reward-bench/Score": 0.6292,
+      "reward-bench/Chat": 0.9944,
+      "reward-bench/Chat Hard": 0.6513,
+      "reward-bench/Safety": 0.7667,
+      "reward-bench/Reasoning": 0.8644,
+      "reward-bench/Prior Sets (0.5 weight)": 0.7492,
       "reward-bench/Factuality": 0.5916,
       "reward-bench/Precise IF": 0.4188,
       "reward-bench/Math": 0.6284,
-      "reward-bench/Safety": 0.8676,
       "reward-bench/Focus": 0.7051,
-      "reward-bench/Ties": 0.6647,
-      "reward-bench/Chat": 0.9944,
-      "reward-bench/Chat Hard": 0.6513,
-      "reward-bench/Reasoning": 0.8644,
-      "reward-bench/Prior Sets (0.5 weight)": 0.7492
+      "reward-bench/Ties": 0.6647
     }
   },
   {
@@ -62567,16 +62552,16 @@
     "developer": "ShikaiChen",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "reward-bench/Score": 0.9499,
+      "reward-bench/Score": 0.7249,
+      "reward-bench/Chat": 0.9637,
+      "reward-bench/Chat Hard": 0.9079,
+      "reward-bench/Safety": 0.9222,
+      "reward-bench/Reasoning": 0.9903,
       "reward-bench/Factuality": 0.7558,
       "reward-bench/Precise IF": 0.35,
       "reward-bench/Math": 0.6448,
-      "reward-bench/Safety": 0.9378,
       "reward-bench/Focus": 0.9131,
-      "reward-bench/Ties": 0.7633,
-      "reward-bench/Chat": 0.9637,
-      "reward-bench/Chat Hard": 0.9079,
-      "reward-bench/Reasoning": 0.9903
+      "reward-bench/Ties": 0.7633
     }
   },
   {
@@ -63269,16 +63254,16 @@
     "developer": "Skywork",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "reward-bench/Score": 0.7576,
-      "reward-bench/Chat": 0.9581,
-      "reward-bench/Chat Hard": 0.9145,
-      "reward-bench/Safety": 0.9422,
-      "reward-bench/Reasoning": 0.9606,
+      "reward-bench/Score": 0.938,
       "reward-bench/Factuality": 0.7368,
       "reward-bench/Precise IF": 0.4031,
       "reward-bench/Math": 0.7049,
+      "reward-bench/Safety": 0.9189,
       "reward-bench/Focus": 0.9323,
-      "reward-bench/Ties": 0.8261
+      "reward-bench/Ties": 0.8261,
+      "reward-bench/Chat": 0.9581,
+      "reward-bench/Chat Hard": 0.9145,
+      "reward-bench/Reasoning": 0.9606
     }
   },
   {
@@ -63452,16 +63437,16 @@
     "developer": "Skywork",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "reward-bench/Score": 0.6885,
-      "reward-bench/Chat": 0.8994,
-      "reward-bench/Chat Hard": 0.875,
-      "reward-bench/Safety": 0.8911,
-      "reward-bench/Reasoning": 0.9176,
+      "reward-bench/Score": 0.9007,
       "reward-bench/Factuality": 0.6063,
       "reward-bench/Precise IF": 0.35,
       "reward-bench/Math": 0.6339,
+      "reward-bench/Safety": 0.9108,
       "reward-bench/Focus": 0.8909,
-      "reward-bench/Ties": 0.7586
+      "reward-bench/Ties": 0.7586,
+      "reward-bench/Chat": 0.8994,
+      "reward-bench/Chat Hard": 0.875,
+      "reward-bench/Reasoning": 0.9176
     }
   },
   {
@@ -64308,12 +64293,12 @@
     "developer": "sometimesanotion",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "hfopenllm_v2/IFEval": 0.5367,
-      "hfopenllm_v2/BBH": 0.6561,
-      "hfopenllm_v2/MATH Level 5": 0.358,
-      "hfopenllm_v2/GPQA": 0.3867,
-      "hfopenllm_v2/MUSR": 0.474,
-      "hfopenllm_v2/MMLU-PRO": 0.5395
+      "hfopenllm_v2/IFEval": 0.5278,
+      "hfopenllm_v2/BBH": 0.6557,
+      "hfopenllm_v2/MATH Level 5": 0.3119,
+      "hfopenllm_v2/GPQA": 0.3842,
+      "hfopenllm_v2/MUSR": 0.4754,
+      "hfopenllm_v2/MMLU-PRO": 0.5396
     }
   },
   {
@@ -66770,12 +66755,12 @@
     "developer": "tanliboy",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "hfopenllm_v2/IFEval": 0.4501,
-      "hfopenllm_v2/BBH": 0.5472,
-      "hfopenllm_v2/MATH Level 5": 0.0944,
-      "hfopenllm_v2/GPQA": 0.3138,
-      "hfopenllm_v2/MUSR": 0.4017,
-      "hfopenllm_v2/MMLU-PRO": 0.3792
+      "hfopenllm_v2/IFEval": 0.1829,
+      "hfopenllm_v2/BBH": 0.5488,
+      "hfopenllm_v2/MATH Level 5": 0.0,
+      "hfopenllm_v2/GPQA": 0.3104,
+      "hfopenllm_v2/MUSR": 0.4056,
+      "hfopenllm_v2/MMLU-PRO": 0.3805
     }
   },
   {
@@ -70986,12 +70971,12 @@
     "developer": "ValiantLabs",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "hfopenllm_v2/IFEval": 0.7168,
-      "hfopenllm_v2/BBH": 0.4911,
-      "hfopenllm_v2/MATH Level 5": 0.1533,
-      "hfopenllm_v2/GPQA": 0.2861,
-      "hfopenllm_v2/MUSR": 0.3512,
-      "hfopenllm_v2/MMLU-PRO": 0.3663
+      "hfopenllm_v2/IFEval": 0.3496,
+      "hfopenllm_v2/BBH": 0.4947,
+      "hfopenllm_v2/MATH Level 5": 0.1269,
+      "hfopenllm_v2/GPQA": 0.3037,
+      "hfopenllm_v2/MUSR": 0.3959,
+      "hfopenllm_v2/MMLU-PRO": 0.3644
     }
   },
   {
@@ -71672,17 +71657,17 @@
     "developer": "weqweasdas",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "reward-bench/Score": 0.5027,
+      "reward-bench/Score": 0.2498,
+      "reward-bench/Chat": 0.8184,
+      "reward-bench/Chat Hard": 0.3728,
+      "reward-bench/Safety": 0.24,
+      "reward-bench/Reasoning": 0.3281,
+      "reward-bench/Prior Sets (0.5 weight)": 0.6564,
       "reward-bench/Factuality": 0.3642,
       "reward-bench/Precise IF": 0.275,
       "reward-bench/Math": 0.3497,
-      "reward-bench/Safety": 0.4149,
       "reward-bench/Focus": 0.2384,
-      "reward-bench/Ties": 0.0315,
-      "reward-bench/Chat": 0.8184,
-      "reward-bench/Chat Hard": 0.3728,
-      "reward-bench/Reasoning": 0.3281,
-      "reward-bench/Prior Sets (0.5 weight)": 0.6564
+      "reward-bench/Ties": 0.0315
     }
   },
   {
@@ -71691,17 +71676,17 @@
     "developer": "weqweasdas",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "reward-bench/Score": 0.6549,
+      "reward-bench/Score": 0.3057,
+      "reward-bench/Chat": 0.9441,
+      "reward-bench/Chat Hard": 0.4079,
+      "reward-bench/Safety": 0.3311,
+      "reward-bench/Reasoning": 0.7637,
+      "reward-bench/Prior Sets (0.5 weight)": 0.6652,
       "reward-bench/Factuality": 0.3705,
       "reward-bench/Precise IF": 0.2812,
       "reward-bench/Math": 0.4317,
-      "reward-bench/Safety": 0.4986,
       "reward-bench/Focus": 0.2343,
-      "reward-bench/Ties": 0.1851,
-      "reward-bench/Chat": 0.9441,
-      "reward-bench/Chat Hard": 0.4079,
-      "reward-bench/Reasoning": 0.7637,
-      "reward-bench/Prior Sets (0.5 weight)": 0.6652
+      "reward-bench/Ties": 0.1851
     }
   },
   {
@@ -71743,17 +71728,17 @@
     "developer": "weqweasdas",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "reward-bench/Score": 0.7982,
+      "reward-bench/Score": 0.596,
+      "reward-bench/Chat": 0.9665,
+      "reward-bench/Chat Hard": 0.6053,
+      "reward-bench/Safety": 0.6911,
+      "reward-bench/Reasoning": 0.7736,
+      "reward-bench/Prior Sets (0.5 weight)": 0.753,
       "reward-bench/Factuality": 0.5937,
       "reward-bench/Precise IF": 0.3438,
       "reward-bench/Math": 0.5956,
-      "reward-bench/Safety": 0.8703,
       "reward-bench/Focus": 0.7293,
-      "reward-bench/Ties": 0.6226,
-      "reward-bench/Chat": 0.9665,
-      "reward-bench/Chat Hard": 0.6053,
-      "reward-bench/Reasoning": 0.7736,
-      "reward-bench/Prior Sets (0.5 weight)": 0.753
+      "reward-bench/Ties": 0.6226
     }
   },
   {
@@ -73033,12 +73018,12 @@
     "developer": "yam-peleg",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "hfopenllm_v2/IFEval": 0.1856,
-      "hfopenllm_v2/BBH": 0.4149,
-      "hfopenllm_v2/MATH Level 5": 0.0234,
-      "hfopenllm_v2/GPQA": 0.276,
-      "hfopenllm_v2/MUSR": 0.3765,
-      "hfopenllm_v2/MMLU-PRO": 0.2573
+      "hfopenllm_v2/IFEval": 0.177,
+      "hfopenllm_v2/BBH": 0.3411,
+      "hfopenllm_v2/MATH Level 5": 0.031,
+      "hfopenllm_v2/GPQA": 0.2534,
+      "hfopenllm_v2/MUSR": 0.374,
+      "hfopenllm_v2/MMLU-PRO": 0.2529
     }
   },
   {
@@ -75535,7 +75520,7 @@
     "developer": "Z-AI",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "terminal-bench-2.0/terminal-bench-2.0": 33.3
+      "terminal-bench-2.0/terminal-bench-2.0": 33.4
     }
   },
   {
diff --git a/data/models/abhishek_autotrain-0tmgq-5tpbg.json b/data/models/abhishek_autotrain-0tmgq-5tpbg.json
index ac8f1c0a411cfe237fa1ffe1aaf7d7772ddbfda3..b3c557de2c59adc76d997235e3428686e7c95bbc 100644
--- a/data/models/abhishek_autotrain-0tmgq-5tpbg.json
+++ b/data/models/abhishek_autotrain-0tmgq-5tpbg.json
@@ -5,7 +5,7 @@
     "developer": "abhishek",
     "inference_platform": "unknown",
     "additional_details": {
-      "precision": "float16",
+      "precision": "bfloat16",
       "architecture": "LlamaForCausalLM",
       "params_billions": "0.135"
     }
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1957
+            "score": 0.1952
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3135
+            "score": 0.3127
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0
+            "score": 0.0128
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2517
+            "score": 0.2592
           }
         },
         {
@@ -116,7 +116,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.365
+            "score": 0.3584
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1151
+            "score": 0.1144
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1952
+            "score": 0.1957
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3127
+            "score": 0.3135
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0128
+            "score": 0.0
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2592
+            "score": 0.2517
           }
         },
         {
@@ -246,7 +246,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3584
+            "score": 0.365
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1144
+            "score": 0.1151
           }
         }
       ],
diff --git a/data/models/adriszmar_qaimath-qwen2.5-7b-ties.json b/data/models/adriszmar_qaimath-qwen2.5-7b-ties.json
index 776a7c662b5afb276bf059bb90896cee5cd968ec..a8a69697e53329e56da6b7741229b84b4f2eeb85 100644
--- a/data/models/adriszmar_qaimath-qwen2.5-7b-ties.json
+++ b/data/models/adriszmar_qaimath-qwen2.5-7b-ties.json
@@ -5,7 +5,7 @@
     "developer": "adriszmar",
     "inference_platform": "unknown",
     "additional_details": {
-      "precision": "bfloat16",
+      "precision": "float16",
       "architecture": "Qwen2ForCausalLM",
       "params_billions": "7.616"
     }
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1685
+            "score": 0.1746
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3124
+            "score": 0.3126
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0015
+            "score": 0.0
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2492
+            "score": 0.245
           }
         },
         {
@@ -116,7 +116,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3963
+            "score": 0.4096
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1066
+            "score": 0.1087
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1746
+            "score": 0.1685
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3126
+            "score": 0.3124
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0
+            "score": 0.0015
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.245
+            "score": 0.2492
           }
         },
         {
@@ -246,7 +246,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4096
+            "score": 0.3963
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1087
+            "score": 0.1066
           }
         }
       ],
diff --git a/data/models/ai2_tulu-2-7b-rm-v0-nectar-binarized-3.8m-check....json b/data/models/ai2_tulu-2-7b-rm-v0-nectar-binarized-3.8m-check....json
index f109864a284814ea86e7b02eb2f140eae70857b8..036d2144a17c2773cc45b3fcdc429ec4c85d29b1 100644
--- a/data/models/ai2_tulu-2-7b-rm-v0-nectar-binarized-3.8m-check....json
+++ b/data/models/ai2_tulu-2-7b-rm-v0-nectar-binarized-3.8m-check....json
@@ -38,7 +38,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6905
+            "score": 0.7058
           },
           "source_data": {
             "dataset_name": "RewardBench",
@@ -56,7 +56,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9441
+            "score": 0.9525
           },
           "source_data": {
             "dataset_name": "RewardBench",
@@ -74,7 +74,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3596
+            "score": 0.3947
           },
           "source_data": {
             "dataset_name": "RewardBench",
@@ -92,7 +92,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7676
+            "score": 0.7703
           },
           "source_data": {
             "dataset_name": "RewardBench",
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7004
+            "score": 0.6905
           },
           "source_data": {
             "dataset_name": "RewardBench",
@@ -152,7 +152,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9413
+            "score": 0.9441
           },
           "source_data": {
             "dataset_name": "RewardBench",
@@ -170,7 +170,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3882
+            "score": 0.3596
           },
           "source_data": {
             "dataset_name": "RewardBench",
@@ -188,7 +188,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7716
+            "score": 0.7676
           },
           "source_data": {
             "dataset_name": "RewardBench",
@@ -230,7 +230,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6945
+            "score": 0.7004
           },
           "source_data": {
             "dataset_name": "RewardBench",
@@ -248,7 +248,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9385
+            "score": 0.9413
           },
           "source_data": {
             "dataset_name": "RewardBench",
@@ -266,7 +266,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3706
+            "score": 0.3882
           },
           "source_data": {
             "dataset_name": "RewardBench",
@@ -284,7 +284,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7743
+            "score": 0.7716
           },
           "source_data": {
             "dataset_name": "RewardBench",
@@ -326,7 +326,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7008
+            "score": 0.6945
           },
           "source_data": {
             "dataset_name": "RewardBench",
@@ -362,7 +362,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3882
+            "score": 0.3706
           },
           "source_data": {
             "dataset_name": "RewardBench",
@@ -380,7 +380,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7757
+            "score": 0.7743
           },
           "source_data": {
             "dataset_name": "RewardBench",
@@ -422,7 +422,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6895
+            "score": 0.6808
           },
           "source_data": {
             "dataset_name": "RewardBench",
@@ -440,7 +440,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9385
+            "score": 0.9302
           },
           "source_data": {
             "dataset_name": "RewardBench",
@@ -458,7 +458,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3706
+            "score": 0.3596
           },
           "source_data": {
             "dataset_name": "RewardBench",
@@ -476,7 +476,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7595
+            "score": 0.7527
           },
           "source_data": {
             "dataset_name": "RewardBench",
@@ -518,7 +518,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6808
+            "score": 0.7008
           },
           "source_data": {
             "dataset_name": "RewardBench",
@@ -536,7 +536,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9302
+            "score": 0.9385
           },
           "source_data": {
             "dataset_name": "RewardBench",
@@ -554,7 +554,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3596
+            "score": 0.3882
           },
           "source_data": {
             "dataset_name": "RewardBench",
@@ -572,7 +572,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7527
+            "score": 0.7757
           },
           "source_data": {
             "dataset_name": "RewardBench",
@@ -710,7 +710,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7058
+            "score": 0.6924
           },
           "source_data": {
             "dataset_name": "RewardBench",
@@ -728,7 +728,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9525
+            "score": 0.9441
           },
           "source_data": {
             "dataset_name": "RewardBench",
@@ -746,7 +746,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3947
+            "score": 0.3575
           },
           "source_data": {
             "dataset_name": "RewardBench",
@@ -764,7 +764,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7703
+            "score": 0.7757
           },
           "source_data": {
             "dataset_name": "RewardBench",
@@ -806,7 +806,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6924
+            "score": 0.6895
           },
           "source_data": {
             "dataset_name": "RewardBench",
@@ -824,7 +824,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9441
+            "score": 0.9385
           },
           "source_data": {
             "dataset_name": "RewardBench",
@@ -842,7 +842,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3575
+            "score": 0.3706
           },
           "source_data": {
             "dataset_name": "RewardBench",
@@ -860,7 +860,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7757
+            "score": 0.7595
           },
           "source_data": {
             "dataset_name": "RewardBench",
diff --git a/data/models/akjindal53244_llama-3.1-storm-8b.json b/data/models/akjindal53244_llama-3.1-storm-8b.json
index cd06cbbbbe2ccc306c529154ea621a16fb9ebcf6..10080988b150f205c06f956e608326efa2dd3fb0 100644
--- a/data/models/akjindal53244_llama-3.1-storm-8b.json
+++ b/data/models/akjindal53244_llama-3.1-storm-8b.json
@@ -5,7 +5,7 @@
     "developer": "akjindal53244",
     "inference_platform": "unknown",
     "additional_details": {
-      "precision": "float16",
+      "precision": "bfloat16",
       "architecture": "LlamaForCausalLM",
       "params_billions": "8.03"
     }
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.8051
+            "score": 0.8033
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5189
+            "score": 0.5196
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1722
+            "score": 0.1624
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3263
+            "score": 0.3096
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3803
+            "score": 0.3812
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.8033
+            "score": 0.8051
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5196
+            "score": 0.5189
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1624
+            "score": 0.1722
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3096
+            "score": 0.3263
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3812
+            "score": 0.3803
           }
         }
       ],
diff --git a/data/models/alibaba_qwen-3-coder-480b.json b/data/models/alibaba_qwen-3-coder-480b.json
index 4f06f3ef146c1e8e47df3955820bbce15d9ad09d..5529ecfec8fec832ba0fc670045bbad34374bc66 100644
--- a/data/models/alibaba_qwen-3-coder-480b.json
+++ b/data/models/alibaba_qwen-3-coder-480b.json
@@ -4,13 +4,13 @@
     "id": "alibaba/qwen-3-coder-480b",
     "developer": "Alibaba",
     "additional_details": {
-      "agent_name": "OpenHands",
-      "agent_organization": "OpenHands"
+      "agent_name": "Dakou Agent",
+      "agent_organization": "iflow"
     }
   },
   "evaluations": [
     {
-      "evaluation_id": "terminal-bench-2.0/openhands__qwen-3-coder-480b/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/dakou-agent__qwen-3-coder-480b/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -34,7 +34,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-11-02",
+          "evaluation_timestamp": "2025-12-28",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -43,7 +43,7 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 25.4,
+            "score": 27.2,
             "uncertainty": {
               "standard_error": {
                 "value": 2.6
@@ -53,7 +53,7 @@
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"OpenHands\" -m \"Qwen 3 Coder 480B\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Dakou Agent\" -m \"Qwen 3 Coder 480B\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -70,7 +70,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"OpenHands\" -m \"Qwen 3 Coder 480B\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Dakou Agent\" -m \"Qwen 3 Coder 480B\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -158,7 +158,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/dakou-agent__qwen-3-coder-480b/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/openhands__qwen-3-coder-480b/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -182,7 +182,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-12-28",
+          "evaluation_timestamp": "2025-11-02",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -191,7 +191,7 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 27.2,
+            "score": 25.4,
             "uncertainty": {
               "standard_error": {
                 "value": 2.6
@@ -201,7 +201,7 @@
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Dakou Agent\" -m \"Qwen 3 Coder 480B\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"OpenHands\" -m \"Qwen 3 Coder 480B\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -218,7 +218,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Dakou Agent\" -m \"Qwen 3 Coder 480B\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"OpenHands\" -m \"Qwen 3 Coder 480B\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
diff --git a/data/models/alibaba_qwen3-235b-a22b-instruct-2507.json b/data/models/alibaba_qwen3-235b-a22b-instruct-2507.json
index 73411ab4fcdf3bfd9a55ece3006bf091682be221..18e9257ee4a295645c5d70b31ea729844e529c44 100644
--- a/data/models/alibaba_qwen3-235b-a22b-instruct-2507.json
+++ b/data/models/alibaba_qwen3-235b-a22b-instruct-2507.json
@@ -10,8 +10,8 @@
   },
   "evaluations": [
     {
-      "evaluation_id": "global-mmlu-lite/alibaba_qwen3-235b-a22b-instruct-2507/1773936583.743359",
-      "retrieved_timestamp": "1773936583.743359",
+      "evaluation_id": "global-mmlu-lite/alibaba_qwen3-235b-a22b-instruct-2507/1773936496.366405",
+      "retrieved_timestamp": "1773936496.366405",
       "source_metadata": {
         "source_name": "Global MMLU Lite Leaderboard",
         "source_type": "documentation",
@@ -525,8 +525,8 @@
       "generation_config": null
     },
     {
-      "evaluation_id": "global-mmlu-lite/alibaba_qwen3-235b-a22b-instruct-2507/1773936496.366405",
-      "retrieved_timestamp": "1773936496.366405",
+      "evaluation_id": "global-mmlu-lite/alibaba_qwen3-235b-a22b-instruct-2507/1773936583.743359",
+      "retrieved_timestamp": "1773936583.743359",
       "source_metadata": {
         "source_name": "Global MMLU Lite Leaderboard",
         "source_type": "documentation",
diff --git a/data/models/allenai_llama-3.1-8b-base-rm-rb2.json b/data/models/allenai_llama-3.1-8b-base-rm-rb2.json
index b77566d88bfa5b7f18f1a64562aee1f65b27a08c..8e81065be5c6f388ddbf031b25c6ea031d346e21 100644
--- a/data/models/allenai_llama-3.1-8b-base-rm-rb2.json
+++ b/data/models/allenai_llama-3.1-8b-base-rm-rb2.json
@@ -9,10 +9,10 @@
   },
   "evaluations": [
     {
-      "evaluation_id": "reward-bench/allenai_Llama-3.1-8B-Base-RM-RB2/1766412838.146816",
+      "evaluation_id": "reward-bench-2/allenai_Llama-3.1-8B-Base-RM-RB2/1766412838.146816",
       "retrieved_timestamp": "1766412838.146816",
       "source_metadata": {
-        "source_name": "RewardBench",
+        "source_name": "RewardBench 2",
         "source_type": "documentation",
         "source_organization_name": "Allen Institute for AI",
         "source_organization_url": "https://allenai.org",
@@ -31,109 +31,127 @@
         {
           "evaluation_name": "Score",
           "metric_config": {
-            "evaluation_description": "Overall RewardBench Score",
+            "evaluation_description": "Overall RewardBench 2 Score (mean of all metrics)",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.8463
+            "score": 0.649
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Chat",
+          "evaluation_name": "Factuality",
           "metric_config": {
-            "evaluation_description": "Chat accuracy - includes easy chat subsets",
+            "evaluation_description": "Factuality score - measures factual accuracy",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.933
+            "score": 0.72
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Chat Hard",
+          "evaluation_name": "Precise IF",
           "metric_config": {
-            "evaluation_description": "Chat Hard accuracy - includes hard chat subsets",
+            "evaluation_description": "Precise Instruction Following score",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7785
+            "score": 0.3625
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
+          }
+        },
+        {
+          "evaluation_name": "Math",
+          "metric_config": {
+            "evaluation_description": "Math score - measures mathematical reasoning",
+            "lower_is_better": false,
+            "score_type": "continuous",
+            "min_score": 0.0,
+            "max_score": 1.0
+          },
+          "score_details": {
+            "score": 0.612
+          },
+          "source_data": {
+            "dataset_name": "RewardBench 2",
+            "source_type": "hf_dataset",
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
           "evaluation_name": "Safety",
           "metric_config": {
-            "evaluation_description": "Safety accuracy - includes safety subsets",
+            "evaluation_description": "Safety score - measures safety awareness",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.8851
+            "score": 0.8267
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Reasoning",
+          "evaluation_name": "Focus",
           "metric_config": {
-            "evaluation_description": "Reasoning accuracy - includes code and math subsets",
+            "evaluation_description": "Focus score - measures response focus",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7886
+            "score": 0.8323
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Prior Sets (0.5 weight)",
+          "evaluation_name": "Ties",
           "metric_config": {
-            "evaluation_description": "Prior Sets score (weighted 0.5) - includes test sets",
+            "evaluation_description": "Ties score - ability to identify tie cases",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0
+            "score": 0.5406
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         }
       ],
@@ -141,10 +159,10 @@
       "generation_config": null
     },
     {
-      "evaluation_id": "reward-bench-2/allenai_Llama-3.1-8B-Base-RM-RB2/1766412838.146816",
+      "evaluation_id": "reward-bench/allenai_Llama-3.1-8B-Base-RM-RB2/1766412838.146816",
       "retrieved_timestamp": "1766412838.146816",
       "source_metadata": {
-        "source_name": "RewardBench 2",
+        "source_name": "RewardBench",
         "source_type": "documentation",
         "source_organization_name": "Allen Institute for AI",
         "source_organization_url": "https://allenai.org",
@@ -163,127 +181,109 @@
         {
           "evaluation_name": "Score",
           "metric_config": {
-            "evaluation_description": "Overall RewardBench 2 Score (mean of all metrics)",
-            "lower_is_better": false,
-            "score_type": "continuous",
-            "min_score": 0.0,
-            "max_score": 1.0
-          },
-          "score_details": {
-            "score": 0.649
-          },
-          "source_data": {
-            "dataset_name": "RewardBench 2",
-            "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
-          }
-        },
-        {
-          "evaluation_name": "Factuality",
-          "metric_config": {
-            "evaluation_description": "Factuality score - measures factual accuracy",
+            "evaluation_description": "Overall RewardBench Score",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.72
+            "score": 0.8463
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Precise IF",
+          "evaluation_name": "Chat",
           "metric_config": {
-            "evaluation_description": "Precise Instruction Following score",
+            "evaluation_description": "Chat accuracy - includes easy chat subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3625
+            "score": 0.933
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Math",
+          "evaluation_name": "Chat Hard",
           "metric_config": {
-            "evaluation_description": "Math score - measures mathematical reasoning",
+            "evaluation_description": "Chat Hard accuracy - includes hard chat subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.612
+            "score": 0.7785
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
           "evaluation_name": "Safety",
           "metric_config": {
-            "evaluation_description": "Safety score - measures safety awareness",
+            "evaluation_description": "Safety accuracy - includes safety subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.8267
+            "score": 0.8851
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Focus",
+          "evaluation_name": "Reasoning",
           "metric_config": {
-            "evaluation_description": "Focus score - measures response focus",
+            "evaluation_description": "Reasoning accuracy - includes code and math subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.8323
+            "score": 0.7886
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Ties",
+          "evaluation_name": "Prior Sets (0.5 weight)",
           "metric_config": {
-            "evaluation_description": "Ties score - ability to identify tie cases",
+            "evaluation_description": "Prior Sets score (weighted 0.5) - includes test sets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5406
+            "score": 0.0
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         }
       ],
diff --git a/data/models/allenai_llama-3.1-tulu-3-70b-sft-rm-rb2.json b/data/models/allenai_llama-3.1-tulu-3-70b-sft-rm-rb2.json
index 56c7eedcfadd2447274047e1824ef99e14cf4e28..3c470e6abd70f5f2bc9a8be57cc36f939ca7753c 100644
--- a/data/models/allenai_llama-3.1-tulu-3-70b-sft-rm-rb2.json
+++ b/data/models/allenai_llama-3.1-tulu-3-70b-sft-rm-rb2.json
@@ -9,10 +9,10 @@
   },
   "evaluations": [
     {
-      "evaluation_id": "reward-bench-2/allenai_Llama-3.1-Tulu-3-70B-SFT-RM-RB2/1766412838.146816",
+      "evaluation_id": "reward-bench/allenai_Llama-3.1-Tulu-3-70B-SFT-RM-RB2/1766412838.146816",
       "retrieved_timestamp": "1766412838.146816",
       "source_metadata": {
-        "source_name": "RewardBench 2",
+        "source_name": "RewardBench",
         "source_type": "documentation",
         "source_organization_name": "Allen Institute for AI",
         "source_organization_url": "https://allenai.org",
@@ -31,127 +31,109 @@
         {
           "evaluation_name": "Score",
           "metric_config": {
-            "evaluation_description": "Overall RewardBench 2 Score (mean of all metrics)",
-            "lower_is_better": false,
-            "score_type": "continuous",
-            "min_score": 0.0,
-            "max_score": 1.0
-          },
-          "score_details": {
-            "score": 0.722
-          },
-          "source_data": {
-            "dataset_name": "RewardBench 2",
-            "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
-          }
-        },
-        {
-          "evaluation_name": "Factuality",
-          "metric_config": {
-            "evaluation_description": "Factuality score - measures factual accuracy",
+            "evaluation_description": "Overall RewardBench Score",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.8084
+            "score": 0.8892
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Precise IF",
+          "evaluation_name": "Chat",
           "metric_config": {
-            "evaluation_description": "Precise Instruction Following score",
+            "evaluation_description": "Chat accuracy - includes easy chat subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3688
+            "score": 0.9693
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Math",
+          "evaluation_name": "Chat Hard",
           "metric_config": {
-            "evaluation_description": "Math score - measures mathematical reasoning",
+            "evaluation_description": "Chat Hard accuracy - includes hard chat subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6776
+            "score": 0.8268
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
           "evaluation_name": "Safety",
           "metric_config": {
-            "evaluation_description": "Safety score - measures safety awareness",
+            "evaluation_description": "Safety accuracy - includes safety subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.8689
+            "score": 0.9027
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Focus",
+          "evaluation_name": "Reasoning",
           "metric_config": {
-            "evaluation_description": "Focus score - measures response focus",
+            "evaluation_description": "Reasoning accuracy - includes code and math subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7778
+            "score": 0.8583
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Ties",
+          "evaluation_name": "Prior Sets (0.5 weight)",
           "metric_config": {
-            "evaluation_description": "Ties score - ability to identify tie cases",
+            "evaluation_description": "Prior Sets score (weighted 0.5) - includes test sets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.8308
+            "score": 0.0
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         }
       ],
@@ -159,10 +141,10 @@
       "generation_config": null
     },
     {
-      "evaluation_id": "reward-bench/allenai_Llama-3.1-Tulu-3-70B-SFT-RM-RB2/1766412838.146816",
+      "evaluation_id": "reward-bench-2/allenai_Llama-3.1-Tulu-3-70B-SFT-RM-RB2/1766412838.146816",
       "retrieved_timestamp": "1766412838.146816",
       "source_metadata": {
-        "source_name": "RewardBench",
+        "source_name": "RewardBench 2",
         "source_type": "documentation",
         "source_organization_name": "Allen Institute for AI",
         "source_organization_url": "https://allenai.org",
@@ -181,109 +163,127 @@
         {
           "evaluation_name": "Score",
           "metric_config": {
-            "evaluation_description": "Overall RewardBench Score",
+            "evaluation_description": "Overall RewardBench 2 Score (mean of all metrics)",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.8892
+            "score": 0.722
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Chat",
+          "evaluation_name": "Factuality",
           "metric_config": {
-            "evaluation_description": "Chat accuracy - includes easy chat subsets",
+            "evaluation_description": "Factuality score - measures factual accuracy",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9693
+            "score": 0.8084
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Chat Hard",
+          "evaluation_name": "Precise IF",
           "metric_config": {
-            "evaluation_description": "Chat Hard accuracy - includes hard chat subsets",
+            "evaluation_description": "Precise Instruction Following score",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.8268
+            "score": 0.3688
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
+          }
+        },
+        {
+          "evaluation_name": "Math",
+          "metric_config": {
+            "evaluation_description": "Math score - measures mathematical reasoning",
+            "lower_is_better": false,
+            "score_type": "continuous",
+            "min_score": 0.0,
+            "max_score": 1.0
+          },
+          "score_details": {
+            "score": 0.6776
+          },
+          "source_data": {
+            "dataset_name": "RewardBench 2",
+            "source_type": "hf_dataset",
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
           "evaluation_name": "Safety",
           "metric_config": {
-            "evaluation_description": "Safety accuracy - includes safety subsets",
+            "evaluation_description": "Safety score - measures safety awareness",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9027
+            "score": 0.8689
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Reasoning",
+          "evaluation_name": "Focus",
           "metric_config": {
-            "evaluation_description": "Reasoning accuracy - includes code and math subsets",
+            "evaluation_description": "Focus score - measures response focus",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.8583
+            "score": 0.7778
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Prior Sets (0.5 weight)",
+          "evaluation_name": "Ties",
           "metric_config": {
-            "evaluation_description": "Prior Sets score (weighted 0.5) - includes test sets",
+            "evaluation_description": "Ties score - ability to identify tie cases",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0
+            "score": 0.8308
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         }
       ],
diff --git a/data/models/allenai_llama-3.1-tulu-3-70b.json b/data/models/allenai_llama-3.1-tulu-3-70b.json
index dedd220cd13dda3e92225bd87465795dab977b4c..1db7ede127ee803b7ffd5960ed83ddaa8fe5c58c 100644
--- a/data/models/allenai_llama-3.1-tulu-3-70b.json
+++ b/data/models/allenai_llama-3.1-tulu-3-70b.json
@@ -5,7 +5,7 @@
     "developer": "allenai",
     "inference_platform": "unknown",
     "additional_details": {
-      "precision": "float16",
+      "precision": "bfloat16",
       "architecture": "LlamaForCausalLM",
       "params_billions": "70.554"
     }
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.8379
+            "score": 0.8291
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6157
+            "score": 0.6164
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3829
+            "score": 0.4502
           }
         },
         {
@@ -116,7 +116,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4988
+            "score": 0.4948
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4656
+            "score": 0.4645
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.8291
+            "score": 0.8379
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6164
+            "score": 0.6157
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4502
+            "score": 0.3829
           }
         },
         {
@@ -246,7 +246,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4948
+            "score": 0.4988
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4645
+            "score": 0.4656
           }
         }
       ],
diff --git a/data/models/allenai_llama-3.1-tulu-3-8b-dpo-rm-rb2.json b/data/models/allenai_llama-3.1-tulu-3-8b-dpo-rm-rb2.json
index 52eed39924ec31b815aba5be343333e3d61411ae..408cdcea425aaae910c976c1f57587d29fcf9c63 100644
--- a/data/models/allenai_llama-3.1-tulu-3-8b-dpo-rm-rb2.json
+++ b/data/models/allenai_llama-3.1-tulu-3-8b-dpo-rm-rb2.json
@@ -9,10 +9,10 @@
   },
   "evaluations": [
     {
-      "evaluation_id": "reward-bench-2/allenai_Llama-3.1-Tulu-3-8B-DPO-RM-RB2/1766412838.146816",
+      "evaluation_id": "reward-bench/allenai_Llama-3.1-Tulu-3-8B-DPO-RM-RB2/1766412838.146816",
       "retrieved_timestamp": "1766412838.146816",
       "source_metadata": {
-        "source_name": "RewardBench 2",
+        "source_name": "RewardBench",
         "source_type": "documentation",
         "source_organization_name": "Allen Institute for AI",
         "source_organization_url": "https://allenai.org",
@@ -31,127 +31,109 @@
         {
           "evaluation_name": "Score",
           "metric_config": {
-            "evaluation_description": "Overall RewardBench 2 Score (mean of all metrics)",
-            "lower_is_better": false,
-            "score_type": "continuous",
-            "min_score": 0.0,
-            "max_score": 1.0
-          },
-          "score_details": {
-            "score": 0.687
-          },
-          "source_data": {
-            "dataset_name": "RewardBench 2",
-            "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
-          }
-        },
-        {
-          "evaluation_name": "Factuality",
-          "metric_config": {
-            "evaluation_description": "Factuality score - measures factual accuracy",
+            "evaluation_description": "Overall RewardBench Score",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7516
+            "score": 0.8431
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Precise IF",
+          "evaluation_name": "Chat",
           "metric_config": {
-            "evaluation_description": "Precise Instruction Following score",
+            "evaluation_description": "Chat accuracy - includes easy chat subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3875
+            "score": 0.9553
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Math",
+          "evaluation_name": "Chat Hard",
           "metric_config": {
-            "evaluation_description": "Math score - measures mathematical reasoning",
+            "evaluation_description": "Chat Hard accuracy - includes hard chat subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6284
+            "score": 0.761
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
           "evaluation_name": "Safety",
           "metric_config": {
-            "evaluation_description": "Safety score - measures safety awareness",
+            "evaluation_description": "Safety accuracy - includes safety subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.86
+            "score": 0.8662
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Focus",
+          "evaluation_name": "Reasoning",
           "metric_config": {
-            "evaluation_description": "Focus score - measures response focus",
+            "evaluation_description": "Reasoning accuracy - includes code and math subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.8545
+            "score": 0.7898
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Ties",
+          "evaluation_name": "Prior Sets (0.5 weight)",
           "metric_config": {
-            "evaluation_description": "Ties score - ability to identify tie cases",
+            "evaluation_description": "Prior Sets score (weighted 0.5) - includes test sets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6397
+            "score": 0.0
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         }
       ],
@@ -159,10 +141,10 @@
       "generation_config": null
     },
     {
-      "evaluation_id": "reward-bench/allenai_Llama-3.1-Tulu-3-8B-DPO-RM-RB2/1766412838.146816",
+      "evaluation_id": "reward-bench-2/allenai_Llama-3.1-Tulu-3-8B-DPO-RM-RB2/1766412838.146816",
       "retrieved_timestamp": "1766412838.146816",
       "source_metadata": {
-        "source_name": "RewardBench",
+        "source_name": "RewardBench 2",
         "source_type": "documentation",
         "source_organization_name": "Allen Institute for AI",
         "source_organization_url": "https://allenai.org",
@@ -181,109 +163,127 @@
         {
           "evaluation_name": "Score",
           "metric_config": {
-            "evaluation_description": "Overall RewardBench Score",
+            "evaluation_description": "Overall RewardBench 2 Score (mean of all metrics)",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.8431
+            "score": 0.687
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Chat",
+          "evaluation_name": "Factuality",
           "metric_config": {
-            "evaluation_description": "Chat accuracy - includes easy chat subsets",
+            "evaluation_description": "Factuality score - measures factual accuracy",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9553
+            "score": 0.7516
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Chat Hard",
+          "evaluation_name": "Precise IF",
           "metric_config": {
-            "evaluation_description": "Chat Hard accuracy - includes hard chat subsets",
+            "evaluation_description": "Precise Instruction Following score",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.761
+            "score": 0.3875
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
+          }
+        },
+        {
+          "evaluation_name": "Math",
+          "metric_config": {
+            "evaluation_description": "Math score - measures mathematical reasoning",
+            "lower_is_better": false,
+            "score_type": "continuous",
+            "min_score": 0.0,
+            "max_score": 1.0
+          },
+          "score_details": {
+            "score": 0.6284
+          },
+          "source_data": {
+            "dataset_name": "RewardBench 2",
+            "source_type": "hf_dataset",
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
           "evaluation_name": "Safety",
           "metric_config": {
-            "evaluation_description": "Safety accuracy - includes safety subsets",
+            "evaluation_description": "Safety score - measures safety awareness",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.8662
+            "score": 0.86
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Reasoning",
+          "evaluation_name": "Focus",
           "metric_config": {
-            "evaluation_description": "Reasoning accuracy - includes code and math subsets",
+            "evaluation_description": "Focus score - measures response focus",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7898
+            "score": 0.8545
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Prior Sets (0.5 weight)",
+          "evaluation_name": "Ties",
           "metric_config": {
-            "evaluation_description": "Prior Sets score (weighted 0.5) - includes test sets",
+            "evaluation_description": "Ties score - ability to identify tie cases",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0
+            "score": 0.6397
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         }
       ],
diff --git a/data/models/allenai_llama-3.1-tulu-3-8b.json b/data/models/allenai_llama-3.1-tulu-3-8b.json
index 53350f20b1f74556a0af6a9aa87ed77d181deaec..7de1c9431728784c04f1c32781631febc2ed7e32 100644
--- a/data/models/allenai_llama-3.1-tulu-3-8b.json
+++ b/data/models/allenai_llama-3.1-tulu-3-8b.json
@@ -5,7 +5,7 @@
     "developer": "allenai",
     "inference_platform": "unknown",
     "additional_details": {
-      "precision": "float16",
+      "precision": "bfloat16",
       "architecture": "LlamaForCausalLM",
       "params_billions": "8.03"
     }
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.8255
+            "score": 0.8267
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4061
+            "score": 0.405
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2115
+            "score": 0.1964
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.297
+            "score": 0.2987
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2821
+            "score": 0.2827
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.8267
+            "score": 0.8255
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.405
+            "score": 0.4061
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1964
+            "score": 0.2115
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2987
+            "score": 0.297
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2827
+            "score": 0.2821
           }
         }
       ],
diff --git a/data/models/allenai_open_instruct_dev-rm_1e-6_2_30pctflipped__1__1743325094.json b/data/models/allenai_open_instruct_dev-rm_1e-6_2_30pctflipped__1__1743325094.json
deleted file mode 100644
index cedfd398cf32e477ed09f75303d207e32a02614e..0000000000000000000000000000000000000000
--- a/data/models/allenai_open_instruct_dev-rm_1e-6_2_30pctflipped__1__1743325094.json
+++ /dev/null
@@ -1,162 +0,0 @@
-{
-  "model_info": {
-    "name": "allenai/open_instruct_dev-rm_1e-6_2_30pctflipped__1__1743325094",
-    "id": "allenai/open_instruct_dev-rm_1e-6_2_30pctflipped__1__1743325094",
-    "developer": "allenai",
-    "additional_details": {
-      "model_type": "Seq. Classifier"
-    }
-  },
-  "evaluations": [
-    {
-      "evaluation_id": "reward-bench-2/allenai_open_instruct_dev-rm_1e-6_2_30pctflipped__1__1743325094/1766412838.146816",
-      "retrieved_timestamp": "1766412838.146816",
-      "source_metadata": {
-        "source_name": "RewardBench 2",
-        "source_type": "documentation",
-        "source_organization_name": "Allen Institute for AI",
-        "source_organization_url": "https://allenai.org",
-        "evaluator_relationship": "third_party"
-      },
-      "eval_library": {
-        "name": "rewardbench",
-        "version": "0.1.3",
-        "additional_details": {
-          "subsets": "Chat, Chat Hard, Safety, Reasoning",
-          "hf_space": "allenai/reward-bench"
-        }
-      },
-      "benchmark": "reward-bench",
-      "evaluation_results": [
-        {
-          "evaluation_name": "Score",
-          "metric_config": {
-            "evaluation_description": "Overall RewardBench 2 Score (mean of all metrics)",
-            "lower_is_better": false,
-            "score_type": "continuous",
-            "min_score": 0.0,
-            "max_score": 1.0
-          },
-          "score_details": {
-            "score": 0.5151
-          },
-          "source_data": {
-            "dataset_name": "RewardBench 2",
-            "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
-          }
-        },
-        {
-          "evaluation_name": "Factuality",
-          "metric_config": {
-            "evaluation_description": "Factuality score - measures factual accuracy",
-            "lower_is_better": false,
-            "score_type": "continuous",
-            "min_score": 0.0,
-            "max_score": 1.0
-          },
-          "score_details": {
-            "score": 0.6484
-          },
-          "source_data": {
-            "dataset_name": "RewardBench 2",
-            "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
-          }
-        },
-        {
-          "evaluation_name": "Precise IF",
-          "metric_config": {
-            "evaluation_description": "Precise Instruction Following score",
-            "lower_is_better": false,
-            "score_type": "continuous",
-            "min_score": 0.0,
-            "max_score": 1.0
-          },
-          "score_details": {
-            "score": 0.3312
-          },
-          "source_data": {
-            "dataset_name": "RewardBench 2",
-            "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
-          }
-        },
-        {
-          "evaluation_name": "Math",
-          "metric_config": {
-            "evaluation_description": "Math score - measures mathematical reasoning",
-            "lower_is_better": false,
-            "score_type": "continuous",
-            "min_score": 0.0,
-            "max_score": 1.0
-          },
-          "score_details": {
-            "score": 0.5574
-          },
-          "source_data": {
-            "dataset_name": "RewardBench 2",
-            "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
-          }
-        },
-        {
-          "evaluation_name": "Safety",
-          "metric_config": {
-            "evaluation_description": "Safety score - measures safety awareness",
-            "lower_is_better": false,
-            "score_type": "continuous",
-            "min_score": 0.0,
-            "max_score": 1.0
-          },
-          "score_details": {
-            "score": 0.7289
-          },
-          "source_data": {
-            "dataset_name": "RewardBench 2",
-            "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
-          }
-        },
-        {
-          "evaluation_name": "Focus",
-          "metric_config": {
-            "evaluation_description": "Focus score - measures response focus",
-            "lower_is_better": false,
-            "score_type": "continuous",
-            "min_score": 0.0,
-            "max_score": 1.0
-          },
-          "score_details": {
-            "score": 0.4889
-          },
-          "source_data": {
-            "dataset_name": "RewardBench 2",
-            "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
-          }
-        },
-        {
-          "evaluation_name": "Ties",
-          "metric_config": {
-            "evaluation_description": "Ties score - ability to identify tie cases",
-            "lower_is_better": false,
-            "score_type": "continuous",
-            "min_score": 0.0,
-            "max_score": 1.0
-          },
-          "score_details": {
-            "score": 0.3357
-          },
-          "source_data": {
-            "dataset_name": "RewardBench 2",
-            "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
-          }
-        }
-      ],
-      "detailed_evaluation_results": null,
-      "generation_config": null
-    }
-  ]
-}
\ No newline at end of file
diff --git a/data/models/anthropic_claude-3-5-haiku-20241022.json b/data/models/anthropic_claude-3-5-haiku-20241022.json
index 97ab32cadbb5e110dfa409cbea1ee9b8c38d6850..9edb0c7484cd3b1eab61fa90716227281f955253 100644
--- a/data/models/anthropic_claude-3-5-haiku-20241022.json
+++ b/data/models/anthropic_claude-3-5-haiku-20241022.json
@@ -10,8 +10,8 @@
   },
   "evaluations": [
     {
-      "evaluation_id": "global-mmlu-lite/anthropic_claude-3-5-haiku-20241022/1773936496.366405",
-      "retrieved_timestamp": "1773936496.366405",
+      "evaluation_id": "global-mmlu-lite/anthropic_claude-3-5-haiku-20241022/1773936583.743359",
+      "retrieved_timestamp": "1773936583.743359",
       "source_metadata": {
         "source_name": "Global MMLU Lite Leaderboard",
         "source_type": "documentation",
@@ -525,8 +525,8 @@
       "generation_config": null
     },
     {
-      "evaluation_id": "global-mmlu-lite/anthropic_claude-3-5-haiku-20241022/1773936583.743359",
-      "retrieved_timestamp": "1773936583.743359",
+      "evaluation_id": "global-mmlu-lite/anthropic_claude-3-5-haiku-20241022/1773936496.366405",
+      "retrieved_timestamp": "1773936496.366405",
       "source_metadata": {
         "source_name": "Global MMLU Lite Leaderboard",
         "source_type": "documentation",
diff --git a/data/models/anthropic_claude-3-7-sonnet-20250219.json b/data/models/anthropic_claude-3-7-sonnet-20250219.json
index 6e02a0c482b2aed6381eb4f121bd334b0959f1b6..26744b8fcce13c56de7ede1b941e4f633dfc781a 100644
--- a/data/models/anthropic_claude-3-7-sonnet-20250219.json
+++ b/data/models/anthropic_claude-3-7-sonnet-20250219.json
@@ -10,8 +10,8 @@
   },
   "evaluations": [
     {
-      "evaluation_id": "global-mmlu-lite/anthropic_claude-3-7-sonnet-20250219/1773936496.366405",
-      "retrieved_timestamp": "1773936496.366405",
+      "evaluation_id": "global-mmlu-lite/anthropic_claude-3-7-sonnet-20250219/1773936583.743359",
+      "retrieved_timestamp": "1773936583.743359",
       "source_metadata": {
         "source_name": "Global MMLU Lite Leaderboard",
         "source_type": "documentation",
@@ -525,8 +525,8 @@
       "generation_config": null
     },
     {
-      "evaluation_id": "global-mmlu-lite/anthropic_claude-3-7-sonnet-20250219/1773936583.743359",
-      "retrieved_timestamp": "1773936583.743359",
+      "evaluation_id": "global-mmlu-lite/anthropic_claude-3-7-sonnet-20250219/1773936496.366405",
+      "retrieved_timestamp": "1773936496.366405",
       "source_metadata": {
         "source_name": "Global MMLU Lite Leaderboard",
         "source_type": "documentation",
diff --git a/data/models/anthropic_claude-3-haiku-20240307.json b/data/models/anthropic_claude-3-haiku-20240307.json
index 52bb9959dd5613be4f3fe143bd6f01f97e2632c2..4a2b563f634d87e24d77a5003bd4befff9181e63 100644
--- a/data/models/anthropic_claude-3-haiku-20240307.json
+++ b/data/models/anthropic_claude-3-haiku-20240307.json
@@ -1903,10 +1903,10 @@
       }
     },
     {
-      "evaluation_id": "reward-bench/Anthropic_claude-3-haiku-20240307/1766412838.146816",
+      "evaluation_id": "reward-bench-2/anthropic_claude-3-haiku-20240307/1766412838.146816",
       "retrieved_timestamp": "1766412838.146816",
       "source_metadata": {
-        "source_name": "RewardBench",
+        "source_name": "RewardBench 2",
         "source_type": "documentation",
         "source_organization_name": "Allen Institute for AI",
         "source_organization_url": "https://allenai.org",
@@ -1925,109 +1925,127 @@
         {
           "evaluation_name": "Score",
           "metric_config": {
-            "evaluation_description": "Overall RewardBench Score",
+            "evaluation_description": "Overall RewardBench 2 Score (mean of all metrics)",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7289
+            "score": 0.3711
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Chat",
+          "evaluation_name": "Factuality",
           "metric_config": {
-            "evaluation_description": "Chat accuracy - includes easy chat subsets",
+            "evaluation_description": "Factuality score - measures factual accuracy",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9274
+            "score": 0.4042
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Chat Hard",
+          "evaluation_name": "Precise IF",
           "metric_config": {
-            "evaluation_description": "Chat Hard accuracy - includes hard chat subsets",
+            "evaluation_description": "Precise Instruction Following score",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5197
+            "score": 0.2812
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
+          }
+        },
+        {
+          "evaluation_name": "Math",
+          "metric_config": {
+            "evaluation_description": "Math score - measures mathematical reasoning",
+            "lower_is_better": false,
+            "score_type": "continuous",
+            "min_score": 0.0,
+            "max_score": 1.0
+          },
+          "score_details": {
+            "score": 0.3552
+          },
+          "source_data": {
+            "dataset_name": "RewardBench 2",
+            "source_type": "hf_dataset",
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
           "evaluation_name": "Safety",
           "metric_config": {
-            "evaluation_description": "Safety accuracy - includes safety subsets",
+            "evaluation_description": "Safety score - measures safety awareness",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7953
+            "score": 0.595
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Reasoning",
+          "evaluation_name": "Focus",
           "metric_config": {
-            "evaluation_description": "Reasoning accuracy - includes code and math subsets",
+            "evaluation_description": "Focus score - measures response focus",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.706
+            "score": 0.501
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Prior Sets (0.5 weight)",
+          "evaluation_name": "Ties",
           "metric_config": {
-            "evaluation_description": "Prior Sets score (weighted 0.5) - includes test sets",
+            "evaluation_description": "Ties score - ability to identify tie cases",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6635
+            "score": 0.0899
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         }
       ],
@@ -2035,10 +2053,10 @@
       "generation_config": null
     },
     {
-      "evaluation_id": "reward-bench-2/anthropic_claude-3-haiku-20240307/1766412838.146816",
+      "evaluation_id": "reward-bench/Anthropic_claude-3-haiku-20240307/1766412838.146816",
       "retrieved_timestamp": "1766412838.146816",
       "source_metadata": {
-        "source_name": "RewardBench 2",
+        "source_name": "RewardBench",
         "source_type": "documentation",
         "source_organization_name": "Allen Institute for AI",
         "source_organization_url": "https://allenai.org",
@@ -2057,127 +2075,109 @@
         {
           "evaluation_name": "Score",
           "metric_config": {
-            "evaluation_description": "Overall RewardBench 2 Score (mean of all metrics)",
-            "lower_is_better": false,
-            "score_type": "continuous",
-            "min_score": 0.0,
-            "max_score": 1.0
-          },
-          "score_details": {
-            "score": 0.3711
-          },
-          "source_data": {
-            "dataset_name": "RewardBench 2",
-            "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
-          }
-        },
-        {
-          "evaluation_name": "Factuality",
-          "metric_config": {
-            "evaluation_description": "Factuality score - measures factual accuracy",
+            "evaluation_description": "Overall RewardBench Score",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4042
+            "score": 0.7289
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Precise IF",
+          "evaluation_name": "Chat",
           "metric_config": {
-            "evaluation_description": "Precise Instruction Following score",
+            "evaluation_description": "Chat accuracy - includes easy chat subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2812
+            "score": 0.9274
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Math",
+          "evaluation_name": "Chat Hard",
           "metric_config": {
-            "evaluation_description": "Math score - measures mathematical reasoning",
+            "evaluation_description": "Chat Hard accuracy - includes hard chat subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3552
+            "score": 0.5197
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
           "evaluation_name": "Safety",
           "metric_config": {
-            "evaluation_description": "Safety score - measures safety awareness",
+            "evaluation_description": "Safety accuracy - includes safety subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.595
+            "score": 0.7953
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Focus",
+          "evaluation_name": "Reasoning",
           "metric_config": {
-            "evaluation_description": "Focus score - measures response focus",
+            "evaluation_description": "Reasoning accuracy - includes code and math subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.501
+            "score": 0.706
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Ties",
+          "evaluation_name": "Prior Sets (0.5 weight)",
           "metric_config": {
-            "evaluation_description": "Ties score - ability to identify tie cases",
+            "evaluation_description": "Prior Sets score (weighted 0.5) - includes test sets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0899
+            "score": 0.6635
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         }
       ],
diff --git a/data/models/anthropic_claude-3-opus-20240229.json b/data/models/anthropic_claude-3-opus-20240229.json
index 8f8b70dd804fcbb225ceb8111209d93e20e8bd0b..150503f1a5f91571d10a33f8965d4bd84f3ccf46 100644
--- a/data/models/anthropic_claude-3-opus-20240229.json
+++ b/data/models/anthropic_claude-3-opus-20240229.json
@@ -1903,10 +1903,10 @@
       }
     },
     {
-      "evaluation_id": "reward-bench/Anthropic_claude-3-opus-20240229/1766412838.146816",
+      "evaluation_id": "reward-bench-2/anthropic_claude-3-opus-20240229/1766412838.146816",
       "retrieved_timestamp": "1766412838.146816",
       "source_metadata": {
-        "source_name": "RewardBench",
+        "source_name": "RewardBench 2",
         "source_type": "documentation",
         "source_organization_name": "Allen Institute for AI",
         "source_organization_url": "https://allenai.org",
@@ -1925,128 +1925,104 @@
         {
           "evaluation_name": "Score",
           "metric_config": {
-            "evaluation_description": "Overall RewardBench Score",
+            "evaluation_description": "Overall RewardBench 2 Score (mean of all metrics)",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.8008
+            "score": 0.5744
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Chat",
+          "evaluation_name": "Factuality",
           "metric_config": {
-            "evaluation_description": "Chat accuracy - includes easy chat subsets",
+            "evaluation_description": "Factuality score - measures factual accuracy",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9469
+            "score": 0.5389
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Chat Hard",
+          "evaluation_name": "Precise IF",
           "metric_config": {
-            "evaluation_description": "Chat Hard accuracy - includes hard chat subsets",
+            "evaluation_description": "Precise Instruction Following score",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6031
+            "score": 0.3312
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Safety",
+          "evaluation_name": "Math",
           "metric_config": {
-            "evaluation_description": "Safety accuracy - includes safety subsets",
+            "evaluation_description": "Math score - measures mathematical reasoning",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.8662
+            "score": 0.5137
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Reasoning",
+          "evaluation_name": "Safety",
           "metric_config": {
-            "evaluation_description": "Reasoning accuracy - includes code and math subsets",
+            "evaluation_description": "Safety score - measures safety awareness",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7868
+            "score": 0.8378
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
-        }
-      ],
-      "detailed_evaluation_results": null,
-      "generation_config": null
-    },
-    {
-      "evaluation_id": "reward-bench-2/anthropic_claude-3-opus-20240229/1766412838.146816",
-      "retrieved_timestamp": "1766412838.146816",
-      "source_metadata": {
-        "source_name": "RewardBench 2",
-        "source_type": "documentation",
-        "source_organization_name": "Allen Institute for AI",
-        "source_organization_url": "https://allenai.org",
-        "evaluator_relationship": "third_party"
-      },
-      "eval_library": {
-        "name": "rewardbench",
-        "version": "0.1.3",
-        "additional_details": {
-          "subsets": "Chat, Chat Hard, Safety, Reasoning",
-          "hf_space": "allenai/reward-bench"
-        }
-      },
-      "benchmark": "reward-bench",
-      "evaluation_results": [
+        },
         {
-          "evaluation_name": "Score",
+          "evaluation_name": "Focus",
           "metric_config": {
-            "evaluation_description": "Overall RewardBench 2 Score (mean of all metrics)",
+            "evaluation_description": "Focus score - measures response focus",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5744
+            "score": 0.6646
           },
           "source_data": {
             "dataset_name": "RewardBench 2",
@@ -2055,111 +2031,135 @@
           }
         },
         {
-          "evaluation_name": "Factuality",
+          "evaluation_name": "Ties",
           "metric_config": {
-            "evaluation_description": "Factuality score - measures factual accuracy",
+            "evaluation_description": "Ties score - ability to identify tie cases",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5389
+            "score": 0.5601
           },
           "source_data": {
             "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
             "hf_repo": "allenai/reward-bench-2-results"
           }
-        },
+        }
+      ],
+      "detailed_evaluation_results": null,
+      "generation_config": null
+    },
+    {
+      "evaluation_id": "reward-bench/Anthropic_claude-3-opus-20240229/1766412838.146816",
+      "retrieved_timestamp": "1766412838.146816",
+      "source_metadata": {
+        "source_name": "RewardBench",
+        "source_type": "documentation",
+        "source_organization_name": "Allen Institute for AI",
+        "source_organization_url": "https://allenai.org",
+        "evaluator_relationship": "third_party"
+      },
+      "eval_library": {
+        "name": "rewardbench",
+        "version": "0.1.3",
+        "additional_details": {
+          "subsets": "Chat, Chat Hard, Safety, Reasoning",
+          "hf_space": "allenai/reward-bench"
+        }
+      },
+      "benchmark": "reward-bench",
+      "evaluation_results": [
         {
-          "evaluation_name": "Precise IF",
+          "evaluation_name": "Score",
           "metric_config": {
-            "evaluation_description": "Precise Instruction Following score",
+            "evaluation_description": "Overall RewardBench Score",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3312
+            "score": 0.8008
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Math",
+          "evaluation_name": "Chat",
           "metric_config": {
-            "evaluation_description": "Math score - measures mathematical reasoning",
+            "evaluation_description": "Chat accuracy - includes easy chat subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5137
+            "score": 0.9469
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Safety",
+          "evaluation_name": "Chat Hard",
           "metric_config": {
-            "evaluation_description": "Safety score - measures safety awareness",
+            "evaluation_description": "Chat Hard accuracy - includes hard chat subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.8378
+            "score": 0.6031
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Focus",
+          "evaluation_name": "Safety",
           "metric_config": {
-            "evaluation_description": "Focus score - measures response focus",
+            "evaluation_description": "Safety accuracy - includes safety subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6646
+            "score": 0.8662
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Ties",
+          "evaluation_name": "Reasoning",
           "metric_config": {
-            "evaluation_description": "Ties score - ability to identify tie cases",
+            "evaluation_description": "Reasoning accuracy - includes code and math subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5601
+            "score": 0.7868
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         }
       ],
diff --git a/data/models/anthropic_claude-haiku-4.5.json b/data/models/anthropic_claude-haiku-4.5.json
index a51d1ecfb03be58e1a56ba7e5711a9bf62822a49..a44b80f840579ff8c5f06292af8a76c394e19084 100644
--- a/data/models/anthropic_claude-haiku-4.5.json
+++ b/data/models/anthropic_claude-haiku-4.5.json
@@ -84,7 +84,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/terminus-2__claude-haiku-4.5/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/goose__claude-haiku-4.5/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -108,7 +108,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-10-31",
+          "evaluation_timestamp": "2025-12-11",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -117,7 +117,7 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 28.3,
+            "score": 35.5,
             "uncertainty": {
               "standard_error": {
                 "value": 2.9
@@ -127,7 +127,7 @@
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"Claude Haiku 4.5\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Goose\" -m \"Claude Haiku 4.5\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -144,7 +144,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"Claude Haiku 4.5\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Goose\" -m \"Claude Haiku 4.5\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -158,7 +158,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/claude-code__claude-haiku-4.5/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/openhands__claude-haiku-4.5/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -182,7 +182,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-11-04",
+          "evaluation_timestamp": "2025-11-02",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -191,17 +191,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 27.5,
+            "score": 13.9,
             "uncertainty": {
               "standard_error": {
-                "value": 2.8
+                "value": 2.7
               },
               "num_samples": 435
             }
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Claude Code\" -m \"Claude Haiku 4.5\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"OpenHands\" -m \"Claude Haiku 4.5\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -218,7 +218,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Claude Code\" -m \"Claude Haiku 4.5\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"OpenHands\" -m \"Claude Haiku 4.5\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -232,7 +232,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/goose__claude-haiku-4.5/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/terminus-2__claude-haiku-4.5/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -256,7 +256,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-12-11",
+          "evaluation_timestamp": "2025-10-31",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -265,7 +265,7 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 35.5,
+            "score": 28.3,
             "uncertainty": {
               "standard_error": {
                 "value": 2.9
@@ -275,7 +275,7 @@
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Goose\" -m \"Claude Haiku 4.5\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"Claude Haiku 4.5\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -292,7 +292,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Goose\" -m \"Claude Haiku 4.5\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"Claude Haiku 4.5\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -306,7 +306,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/openhands__claude-haiku-4.5/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/claude-code__claude-haiku-4.5/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -330,7 +330,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-11-02",
+          "evaluation_timestamp": "2025-11-04",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -339,17 +339,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 13.9,
+            "score": 27.5,
             "uncertainty": {
               "standard_error": {
-                "value": 2.7
+                "value": 2.8
               },
               "num_samples": 435
             }
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"OpenHands\" -m \"Claude Haiku 4.5\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Claude Code\" -m \"Claude Haiku 4.5\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -366,7 +366,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"OpenHands\" -m \"Claude Haiku 4.5\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Claude Code\" -m \"Claude Haiku 4.5\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
diff --git a/data/models/anthropic_claude-opus-4-5.json b/data/models/anthropic_claude-opus-4-5.json
index 1de3c90261aa34fd7e316493f0ec72792c7a6a7a..e58ae243e6675ffbe5718b2cd53dbb80e8f1ba8b 100644
--- a/data/models/anthropic_claude-opus-4-5.json
+++ b/data/models/anthropic_claude-opus-4-5.json
@@ -78,7 +78,7 @@
       }
     },
     {
-      "evaluation_id": "browsecompplus/openai-solo__anthropic_claude-opus-4-5/1774263615.0201504",
+      "evaluation_id": "appworld/test_normal/claude-code-cli__anthropic_claude-opus-4-5/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -91,42 +91,42 @@
         "name": "exgentic",
         "version": "0.1.0"
       },
-      "benchmark": "browsecompplus",
+      "benchmark": "appworld_test_normal",
       "evaluation_results": [
         {
-          "evaluation_name": "browsecompplus",
+          "evaluation_name": "appworld/test_normal",
           "source_data": {
-            "dataset_name": "browsecompplus",
+            "dataset_name": "appworld/test_normal",
             "source_type": "url",
             "url": [
               "https://github.com/Exgentic/exgentic"
             ]
           },
           "metric_config": {
-            "evaluation_description": "BrowseCompPlus benchmark evaluation",
+            "evaluation_description": "AppWorld benchmark evaluation (test_normal subset)",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.61,
+            "score": 0.66,
             "uncertainty": {
               "num_samples": 100
             },
             "details": {
-              "average_agent_cost": "7.59",
-              "total_run_cost": "759.44",
-              "average_steps": "27.18",
-              "percent_finished": "1.0"
+              "average_agent_cost": "13.08",
+              "total_run_cost": "1308.38",
+              "average_steps": "49.69",
+              "percent_finished": "0.74"
             }
           },
           "generation_config": {
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "OpenAI Solo",
-                  "agent_framework": "openai_solo"
+                  "agent_name": "Claude Code CLI",
+                  "agent_framework": "claude_code"
                 }
               }
             }
@@ -138,15 +138,15 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "OpenAI Solo",
-              "agent_framework": "openai_solo"
+              "agent_name": "Claude Code CLI",
+              "agent_framework": "claude_code"
             }
           }
         }
       }
     },
     {
-      "evaluation_id": "browsecompplus/litellm-tool-calling__anthropic_claude-opus-4-5/1774263615.0201504",
+      "evaluation_id": "appworld/test_normal/litellm-tool-calling__anthropic_claude-opus-4-5/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -159,34 +159,34 @@
         "name": "exgentic",
         "version": "0.1.0"
       },
-      "benchmark": "browsecompplus",
+      "benchmark": "appworld_test_normal",
       "evaluation_results": [
         {
-          "evaluation_name": "browsecompplus",
+          "evaluation_name": "appworld/test_normal",
           "source_data": {
-            "dataset_name": "browsecompplus",
+            "dataset_name": "appworld/test_normal",
             "source_type": "url",
             "url": [
               "https://github.com/Exgentic/exgentic"
             ]
           },
           "metric_config": {
-            "evaluation_description": "BrowseCompPlus benchmark evaluation",
+            "evaluation_description": "AppWorld benchmark evaluation (test_normal subset)",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.49,
+            "score": 0.61,
             "uncertainty": {
               "num_samples": 100
             },
             "details": {
-              "average_agent_cost": "7.09",
-              "total_run_cost": "709.54",
-              "average_steps": "21.66",
-              "percent_finished": "0.93"
+              "average_agent_cost": "11.32",
+              "total_run_cost": "1132.47",
+              "average_steps": "21.99",
+              "percent_finished": "0.83"
             }
           },
           "generation_config": {
@@ -214,7 +214,7 @@
       }
     },
     {
-      "evaluation_id": "appworld/test_normal/litellm-tool-calling__anthropic_claude-opus-4-5/1774263615.0201504",
+      "evaluation_id": "browsecompplus/smolagents-code__anthropic_claude-opus-4-5/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -227,19 +227,19 @@
         "name": "exgentic",
         "version": "0.1.0"
       },
-      "benchmark": "appworld_test_normal",
+      "benchmark": "browsecompplus",
       "evaluation_results": [
         {
-          "evaluation_name": "appworld/test_normal",
+          "evaluation_name": "browsecompplus",
           "source_data": {
-            "dataset_name": "appworld/test_normal",
+            "dataset_name": "browsecompplus",
             "source_type": "url",
             "url": [
               "https://github.com/Exgentic/exgentic"
             ]
           },
           "metric_config": {
-            "evaluation_description": "AppWorld benchmark evaluation (test_normal subset)",
+            "evaluation_description": "BrowseCompPlus benchmark evaluation",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
@@ -251,18 +251,18 @@
               "num_samples": 100
             },
             "details": {
-              "average_agent_cost": "11.32",
-              "total_run_cost": "1132.47",
-              "average_steps": "21.99",
-              "percent_finished": "0.83"
+              "average_agent_cost": "6.3",
+              "total_run_cost": "630.56",
+              "average_steps": "24.16",
+              "percent_finished": "1.0"
             }
           },
           "generation_config": {
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "LiteLLM Tool Calling",
-                  "agent_framework": "tool_calling"
+                  "agent_name": "SmolAgents Code",
+                  "agent_framework": "smolagents_code"
                 }
               }
             }
@@ -274,15 +274,15 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "LiteLLM Tool Calling",
-              "agent_framework": "tool_calling"
+              "agent_name": "SmolAgents Code",
+              "agent_framework": "smolagents_code"
             }
           }
         }
       }
     },
     {
-      "evaluation_id": "appworld/test_normal/claude-code-cli__anthropic_claude-opus-4-5/1774263615.0201504",
+      "evaluation_id": "appworld/test_normal/smolagents-code__anthropic_claude-opus-4-5/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -314,23 +314,23 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.66,
+            "score": 0.7,
             "uncertainty": {
               "num_samples": 100
             },
             "details": {
-              "average_agent_cost": "13.08",
-              "total_run_cost": "1308.38",
-              "average_steps": "49.69",
-              "percent_finished": "0.74"
+              "average_agent_cost": "5.59",
+              "total_run_cost": "558.51",
+              "average_steps": "41.07",
+              "percent_finished": "0.82"
             }
           },
           "generation_config": {
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "Claude Code CLI",
-                  "agent_framework": "claude_code"
+                  "agent_name": "SmolAgents Code",
+                  "agent_framework": "smolagents_code"
                 }
               }
             }
@@ -342,8 +342,8 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "Claude Code CLI",
-              "agent_framework": "claude_code"
+              "agent_name": "SmolAgents Code",
+              "agent_framework": "smolagents_code"
             }
           }
         }
@@ -486,7 +486,7 @@
       }
     },
     {
-      "evaluation_id": "appworld/test_normal/smolagents-code__anthropic_claude-opus-4-5/1774263615.0201504",
+      "evaluation_id": "browsecompplus/litellm-tool-calling__anthropic_claude-opus-4-5/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -499,42 +499,42 @@
         "name": "exgentic",
         "version": "0.1.0"
       },
-      "benchmark": "appworld_test_normal",
+      "benchmark": "browsecompplus",
       "evaluation_results": [
         {
-          "evaluation_name": "appworld/test_normal",
+          "evaluation_name": "browsecompplus",
           "source_data": {
-            "dataset_name": "appworld/test_normal",
+            "dataset_name": "browsecompplus",
             "source_type": "url",
             "url": [
               "https://github.com/Exgentic/exgentic"
             ]
           },
           "metric_config": {
-            "evaluation_description": "AppWorld benchmark evaluation (test_normal subset)",
+            "evaluation_description": "BrowseCompPlus benchmark evaluation",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7,
+            "score": 0.49,
             "uncertainty": {
               "num_samples": 100
             },
             "details": {
-              "average_agent_cost": "5.59",
-              "total_run_cost": "558.51",
-              "average_steps": "41.07",
-              "percent_finished": "0.82"
+              "average_agent_cost": "7.09",
+              "total_run_cost": "709.54",
+              "average_steps": "21.66",
+              "percent_finished": "0.93"
             }
           },
           "generation_config": {
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "SmolAgents Code",
-                  "agent_framework": "smolagents_code"
+                  "agent_name": "LiteLLM Tool Calling",
+                  "agent_framework": "tool_calling"
                 }
               }
             }
@@ -546,8 +546,8 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "SmolAgents Code",
-              "agent_framework": "smolagents_code"
+              "agent_name": "LiteLLM Tool Calling",
+              "agent_framework": "tool_calling"
             }
           }
         }
@@ -622,7 +622,7 @@
       }
     },
     {
-      "evaluation_id": "browsecompplus/smolagents-code__anthropic_claude-opus-4-5/1774263615.0201504",
+      "evaluation_id": "browsecompplus/openai-solo__anthropic_claude-opus-4-5/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -659,9 +659,9 @@
               "num_samples": 100
             },
             "details": {
-              "average_agent_cost": "6.3",
-              "total_run_cost": "630.56",
-              "average_steps": "24.16",
+              "average_agent_cost": "7.59",
+              "total_run_cost": "759.44",
+              "average_steps": "27.18",
               "percent_finished": "1.0"
             }
           },
@@ -669,8 +669,8 @@
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "SmolAgents Code",
-                  "agent_framework": "smolagents_code"
+                  "agent_name": "OpenAI Solo",
+                  "agent_framework": "openai_solo"
                 }
               }
             }
@@ -682,15 +682,15 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "SmolAgents Code",
-              "agent_framework": "smolagents_code"
+              "agent_name": "OpenAI Solo",
+              "agent_framework": "openai_solo"
             }
           }
         }
       }
     },
     {
-      "evaluation_id": "swe-bench/claude-code-cli__anthropic_claude-opus-4-5/1774263615.0201504",
+      "evaluation_id": "swe-bench/smolagents-code__anthropic_claude-opus-4-5/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -722,14 +722,14 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7423,
+            "score": 0.65,
             "uncertainty": {
-              "num_samples": 97
+              "num_samples": 100
             },
             "details": {
-              "average_agent_cost": "5.6",
-              "total_run_cost": "543.62",
-              "average_steps": "31.76",
+              "average_agent_cost": "4.85",
+              "total_run_cost": "485.22",
+              "average_steps": "39.13",
               "percent_finished": "1.0"
             }
           },
@@ -737,8 +737,8 @@
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "Claude Code CLI",
-                  "agent_framework": "claude_code"
+                  "agent_name": "SmolAgents Code",
+                  "agent_framework": "smolagents_code"
                 }
               }
             }
@@ -750,15 +750,15 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "Claude Code CLI",
-              "agent_framework": "claude_code"
+              "agent_name": "SmolAgents Code",
+              "agent_framework": "smolagents_code"
             }
           }
         }
       }
     },
     {
-      "evaluation_id": "swe-bench/litellm-tool-calling__anthropic_claude-opus-4-5/1774263615.0201504",
+      "evaluation_id": "swe-bench/openai-solo__anthropic_claude-opus-4-5/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -790,14 +790,14 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6061,
+            "score": 0.8072,
             "uncertainty": {
-              "num_samples": 99
+              "num_samples": 83
             },
             "details": {
-              "average_agent_cost": "3.97",
-              "total_run_cost": "393.16",
-              "average_steps": "43.44",
+              "average_agent_cost": "2.96",
+              "total_run_cost": "245.78",
+              "average_steps": "34.1",
               "percent_finished": "1.0"
             }
           },
@@ -805,8 +805,8 @@
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "LiteLLM Tool Calling",
-                  "agent_framework": "tool_calling"
+                  "agent_name": "OpenAI Solo",
+                  "agent_framework": "openai_solo"
                 }
               }
             }
@@ -818,15 +818,15 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "LiteLLM Tool Calling",
-              "agent_framework": "tool_calling"
+              "agent_name": "OpenAI Solo",
+              "agent_framework": "openai_solo"
             }
           }
         }
       }
     },
     {
-      "evaluation_id": "swe-bench/openai-solo__anthropic_claude-opus-4-5/1774263615.0201504",
+      "evaluation_id": "swe-bench/claude-code-cli__anthropic_claude-opus-4-5/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -858,14 +858,14 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.8072,
+            "score": 0.7423,
             "uncertainty": {
-              "num_samples": 83
+              "num_samples": 97
             },
             "details": {
-              "average_agent_cost": "2.96",
-              "total_run_cost": "245.78",
-              "average_steps": "34.1",
+              "average_agent_cost": "5.6",
+              "total_run_cost": "543.62",
+              "average_steps": "31.76",
               "percent_finished": "1.0"
             }
           },
@@ -873,8 +873,8 @@
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "OpenAI Solo",
-                  "agent_framework": "openai_solo"
+                  "agent_name": "Claude Code CLI",
+                  "agent_framework": "claude_code"
                 }
               }
             }
@@ -886,15 +886,15 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "OpenAI Solo",
-              "agent_framework": "openai_solo"
+              "agent_name": "Claude Code CLI",
+              "agent_framework": "claude_code"
             }
           }
         }
       }
     },
     {
-      "evaluation_id": "swe-bench/smolagents-code__anthropic_claude-opus-4-5/1774263615.0201504",
+      "evaluation_id": "swe-bench/litellm-tool-calling__anthropic_claude-opus-4-5/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -926,14 +926,14 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.65,
+            "score": 0.6061,
             "uncertainty": {
-              "num_samples": 100
+              "num_samples": 99
             },
             "details": {
-              "average_agent_cost": "4.85",
-              "total_run_cost": "485.22",
-              "average_steps": "39.13",
+              "average_agent_cost": "3.97",
+              "total_run_cost": "393.16",
+              "average_steps": "43.44",
               "percent_finished": "1.0"
             }
           },
@@ -941,8 +941,8 @@
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "SmolAgents Code",
-                  "agent_framework": "smolagents_code"
+                  "agent_name": "LiteLLM Tool Calling",
+                  "agent_framework": "tool_calling"
                 }
               }
             }
@@ -954,8 +954,8 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "SmolAgents Code",
-              "agent_framework": "smolagents_code"
+              "agent_name": "LiteLLM Tool Calling",
+              "agent_framework": "tool_calling"
             }
           }
         }
@@ -1030,7 +1030,7 @@
       }
     },
     {
-      "evaluation_id": "tau-bench-2/airline/smolagents-code__anthropic_claude-opus-4-5/1774263615.0201504",
+      "evaluation_id": "tau-bench-2/airline/litellm-tool-calling__anthropic_claude-opus-4-5/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -1062,14 +1062,14 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.72,
+            "score": 0.66,
             "uncertainty": {
               "num_samples": 50
             },
             "details": {
-              "average_agent_cost": "0.78",
-              "total_run_cost": "39.67",
-              "average_steps": "11.88",
+              "average_agent_cost": "0.47",
+              "total_run_cost": "24.23",
+              "average_steps": "10.0",
               "percent_finished": "1.0"
             }
           },
@@ -1077,8 +1077,8 @@
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "SmolAgents Code",
-                  "agent_framework": "smolagents_code"
+                  "agent_name": "LiteLLM Tool Calling",
+                  "agent_framework": "tool_calling"
                 }
               }
             }
@@ -1090,8 +1090,8 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "SmolAgents Code",
-              "agent_framework": "smolagents_code"
+              "agent_name": "LiteLLM Tool Calling",
+              "agent_framework": "tool_calling"
             }
           }
         }
@@ -1166,7 +1166,7 @@
       }
     },
     {
-      "evaluation_id": "tau-bench-2/airline/litellm-tool-calling__anthropic_claude-opus-4-5/1774263615.0201504",
+      "evaluation_id": "tau-bench-2/airline/openai-solo__anthropic_claude-opus-4-5/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -1198,14 +1198,14 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.66,
+            "score": 0.74,
             "uncertainty": {
               "num_samples": 50
             },
             "details": {
-              "average_agent_cost": "0.47",
-              "total_run_cost": "24.23",
-              "average_steps": "10.0",
+              "average_agent_cost": "0.72",
+              "total_run_cost": "36.55",
+              "average_steps": "12.22",
               "percent_finished": "1.0"
             }
           },
@@ -1213,8 +1213,8 @@
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "LiteLLM Tool Calling",
-                  "agent_framework": "tool_calling"
+                  "agent_name": "OpenAI Solo",
+                  "agent_framework": "openai_solo"
                 }
               }
             }
@@ -1226,15 +1226,15 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "LiteLLM Tool Calling",
-              "agent_framework": "tool_calling"
+              "agent_name": "OpenAI Solo",
+              "agent_framework": "openai_solo"
             }
           }
         }
       }
     },
     {
-      "evaluation_id": "tau-bench-2/airline/openai-solo__anthropic_claude-opus-4-5/1774263615.0201504",
+      "evaluation_id": "tau-bench-2/airline/litellm-tool-calling-with-shortlisting__anthropic_claude-opus-4-5/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -1266,14 +1266,14 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.74,
+            "score": 0.66,
             "uncertainty": {
               "num_samples": 50
             },
             "details": {
-              "average_agent_cost": "0.72",
-              "total_run_cost": "36.55",
-              "average_steps": "12.22",
+              "average_agent_cost": "0.47",
+              "total_run_cost": "24.23",
+              "average_steps": "10.0",
               "percent_finished": "1.0"
             }
           },
@@ -1281,8 +1281,8 @@
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "OpenAI Solo",
-                  "agent_framework": "openai_solo"
+                  "agent_name": "LiteLLM Tool Calling with Shortlisting",
+                  "agent_framework": "tool_calling_with_shortlisting"
                 }
               }
             }
@@ -1294,15 +1294,15 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "OpenAI Solo",
-              "agent_framework": "openai_solo"
+              "agent_name": "LiteLLM Tool Calling with Shortlisting",
+              "agent_framework": "tool_calling_with_shortlisting"
             }
           }
         }
       }
     },
     {
-      "evaluation_id": "tau-bench-2/retail/litellm-tool-calling__anthropic_claude-opus-4-5/1774263615.0201504",
+      "evaluation_id": "tau-bench-2/airline/smolagents-code__anthropic_claude-opus-4-5/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -1315,33 +1315,33 @@
         "name": "exgentic",
         "version": "0.1.0"
       },
-      "benchmark": "tau-bench-2_retail",
+      "benchmark": "tau-bench-2_airline",
       "evaluation_results": [
         {
-          "evaluation_name": "tau-bench-2/retail",
+          "evaluation_name": "tau-bench-2/airline",
           "source_data": {
-            "dataset_name": "tau-bench-2/retail",
+            "dataset_name": "tau-bench-2/airline",
             "source_type": "url",
             "url": [
               "https://github.com/Exgentic/exgentic"
             ]
           },
           "metric_config": {
-            "evaluation_description": "Tau Bench 2 benchmark evaluation (retail subset)",
+            "evaluation_description": "Tau Bench 2 benchmark evaluation (airline subset)",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.78,
+            "score": 0.72,
             "uncertainty": {
-              "num_samples": 100
+              "num_samples": 50
             },
             "details": {
-              "average_agent_cost": "0.47",
-              "total_run_cost": "48.01",
-              "average_steps": "11.33",
+              "average_agent_cost": "0.78",
+              "total_run_cost": "39.67",
+              "average_steps": "11.88",
               "percent_finished": "1.0"
             }
           },
@@ -1349,8 +1349,8 @@
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "LiteLLM Tool Calling",
-                  "agent_framework": "tool_calling"
+                  "agent_name": "SmolAgents Code",
+                  "agent_framework": "smolagents_code"
                 }
               }
             }
@@ -1362,15 +1362,15 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "LiteLLM Tool Calling",
-              "agent_framework": "tool_calling"
+              "agent_name": "SmolAgents Code",
+              "agent_framework": "smolagents_code"
             }
           }
         }
       }
     },
     {
-      "evaluation_id": "tau-bench-2/retail/claude-code-cli__anthropic_claude-opus-4-5/1774263615.0201504",
+      "evaluation_id": "tau-bench-2/retail/smolagents-code__anthropic_claude-opus-4-5/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -1402,14 +1402,14 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.83,
+            "score": 0.78,
             "uncertainty": {
               "num_samples": 100
             },
             "details": {
-              "average_agent_cost": "1.6",
-              "total_run_cost": "161.14",
-              "average_steps": "12.54",
+              "average_agent_cost": "0.67",
+              "total_run_cost": "68.24",
+              "average_steps": "11.71",
               "percent_finished": "1.0"
             }
           },
@@ -1417,8 +1417,8 @@
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "Claude Code CLI",
-                  "agent_framework": "claude_code"
+                  "agent_name": "SmolAgents Code",
+                  "agent_framework": "smolagents_code"
                 }
               }
             }
@@ -1430,15 +1430,15 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "Claude Code CLI",
-              "agent_framework": "claude_code"
+              "agent_name": "SmolAgents Code",
+              "agent_framework": "smolagents_code"
             }
           }
         }
       }
     },
     {
-      "evaluation_id": "tau-bench-2/retail/smolagents-code__anthropic_claude-opus-4-5/1774263615.0201504",
+      "evaluation_id": "tau-bench-2/retail/claude-code-cli__anthropic_claude-opus-4-5/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -1470,14 +1470,14 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.78,
+            "score": 0.83,
             "uncertainty": {
               "num_samples": 100
             },
             "details": {
-              "average_agent_cost": "0.67",
-              "total_run_cost": "68.24",
-              "average_steps": "11.71",
+              "average_agent_cost": "1.6",
+              "total_run_cost": "161.14",
+              "average_steps": "12.54",
               "percent_finished": "1.0"
             }
           },
@@ -1485,8 +1485,8 @@
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "SmolAgents Code",
-                  "agent_framework": "smolagents_code"
+                  "agent_name": "Claude Code CLI",
+                  "agent_framework": "claude_code"
                 }
               }
             }
@@ -1498,15 +1498,15 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "SmolAgents Code",
-              "agent_framework": "smolagents_code"
+              "agent_name": "Claude Code CLI",
+              "agent_framework": "claude_code"
             }
           }
         }
       }
     },
     {
-      "evaluation_id": "tau-bench-2/airline/litellm-tool-calling-with-shortlisting__anthropic_claude-opus-4-5/1774263615.0201504",
+      "evaluation_id": "tau-bench-2/retail/litellm-tool-calling-with-shortlisting__anthropic_claude-opus-4-5/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -1519,33 +1519,33 @@
         "name": "exgentic",
         "version": "0.1.0"
       },
-      "benchmark": "tau-bench-2_airline",
+      "benchmark": "tau-bench-2_retail",
       "evaluation_results": [
         {
-          "evaluation_name": "tau-bench-2/airline",
+          "evaluation_name": "tau-bench-2/retail",
           "source_data": {
-            "dataset_name": "tau-bench-2/airline",
+            "dataset_name": "tau-bench-2/retail",
             "source_type": "url",
             "url": [
               "https://github.com/Exgentic/exgentic"
             ]
           },
           "metric_config": {
-            "evaluation_description": "Tau Bench 2 benchmark evaluation (airline subset)",
+            "evaluation_description": "Tau Bench 2 benchmark evaluation (retail subset)",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.66,
+            "score": 0.78,
             "uncertainty": {
-              "num_samples": 50
+              "num_samples": 100
             },
             "details": {
               "average_agent_cost": "0.47",
-              "total_run_cost": "24.23",
-              "average_steps": "10.0",
+              "total_run_cost": "48.01",
+              "average_steps": "11.33",
               "percent_finished": "1.0"
             }
           },
@@ -1574,7 +1574,7 @@
       }
     },
     {
-      "evaluation_id": "tau-bench-2/retail/openai-solo__anthropic_claude-opus-4-5/1774263615.0201504",
+      "evaluation_id": "tau-bench-2/retail/litellm-tool-calling__anthropic_claude-opus-4-5/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -1606,14 +1606,14 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.85,
+            "score": 0.78,
             "uncertainty": {
               "num_samples": 100
             },
             "details": {
-              "average_agent_cost": "0.55",
-              "total_run_cost": "56.18",
-              "average_steps": "12.54",
+              "average_agent_cost": "0.47",
+              "total_run_cost": "48.01",
+              "average_steps": "11.33",
               "percent_finished": "1.0"
             }
           },
@@ -1621,8 +1621,8 @@
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "OpenAI Solo",
-                  "agent_framework": "openai_solo"
+                  "agent_name": "LiteLLM Tool Calling",
+                  "agent_framework": "tool_calling"
                 }
               }
             }
@@ -1634,15 +1634,15 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "OpenAI Solo",
-              "agent_framework": "openai_solo"
+              "agent_name": "LiteLLM Tool Calling",
+              "agent_framework": "tool_calling"
             }
           }
         }
       }
     },
     {
-      "evaluation_id": "tau-bench-2/retail/litellm-tool-calling-with-shortlisting__anthropic_claude-opus-4-5/1774263615.0201504",
+      "evaluation_id": "tau-bench-2/retail/openai-solo__anthropic_claude-opus-4-5/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -1674,14 +1674,14 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.78,
+            "score": 0.85,
             "uncertainty": {
               "num_samples": 100
             },
             "details": {
-              "average_agent_cost": "0.47",
-              "total_run_cost": "48.01",
-              "average_steps": "11.33",
+              "average_agent_cost": "0.55",
+              "total_run_cost": "56.18",
+              "average_steps": "12.54",
               "percent_finished": "1.0"
             }
           },
@@ -1689,8 +1689,8 @@
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "LiteLLM Tool Calling with Shortlisting",
-                  "agent_framework": "tool_calling_with_shortlisting"
+                  "agent_name": "OpenAI Solo",
+                  "agent_framework": "openai_solo"
                 }
               }
             }
@@ -1702,15 +1702,15 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "LiteLLM Tool Calling with Shortlisting",
-              "agent_framework": "tool_calling_with_shortlisting"
+              "agent_name": "OpenAI Solo",
+              "agent_framework": "openai_solo"
             }
           }
         }
       }
     },
     {
-      "evaluation_id": "tau-bench-2/telecom/litellm-tool-calling-with-shortlisting__anthropic_claude-opus-4-5/1774263615.0201504",
+      "evaluation_id": "tau-bench-2/telecom/smolagents-code__anthropic_claude-opus-4-5/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -1742,14 +1742,14 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.76,
+            "score": 0.58,
             "uncertainty": {
               "num_samples": 100
             },
             "details": {
-              "average_agent_cost": "0.92",
-              "total_run_cost": "102.01",
-              "average_steps": "17.22",
+              "average_agent_cost": "1.06",
+              "total_run_cost": "114.62",
+              "average_steps": "13.77",
               "percent_finished": "1.0"
             }
           },
@@ -1757,8 +1757,8 @@
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "LiteLLM Tool Calling with Shortlisting",
-                  "agent_framework": "tool_calling_with_shortlisting"
+                  "agent_name": "SmolAgents Code",
+                  "agent_framework": "smolagents_code"
                 }
               }
             }
@@ -1770,15 +1770,15 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "LiteLLM Tool Calling with Shortlisting",
-              "agent_framework": "tool_calling_with_shortlisting"
+              "agent_name": "SmolAgents Code",
+              "agent_framework": "smolagents_code"
             }
           }
         }
       }
     },
     {
-      "evaluation_id": "tau-bench-2/telecom/smolagents-code__anthropic_claude-opus-4-5/1774263615.0201504",
+      "evaluation_id": "tau-bench-2/telecom/claude-code-cli__anthropic_claude-opus-4-5/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -1810,14 +1810,14 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.58,
+            "score": 0.76,
             "uncertainty": {
               "num_samples": 100
             },
             "details": {
-              "average_agent_cost": "1.06",
-              "total_run_cost": "114.62",
-              "average_steps": "13.77",
+              "average_agent_cost": "2.45",
+              "total_run_cost": "255.97",
+              "average_steps": "18.71",
               "percent_finished": "1.0"
             }
           },
@@ -1825,8 +1825,8 @@
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "SmolAgents Code",
-                  "agent_framework": "smolagents_code"
+                  "agent_name": "Claude Code CLI",
+                  "agent_framework": "claude_code"
                 }
               }
             }
@@ -1838,15 +1838,15 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "SmolAgents Code",
-              "agent_framework": "smolagents_code"
+              "agent_name": "Claude Code CLI",
+              "agent_framework": "claude_code"
             }
           }
         }
       }
     },
     {
-      "evaluation_id": "tau-bench-2/telecom/claude-code-cli__anthropic_claude-opus-4-5/1774263615.0201504",
+      "evaluation_id": "tau-bench-2/telecom/litellm-tool-calling-with-shortlisting__anthropic_claude-opus-4-5/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -1883,9 +1883,9 @@
               "num_samples": 100
             },
             "details": {
-              "average_agent_cost": "2.45",
-              "total_run_cost": "255.97",
-              "average_steps": "18.71",
+              "average_agent_cost": "0.92",
+              "total_run_cost": "102.01",
+              "average_steps": "17.22",
               "percent_finished": "1.0"
             }
           },
@@ -1893,8 +1893,8 @@
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "Claude Code CLI",
-                  "agent_framework": "claude_code"
+                  "agent_name": "LiteLLM Tool Calling with Shortlisting",
+                  "agent_framework": "tool_calling_with_shortlisting"
                 }
               }
             }
@@ -1906,15 +1906,15 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "Claude Code CLI",
-              "agent_framework": "claude_code"
+              "agent_name": "LiteLLM Tool Calling with Shortlisting",
+              "agent_framework": "tool_calling_with_shortlisting"
             }
           }
         }
       }
     },
     {
-      "evaluation_id": "tau-bench-2/telecom/litellm-tool-calling__anthropic_claude-opus-4-5/1774263615.0201504",
+      "evaluation_id": "tau-bench-2/telecom/openai-solo__anthropic_claude-opus-4-5/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -1946,14 +1946,14 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.76,
+            "score": 0.84,
             "uncertainty": {
               "num_samples": 100
             },
             "details": {
-              "average_agent_cost": "0.92",
-              "total_run_cost": "102.01",
-              "average_steps": "17.22",
+              "average_agent_cost": "1.25",
+              "total_run_cost": "136.84",
+              "average_steps": "17.15",
               "percent_finished": "1.0"
             }
           },
@@ -1961,8 +1961,8 @@
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "LiteLLM Tool Calling",
-                  "agent_framework": "tool_calling"
+                  "agent_name": "OpenAI Solo",
+                  "agent_framework": "openai_solo"
                 }
               }
             }
@@ -1974,15 +1974,15 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "LiteLLM Tool Calling",
-              "agent_framework": "tool_calling"
+              "agent_name": "OpenAI Solo",
+              "agent_framework": "openai_solo"
             }
           }
         }
       }
     },
     {
-      "evaluation_id": "tau-bench-2/telecom/openai-solo__anthropic_claude-opus-4-5/1774263615.0201504",
+      "evaluation_id": "tau-bench-2/telecom/litellm-tool-calling__anthropic_claude-opus-4-5/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -2014,14 +2014,14 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.84,
+            "score": 0.76,
             "uncertainty": {
               "num_samples": 100
             },
             "details": {
-              "average_agent_cost": "1.25",
-              "total_run_cost": "136.84",
-              "average_steps": "17.15",
+              "average_agent_cost": "0.92",
+              "total_run_cost": "102.01",
+              "average_steps": "17.22",
               "percent_finished": "1.0"
             }
           },
@@ -2029,8 +2029,8 @@
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "OpenAI Solo",
-                  "agent_framework": "openai_solo"
+                  "agent_name": "LiteLLM Tool Calling",
+                  "agent_framework": "tool_calling"
                 }
               }
             }
@@ -2042,8 +2042,8 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "OpenAI Solo",
-              "agent_framework": "openai_solo"
+              "agent_name": "LiteLLM Tool Calling",
+              "agent_framework": "tool_calling"
             }
           }
         }
diff --git a/data/models/anthropic_claude-opus-4.1.json b/data/models/anthropic_claude-opus-4.1.json
index b51256b4d5a95f9160a82aa03d45fc55ec0aba09..59416d90b1dbdb120915f9f1b242f981bce8e890 100644
--- a/data/models/anthropic_claude-opus-4.1.json
+++ b/data/models/anthropic_claude-opus-4.1.json
@@ -158,7 +158,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/claude-code__claude-opus-4.1/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/mini-swe-agent__claude-opus-4.1/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -182,7 +182,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-11-04",
+          "evaluation_timestamp": "2025-11-03",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -191,17 +191,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 34.8,
+            "score": 35.1,
             "uncertainty": {
               "standard_error": {
-                "value": 2.9
+                "value": 2.5
               },
               "num_samples": 435
             }
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Claude Code\" -m \"Claude Opus 4.1\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Mini-SWE-Agent\" -m \"Claude Opus 4.1\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -218,7 +218,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Claude Code\" -m \"Claude Opus 4.1\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Mini-SWE-Agent\" -m \"Claude Opus 4.1\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -232,7 +232,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/mini-swe-agent__claude-opus-4.1/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/claude-code__claude-opus-4.1/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -256,7 +256,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-11-03",
+          "evaluation_timestamp": "2025-11-04",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -265,17 +265,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 35.1,
+            "score": 34.8,
             "uncertainty": {
               "standard_error": {
-                "value": 2.5
+                "value": 2.9
               },
               "num_samples": 435
             }
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Mini-SWE-Agent\" -m \"Claude Opus 4.1\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Claude Code\" -m \"Claude Opus 4.1\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -292,7 +292,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Mini-SWE-Agent\" -m \"Claude Opus 4.1\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Claude Code\" -m \"Claude Opus 4.1\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
diff --git a/data/models/anthropic_claude-opus-4.5.json b/data/models/anthropic_claude-opus-4.5.json
index 14b1dc3ce90d80ab30d23bbb2e060321876d554a..007d3ac2c88dec5dff72fba0205d56eeaed42464 100644
--- a/data/models/anthropic_claude-opus-4.5.json
+++ b/data/models/anthropic_claude-opus-4.5.json
@@ -4,13 +4,13 @@
     "id": "anthropic/claude-opus-4.5",
     "developer": "Anthropic",
     "additional_details": {
-      "agent_name": "OpenCode",
-      "agent_organization": "Anomaly Innovations"
+      "agent_name": "Terminus 2",
+      "agent_organization": "Terminal Bench"
     }
   },
   "evaluations": [
     {
-      "evaluation_id": "terminal-bench-2.0/opencode__claude-opus-4.5/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/terminus-2__claude-opus-4.5/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -34,7 +34,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2026-01-12",
+          "evaluation_timestamp": "2025-11-22",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -43,11 +43,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 51.7
+            "score": 57.8,
+            "uncertainty": {
+              "standard_error": {
+                "value": 2.5
+              },
+              "num_samples": 435
+            }
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"OpenCode\" -m \"Claude Opus 4.5\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"Claude Opus 4.5\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -64,7 +70,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"OpenCode\" -m \"Claude Opus 4.5\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"Claude Opus 4.5\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -78,7 +84,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/terminus-2__claude-opus-4.5/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/mux__claude-opus-4.5/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -102,7 +108,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-11-22",
+          "evaluation_timestamp": "2026-01-17",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -111,17 +117,11 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 57.8,
-            "uncertainty": {
-              "standard_error": {
-                "value": 2.5
-              },
-              "num_samples": 435
-            }
+            "score": 58.4
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"Claude Opus 4.5\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Mux\" -m \"Claude Opus 4.5\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -138,7 +138,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"Claude Opus 4.5\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Mux\" -m \"Claude Opus 4.5\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -152,7 +152,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/goose__claude-opus-4.5/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/opencode__claude-opus-4.5/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -176,7 +176,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-12-11",
+          "evaluation_timestamp": "2026-01-12",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -185,17 +185,11 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 54.3,
-            "uncertainty": {
-              "standard_error": {
-                "value": 2.6
-              },
-              "num_samples": 435
-            }
+            "score": 51.7
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Goose\" -m \"Claude Opus 4.5\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"OpenCode\" -m \"Claude Opus 4.5\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -212,7 +206,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Goose\" -m \"Claude Opus 4.5\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"OpenCode\" -m \"Claude Opus 4.5\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -226,7 +220,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/openhands__claude-opus-4.5/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/goose__claude-opus-4.5/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -250,7 +244,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2026-01-04",
+          "evaluation_timestamp": "2025-12-11",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -259,17 +253,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 51.9,
+            "score": 54.3,
             "uncertainty": {
               "standard_error": {
-                "value": 2.9
+                "value": 2.6
               },
               "num_samples": 435
             }
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"OpenHands\" -m \"Claude Opus 4.5\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Goose\" -m \"Claude Opus 4.5\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -286,7 +280,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"OpenHands\" -m \"Claude Opus 4.5\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Goose\" -m \"Claude Opus 4.5\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -300,7 +294,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/mux__claude-opus-4.5/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/letta-code__claude-opus-4.5/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -324,7 +318,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2026-01-17",
+          "evaluation_timestamp": "2025-12-17",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -333,11 +327,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 58.4
+            "score": 59.1,
+            "uncertainty": {
+              "standard_error": {
+                "value": 2.4
+              },
+              "num_samples": 435
+            }
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Mux\" -m \"Claude Opus 4.5\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Letta Code\" -m \"Claude Opus 4.5\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -354,7 +354,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Mux\" -m \"Claude Opus 4.5\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Letta Code\" -m \"Claude Opus 4.5\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -368,7 +368,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/droid__claude-opus-4.5/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/openhands__claude-opus-4.5/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -392,7 +392,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-12-11",
+          "evaluation_timestamp": "2026-01-04",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -401,17 +401,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 63.1,
+            "score": 51.9,
             "uncertainty": {
               "standard_error": {
-                "value": 2.7
+                "value": 2.9
               },
               "num_samples": 435
             }
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Droid\" -m \"Claude Opus 4.5\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"OpenHands\" -m \"Claude Opus 4.5\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -428,7 +428,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Droid\" -m \"Claude Opus 4.5\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"OpenHands\" -m \"Claude Opus 4.5\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -442,7 +442,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/letta-code__claude-opus-4.5/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/droid__claude-opus-4.5/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -466,7 +466,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-12-17",
+          "evaluation_timestamp": "2025-12-11",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -475,17 +475,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 59.1,
+            "score": 63.1,
             "uncertainty": {
               "standard_error": {
-                "value": 2.4
+                "value": 2.7
               },
               "num_samples": 435
             }
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Letta Code\" -m \"Claude Opus 4.5\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Droid\" -m \"Claude Opus 4.5\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -502,7 +502,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Letta Code\" -m \"Claude Opus 4.5\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Droid\" -m \"Claude Opus 4.5\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
diff --git a/data/models/anthropic_claude-opus-4.6.json b/data/models/anthropic_claude-opus-4.6.json
index 048dae2de3da40230747c994f11a1351dfec5a14..6de13fc0f3140d257d348a852063485bd1007995 100644
--- a/data/models/anthropic_claude-opus-4.6.json
+++ b/data/models/anthropic_claude-opus-4.6.json
@@ -4,13 +4,13 @@
     "id": "anthropic/claude-opus-4.6",
     "developer": "Anthropic",
     "additional_details": {
-      "agent_name": "Terminus-KIRA",
-      "agent_organization": "KRAFTON AI"
+      "agent_name": "Claude Code",
+      "agent_organization": "Anthropic"
     }
   },
   "evaluations": [
     {
-      "evaluation_id": "terminal-bench-2.0/terminus-kira__claude-opus-4.6/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/claude-code__claude-opus-4.6/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -34,7 +34,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2026-02-22",
+          "evaluation_timestamp": "2026-02-07",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -43,17 +43,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 74.7,
+            "score": 58.0,
             "uncertainty": {
               "standard_error": {
-                "value": 2.6
+                "value": 2.9
               },
               "num_samples": 435
             }
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus-KIRA\" -m \"Claude Opus 4.6\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Claude Code\" -m \"Claude Opus 4.6\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -70,7 +70,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus-KIRA\" -m \"Claude Opus 4.6\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Claude Code\" -m \"Claude Opus 4.6\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -84,7 +84,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/droid__claude-opus-4.6/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/mux__claude-opus-4.6/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -108,7 +108,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2026-02-05",
+          "evaluation_timestamp": "2026-02-13",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -117,7 +117,7 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 69.9,
+            "score": 66.5,
             "uncertainty": {
               "standard_error": {
                 "value": 2.5
@@ -127,7 +127,7 @@
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Droid\" -m \"Claude Opus 4.6\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Mux\" -m \"Claude Opus 4.6\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -144,7 +144,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Droid\" -m \"Claude Opus 4.6\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Mux\" -m \"Claude Opus 4.6\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -158,7 +158,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/mux__claude-opus-4.6/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/tongagents__claude-opus-4.6/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -182,7 +182,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2026-02-13",
+          "evaluation_timestamp": "2026-02-22",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -191,17 +191,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 66.5,
+            "score": 71.9,
             "uncertainty": {
               "standard_error": {
-                "value": 2.5
+                "value": 2.7
               },
               "num_samples": 435
             }
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Mux\" -m \"Claude Opus 4.6\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"TongAgents\" -m \"Claude Opus 4.6\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -218,7 +218,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Mux\" -m \"Claude Opus 4.6\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"TongAgents\" -m \"Claude Opus 4.6\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -232,7 +232,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/crux__claude-opus-4.6/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/terminus-2__claude-opus-4.6/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -256,7 +256,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2026-02-23",
+          "evaluation_timestamp": "2026-02-06",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -265,11 +265,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 66.9
+            "score": 62.9,
+            "uncertainty": {
+              "standard_error": {
+                "value": 2.7
+              },
+              "num_samples": 435
+            }
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Crux\" -m \"Claude Opus 4.6\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"Claude Opus 4.6\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -286,7 +292,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Crux\" -m \"Claude Opus 4.6\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"Claude Opus 4.6\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -300,7 +306,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/claude-code__claude-opus-4.6/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/crux__claude-opus-4.6/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -324,7 +330,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2026-02-07",
+          "evaluation_timestamp": "2026-02-23",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -333,17 +339,11 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 58.0,
-            "uncertainty": {
-              "standard_error": {
-                "value": 2.9
-              },
-              "num_samples": 435
-            }
+            "score": 66.9
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Claude Code\" -m \"Claude Opus 4.6\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Crux\" -m \"Claude Opus 4.6\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -360,7 +360,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Claude Code\" -m \"Claude Opus 4.6\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Crux\" -m \"Claude Opus 4.6\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -374,7 +374,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/tongagents__claude-opus-4.6/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/droid__claude-opus-4.6/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -398,7 +398,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2026-02-22",
+          "evaluation_timestamp": "2026-02-05",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -407,17 +407,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 71.9,
+            "score": 69.9,
             "uncertainty": {
               "standard_error": {
-                "value": 2.7
+                "value": 2.5
               },
               "num_samples": 435
             }
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"TongAgents\" -m \"Claude Opus 4.6\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Droid\" -m \"Claude Opus 4.6\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -434,7 +434,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"TongAgents\" -m \"Claude Opus 4.6\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Droid\" -m \"Claude Opus 4.6\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -448,7 +448,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/terminus-2__claude-opus-4.6/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/terminus-kira__claude-opus-4.6/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -472,7 +472,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2026-02-06",
+          "evaluation_timestamp": "2026-02-22",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -481,17 +481,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 62.9,
+            "score": 74.7,
             "uncertainty": {
               "standard_error": {
-                "value": 2.7
+                "value": 2.6
               },
               "num_samples": 435
             }
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"Claude Opus 4.6\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus-KIRA\" -m \"Claude Opus 4.6\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -508,7 +508,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"Claude Opus 4.6\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus-KIRA\" -m \"Claude Opus 4.6\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
diff --git a/data/models/anthropic_claude-sonnet-4.5.json b/data/models/anthropic_claude-sonnet-4.5.json
index 2721b6a2b6511249d3161ee660ebb342753596b5..66356dbecae8af8177ad511141877805ad8752da 100644
--- a/data/models/anthropic_claude-sonnet-4.5.json
+++ b/data/models/anthropic_claude-sonnet-4.5.json
@@ -158,7 +158,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/claude-code__claude-sonnet-4.5/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/maya__claude-sonnet-4.5/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -182,7 +182,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-11-04",
+          "evaluation_timestamp": "2026-01-04",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -191,17 +191,11 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 40.1,
-            "uncertainty": {
-              "standard_error": {
-                "value": 2.9
-              },
-              "num_samples": 435
-            }
+            "score": 42.7
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Claude Code\" -m \"Claude Sonnet 4.5\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"MAYA\" -m \"Claude Sonnet 4.5\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -218,7 +212,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Claude Code\" -m \"Claude Sonnet 4.5\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"MAYA\" -m \"Claude Sonnet 4.5\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -232,7 +226,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/maya__claude-sonnet-4.5/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/openhands__claude-sonnet-4.5/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -256,7 +250,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2026-01-04",
+          "evaluation_timestamp": "2025-11-02",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -265,11 +259,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 42.7
+            "score": 42.6,
+            "uncertainty": {
+              "standard_error": {
+                "value": 2.8
+              },
+              "num_samples": 435
+            }
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"MAYA\" -m \"Claude Sonnet 4.5\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"OpenHands\" -m \"Claude Sonnet 4.5\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -286,7 +286,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"MAYA\" -m \"Claude Sonnet 4.5\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"OpenHands\" -m \"Claude Sonnet 4.5\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -300,7 +300,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/mini-swe-agent__claude-sonnet-4.5/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/claude-code__claude-sonnet-4.5/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -324,7 +324,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-11-03",
+          "evaluation_timestamp": "2025-11-04",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -333,17 +333,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 42.5,
+            "score": 40.1,
             "uncertainty": {
               "standard_error": {
-                "value": 2.8
+                "value": 2.9
               },
               "num_samples": 435
             }
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Mini-SWE-Agent\" -m \"Claude Sonnet 4.5\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Claude Code\" -m \"Claude Sonnet 4.5\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -360,7 +360,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Mini-SWE-Agent\" -m \"Claude Sonnet 4.5\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Claude Code\" -m \"Claude Sonnet 4.5\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -448,7 +448,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/openhands__claude-sonnet-4.5/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/mini-swe-agent__claude-sonnet-4.5/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -472,7 +472,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-11-02",
+          "evaluation_timestamp": "2025-11-03",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -481,7 +481,7 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 42.6,
+            "score": 42.5,
             "uncertainty": {
               "standard_error": {
                 "value": 2.8
@@ -491,7 +491,7 @@
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"OpenHands\" -m \"Claude Sonnet 4.5\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Mini-SWE-Agent\" -m \"Claude Sonnet 4.5\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -508,7 +508,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"OpenHands\" -m \"Claude Sonnet 4.5\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Mini-SWE-Agent\" -m \"Claude Sonnet 4.5\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
diff --git a/data/models/boltmonkey_neuraldaredevil-supernova-lite-7b-dareties-abliterated.json b/data/models/boltmonkey_neuraldaredevil-supernova-lite-7b-dareties-abliterated.json
index eb03ad8b35e71a4f26603a2960132d29f0246b60..ed5c0ad9e23e3e1024094c595c2931cbc579e102 100644
--- a/data/models/boltmonkey_neuraldaredevil-supernova-lite-7b-dareties-abliterated.json
+++ b/data/models/boltmonkey_neuraldaredevil-supernova-lite-7b-dareties-abliterated.json
@@ -5,7 +5,7 @@
     "developer": "BoltMonkey",
     "inference_platform": "unknown",
     "additional_details": {
-      "precision": "bfloat16",
+      "precision": "float16",
       "architecture": "LlamaForCausalLM",
       "params_billions": "8.03"
     }
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7999
+            "score": 0.459
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5152
+            "score": 0.5185
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1193
+            "score": 0.0937
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.281
+            "score": 0.2743
           }
         },
         {
@@ -116,7 +116,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4019
+            "score": 0.4083
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3733
+            "score": 0.3631
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.459
+            "score": 0.7999
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5185
+            "score": 0.5152
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0937
+            "score": 0.1193
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2743
+            "score": 0.281
           }
         },
         {
@@ -246,7 +246,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4083
+            "score": 0.4019
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3631
+            "score": 0.3733
           }
         }
       ],
diff --git a/data/models/bunnycore_llama-3.2-3b-deep-test.json b/data/models/bunnycore_llama-3.2-3b-deep-test.json
index 05cbb770cffa010b799551a630bc7b1089a91900..c829321bc4e1b62229f276602c62e6f6bd9a3faf 100644
--- a/data/models/bunnycore_llama-3.2-3b-deep-test.json
+++ b/data/models/bunnycore_llama-3.2-3b-deep-test.json
@@ -5,9 +5,9 @@
     "developer": "bunnycore",
     "inference_platform": "unknown",
     "additional_details": {
-      "precision": "float16",
+      "precision": "bfloat16",
       "architecture": "LlamaForCausalLM",
-      "params_billions": "3.607"
+      "params_billions": "1.803"
     }
   },
   "evaluations": [
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4652
+            "score": 0.1775
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4531
+            "score": 0.295
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1284
+            "score": 0.0
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2643
+            "score": 0.2517
           }
         },
         {
@@ -116,7 +116,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3394
+            "score": 0.3647
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3152
+            "score": 0.1049
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1775
+            "score": 0.4652
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.295
+            "score": 0.4531
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0
+            "score": 0.1284
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2517
+            "score": 0.2643
           }
         },
         {
@@ -246,7 +246,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3647
+            "score": 0.3394
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1049
+            "score": 0.3152
           }
         }
       ],
diff --git a/data/models/cir-ams_btrm_qwen2_7b_0613.json b/data/models/cir-ams_btrm_qwen2_7b_0613.json
index 9fb827ce32fb32044e2247d7f86c70d1bc13d414..84a36ab2262aa5d4869e5d141d383b85699971f1 100644
--- a/data/models/cir-ams_btrm_qwen2_7b_0613.json
+++ b/data/models/cir-ams_btrm_qwen2_7b_0613.json
@@ -9,10 +9,10 @@
   },
   "evaluations": [
     {
-      "evaluation_id": "reward-bench-2/CIR-AMS_BTRM_Qwen2_7b_0613/1766412838.146816",
+      "evaluation_id": "reward-bench/CIR-AMS_BTRM_Qwen2_7b_0613/1766412838.146816",
       "retrieved_timestamp": "1766412838.146816",
       "source_metadata": {
-        "source_name": "RewardBench 2",
+        "source_name": "RewardBench",
         "source_type": "documentation",
         "source_organization_name": "Allen Institute for AI",
         "source_organization_url": "https://allenai.org",
@@ -31,127 +31,109 @@
         {
           "evaluation_name": "Score",
           "metric_config": {
-            "evaluation_description": "Overall RewardBench 2 Score (mean of all metrics)",
-            "lower_is_better": false,
-            "score_type": "continuous",
-            "min_score": 0.0,
-            "max_score": 1.0
-          },
-          "score_details": {
-            "score": 0.5736
-          },
-          "source_data": {
-            "dataset_name": "RewardBench 2",
-            "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
-          }
-        },
-        {
-          "evaluation_name": "Factuality",
-          "metric_config": {
-            "evaluation_description": "Factuality score - measures factual accuracy",
+            "evaluation_description": "Overall RewardBench Score",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5347
+            "score": 0.8172
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Precise IF",
+          "evaluation_name": "Chat",
           "metric_config": {
-            "evaluation_description": "Precise Instruction Following score",
+            "evaluation_description": "Chat accuracy - includes easy chat subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3563
+            "score": 0.9749
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Math",
+          "evaluation_name": "Chat Hard",
           "metric_config": {
-            "evaluation_description": "Math score - measures mathematical reasoning",
+            "evaluation_description": "Chat Hard accuracy - includes hard chat subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6066
+            "score": 0.5724
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
           "evaluation_name": "Safety",
           "metric_config": {
-            "evaluation_description": "Safety score - measures safety awareness",
+            "evaluation_description": "Safety accuracy - includes safety subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7178
+            "score": 0.9014
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Focus",
+          "evaluation_name": "Reasoning",
           "metric_config": {
-            "evaluation_description": "Focus score - measures response focus",
+            "evaluation_description": "Reasoning accuracy - includes code and math subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5737
+            "score": 0.8775
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Ties",
+          "evaluation_name": "Prior Sets (0.5 weight)",
           "metric_config": {
-            "evaluation_description": "Ties score - ability to identify tie cases",
+            "evaluation_description": "Prior Sets score (weighted 0.5) - includes test sets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6527
+            "score": 0.7029
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         }
       ],
@@ -159,10 +141,10 @@
       "generation_config": null
     },
     {
-      "evaluation_id": "reward-bench/CIR-AMS_BTRM_Qwen2_7b_0613/1766412838.146816",
+      "evaluation_id": "reward-bench-2/CIR-AMS_BTRM_Qwen2_7b_0613/1766412838.146816",
       "retrieved_timestamp": "1766412838.146816",
       "source_metadata": {
-        "source_name": "RewardBench",
+        "source_name": "RewardBench 2",
         "source_type": "documentation",
         "source_organization_name": "Allen Institute for AI",
         "source_organization_url": "https://allenai.org",
@@ -181,109 +163,127 @@
         {
           "evaluation_name": "Score",
           "metric_config": {
-            "evaluation_description": "Overall RewardBench Score",
+            "evaluation_description": "Overall RewardBench 2 Score (mean of all metrics)",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.8172
+            "score": 0.5736
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Chat",
+          "evaluation_name": "Factuality",
           "metric_config": {
-            "evaluation_description": "Chat accuracy - includes easy chat subsets",
+            "evaluation_description": "Factuality score - measures factual accuracy",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9749
+            "score": 0.5347
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Chat Hard",
+          "evaluation_name": "Precise IF",
           "metric_config": {
-            "evaluation_description": "Chat Hard accuracy - includes hard chat subsets",
+            "evaluation_description": "Precise Instruction Following score",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5724
+            "score": 0.3563
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
+          }
+        },
+        {
+          "evaluation_name": "Math",
+          "metric_config": {
+            "evaluation_description": "Math score - measures mathematical reasoning",
+            "lower_is_better": false,
+            "score_type": "continuous",
+            "min_score": 0.0,
+            "max_score": 1.0
+          },
+          "score_details": {
+            "score": 0.6066
+          },
+          "source_data": {
+            "dataset_name": "RewardBench 2",
+            "source_type": "hf_dataset",
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
           "evaluation_name": "Safety",
           "metric_config": {
-            "evaluation_description": "Safety accuracy - includes safety subsets",
+            "evaluation_description": "Safety score - measures safety awareness",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9014
+            "score": 0.7178
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Reasoning",
+          "evaluation_name": "Focus",
           "metric_config": {
-            "evaluation_description": "Reasoning accuracy - includes code and math subsets",
+            "evaluation_description": "Focus score - measures response focus",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.8775
+            "score": 0.5737
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Prior Sets (0.5 weight)",
+          "evaluation_name": "Ties",
           "metric_config": {
-            "evaluation_description": "Prior Sets score (weighted 0.5) - includes test sets",
+            "evaluation_description": "Ties score - ability to identify tie cases",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7029
+            "score": 0.6527
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         }
       ],
diff --git a/data/models/cohere_command-a-03-2025.json b/data/models/cohere_command-a-03-2025.json
index 205f7c496ed81b612dd2b182b3cf2e9fd9ac9c54..aedaf4e5f944a400d87afc543fa422bde24be135 100644
--- a/data/models/cohere_command-a-03-2025.json
+++ b/data/models/cohere_command-a-03-2025.json
@@ -10,8 +10,8 @@
   },
   "evaluations": [
     {
-      "evaluation_id": "global-mmlu-lite/cohere_command-a-03-2025/1773936583.743359",
-      "retrieved_timestamp": "1773936583.743359",
+      "evaluation_id": "global-mmlu-lite/cohere_command-a-03-2025/1773936496.366405",
+      "retrieved_timestamp": "1773936496.366405",
       "source_metadata": {
         "source_name": "Global MMLU Lite Leaderboard",
         "source_type": "documentation",
@@ -525,8 +525,8 @@
       "generation_config": null
     },
     {
-      "evaluation_id": "global-mmlu-lite/cohere_command-a-03-2025/1773936496.366405",
-      "retrieved_timestamp": "1773936496.366405",
+      "evaluation_id": "global-mmlu-lite/cohere_command-a-03-2025/1773936583.743359",
+      "retrieved_timestamp": "1773936583.743359",
       "source_metadata": {
         "source_name": "Global MMLU Lite Leaderboard",
         "source_type": "documentation",
diff --git a/data/models/columbia-nlp_lion-gemma-2b-dpo-v1.0.json b/data/models/columbia-nlp_lion-gemma-2b-dpo-v1.0.json
index e1500a121f56ad89301900472e223d7937764cb0..fcba7390760a9757eb868fa82619eef91d551f86 100644
--- a/data/models/columbia-nlp_lion-gemma-2b-dpo-v1.0.json
+++ b/data/models/columbia-nlp_lion-gemma-2b-dpo-v1.0.json
@@ -5,7 +5,7 @@
     "developer": "Columbia-NLP",
     "inference_platform": "unknown",
     "additional_details": {
-      "precision": "float16",
+      "precision": "bfloat16",
       "architecture": "GemmaForCausalLM",
       "params_billions": "2.506"
     }
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3278
+            "score": 0.3102
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.392
+            "score": 0.3881
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0431
+            "score": 0.0536
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2492
+            "score": 0.2534
           }
         },
         {
@@ -116,7 +116,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.412
+            "score": 0.4081
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1666
+            "score": 0.1665
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3102
+            "score": 0.3278
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3881
+            "score": 0.392
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0536
+            "score": 0.0431
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2534
+            "score": 0.2492
           }
         },
         {
@@ -246,7 +246,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4081
+            "score": 0.412
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1665
+            "score": 0.1666
           }
         }
       ],
diff --git a/data/models/daemontatox_pathfinderai.json b/data/models/daemontatox_pathfinderai.json
index 8b13e2aabf79ff36b82f8d8bd4c0bcdf2b41e385..7a5f7d25c7278e2df08548a48abfe0b0ee9b4f2a 100644
--- a/data/models/daemontatox_pathfinderai.json
+++ b/data/models/daemontatox_pathfinderai.json
@@ -5,7 +5,7 @@
     "developer": "Daemontatox",
     "inference_platform": "unknown",
     "additional_details": {
-      "precision": "float16",
+      "precision": "bfloat16",
       "architecture": "Qwen2ForCausalLM",
       "params_billions": "32.764"
     }
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3745
+            "score": 0.4855
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6668
+            "score": 0.6627
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4758
+            "score": 0.4841
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3943
+            "score": 0.3096
           }
         },
         {
@@ -116,7 +116,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4858
+            "score": 0.4256
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5593
+            "score": 0.5542
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4855
+            "score": 0.3745
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6627
+            "score": 0.6668
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4841
+            "score": 0.4758
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3096
+            "score": 0.3943
           }
         },
         {
@@ -246,7 +246,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4256
+            "score": 0.4858
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5542
+            "score": 0.5593
           }
         }
       ],
diff --git a/data/models/davielion_llama-3.2-1b-spin-iter0.json b/data/models/davielion_llama-3.2-1b-spin-iter0.json
index 849a1d52d59a5f16eab6aaa35f259f630d9dc175..2ea14b6e6da41d61b06880761473f45de63d9756 100644
--- a/data/models/davielion_llama-3.2-1b-spin-iter0.json
+++ b/data/models/davielion_llama-3.2-1b-spin-iter0.json
@@ -5,7 +5,7 @@
     "developer": "DavieLion",
     "inference_platform": "unknown",
     "additional_details": {
-      "precision": "bfloat16",
+      "precision": "float16",
       "architecture": "LlamaForCausalLM",
       "params_billions": "1.236"
     }
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1549
+            "score": 0.1507
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2937
+            "score": 0.293
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.006
+            "score": 0.0
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2576
+            "score": 0.2534
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1128
+            "score": 0.1125
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1507
+            "score": 0.1549
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.293
+            "score": 0.2937
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0
+            "score": 0.006
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2534
+            "score": 0.2576
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1125
+            "score": 0.1128
           }
         }
       ],
diff --git a/data/models/davielion_llama-3.2-1b-spin-iter3.json b/data/models/davielion_llama-3.2-1b-spin-iter3.json
index 99c7b4d0290325891f13fa396abea88044dda26d..7ac3466820dc73e6944e390d07375635e5394c56 100644
--- a/data/models/davielion_llama-3.2-1b-spin-iter3.json
+++ b/data/models/davielion_llama-3.2-1b-spin-iter3.json
@@ -5,7 +5,7 @@
     "developer": "DavieLion",
     "inference_platform": "unknown",
     "additional_details": {
-      "precision": "bfloat16",
+      "precision": "float16",
       "architecture": "LlamaForCausalLM",
       "params_billions": "1.236"
     }
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1324
+            "score": 0.1336
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2972
+            "score": 0.2975
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0
+            "score": 0.0068
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2643
+            "score": 0.2534
           }
         },
         {
@@ -116,7 +116,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3527
+            "score": 0.35
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1129
+            "score": 0.1128
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1336
+            "score": 0.1324
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2975
+            "score": 0.2972
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0068
+            "score": 0.0
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2534
+            "score": 0.2643
           }
         },
         {
@@ -246,7 +246,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.35
+            "score": 0.3527
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1128
+            "score": 0.1129
           }
         }
       ],
diff --git a/data/models/deepmount00_llama-3.1-8b-ita.json b/data/models/deepmount00_llama-3.1-8b-ita.json
index 1fef7ca0b3d471692e7379016093b45312ecc7df..be94466036e753700b8de72e15b468fc6edebdee 100644
--- a/data/models/deepmount00_llama-3.1-8b-ita.json
+++ b/data/models/deepmount00_llama-3.1-8b-ita.json
@@ -6,8 +6,8 @@
     "inference_platform": "unknown",
     "additional_details": {
       "precision": "bfloat16",
-      "architecture": "LlamaForCausalLM",
-      "params_billions": "8.03",
+      "architecture": "Unknown",
+      "params_billions": "0.0",
       "model_id_aliases": [
         "DeepMount00/Llama-3.1-8b-Ita"
       ]
@@ -15,7 +15,7 @@
   },
   "evaluations": [
     {
-      "evaluation_id": "hfopenllm_v2/DeepMount00_Llama-3.1-8b-ITA/1773936498.240187",
+      "evaluation_id": "hfopenllm_v2/DeepMount00_Llama-3.1-8b-Ita/1773936498.240187",
       "retrieved_timestamp": "1773936498.240187",
       "source_metadata": {
         "source_name": "HF Open LLM v2",
@@ -47,7 +47,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7917
+            "score": 0.5365
           }
         },
         {
@@ -65,7 +65,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5109
+            "score": 0.517
           }
         },
         {
@@ -83,7 +83,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1088
+            "score": 0.1707
           }
         },
         {
@@ -101,7 +101,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2878
+            "score": 0.3062
           }
         },
         {
@@ -119,7 +119,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4136
+            "score": 0.4487
           }
         },
         {
@@ -137,7 +137,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3876
+            "score": 0.396
           }
         }
       ],
@@ -145,7 +145,7 @@
       "generation_config": null
     },
     {
-      "evaluation_id": "hfopenllm_v2/DeepMount00_Llama-3.1-8b-Ita/1773936498.240187",
+      "evaluation_id": "hfopenllm_v2/DeepMount00_Llama-3.1-8b-ITA/1773936498.240187",
       "retrieved_timestamp": "1773936498.240187",
       "source_metadata": {
         "source_name": "HF Open LLM v2",
@@ -177,7 +177,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5365
+            "score": 0.7917
           }
         },
         {
@@ -195,7 +195,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.517
+            "score": 0.5109
           }
         },
         {
@@ -213,7 +213,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1707
+            "score": 0.1088
           }
         },
         {
@@ -231,7 +231,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3062
+            "score": 0.2878
           }
         },
         {
@@ -249,7 +249,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4487
+            "score": 0.4136
           }
         },
         {
@@ -267,7 +267,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.396
+            "score": 0.3876
           }
         }
       ],
diff --git a/data/models/deepseek_deepseek-r1-0528.json b/data/models/deepseek_deepseek-r1-0528.json
index 712c8d82096fdfa393951ac4421e5d6c18ee722d..22f7f1e7159f38877f415a9a6f07905fabcb5d33 100644
--- a/data/models/deepseek_deepseek-r1-0528.json
+++ b/data/models/deepseek_deepseek-r1-0528.json
@@ -10,8 +10,8 @@
   },
   "evaluations": [
     {
-      "evaluation_id": "global-mmlu-lite/deepseek_deepseek-r1-0528/1773936583.743359",
-      "retrieved_timestamp": "1773936583.743359",
+      "evaluation_id": "global-mmlu-lite/deepseek_deepseek-r1-0528/1773936496.366405",
+      "retrieved_timestamp": "1773936496.366405",
       "source_metadata": {
         "source_name": "Global MMLU Lite Leaderboard",
         "source_type": "documentation",
@@ -525,8 +525,8 @@
       "generation_config": null
     },
     {
-      "evaluation_id": "global-mmlu-lite/deepseek_deepseek-r1-0528/1773936496.366405",
-      "retrieved_timestamp": "1773936496.366405",
+      "evaluation_id": "global-mmlu-lite/deepseek_deepseek-r1-0528/1773936583.743359",
+      "retrieved_timestamp": "1773936583.743359",
       "source_metadata": {
         "source_name": "Global MMLU Lite Leaderboard",
         "source_type": "documentation",
diff --git a/data/models/deepseek_deepseek-v3.1.json b/data/models/deepseek_deepseek-v3.1.json
index 52e144fa11c26943b339cba2c9fa28b1d9098c61..28271d97eb42a16e44db35269bdfee0d33d2475a 100644
--- a/data/models/deepseek_deepseek-v3.1.json
+++ b/data/models/deepseek_deepseek-v3.1.json
@@ -7,8 +7,8 @@
   },
   "evaluations": [
     {
-      "evaluation_id": "global-mmlu-lite/deepseek_deepseek-v3.1/1773936496.366405",
-      "retrieved_timestamp": "1773936496.366405",
+      "evaluation_id": "global-mmlu-lite/deepseek_deepseek-v3.1/1773936583.743359",
+      "retrieved_timestamp": "1773936583.743359",
       "source_metadata": {
         "source_name": "Global MMLU Lite Leaderboard",
         "source_type": "documentation",
@@ -522,8 +522,8 @@
       "generation_config": null
     },
     {
-      "evaluation_id": "global-mmlu-lite/deepseek_deepseek-v3.1/1773936583.743359",
-      "retrieved_timestamp": "1773936583.743359",
+      "evaluation_id": "global-mmlu-lite/deepseek_deepseek-v3.1/1773936496.366405",
+      "retrieved_timestamp": "1773936496.366405",
       "source_metadata": {
         "source_name": "Global MMLU Lite Leaderboard",
         "source_type": "documentation",
diff --git a/data/models/dfurman_llama-3-8b-orpo-v0.1.json b/data/models/dfurman_llama-3-8b-orpo-v0.1.json
index a2dcf54fc8dfd61d5182710e882025f5ed46cdab..987b3112f03b34626e0421787b1c9cb2e2b55a46 100644
--- a/data/models/dfurman_llama-3-8b-orpo-v0.1.json
+++ b/data/models/dfurman_llama-3-8b-orpo-v0.1.json
@@ -5,8 +5,8 @@
     "developer": "dfurman",
     "inference_platform": "unknown",
     "additional_details": {
-      "precision": "float16",
-      "architecture": "?",
+      "precision": "bfloat16",
+      "architecture": "LlamaForCausalLM",
       "params_billions": "8.03"
     }
   },
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2835
+            "score": 0.3
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3842
+            "score": 0.3853
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0521
+            "score": 0.0415
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2609
+            "score": 0.2617
           }
         },
         {
@@ -116,7 +116,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3566
+            "score": 0.3579
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2298
+            "score": 0.2281
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3
+            "score": 0.2835
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3853
+            "score": 0.3842
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0415
+            "score": 0.0521
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2617
+            "score": 0.2609
           }
         },
         {
@@ -246,7 +246,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3579
+            "score": 0.3566
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2281
+            "score": 0.2298
           }
         }
       ],
diff --git a/data/models/epistemeai_fireball-meta-llama-3.1-8b-instruct-agent-0.003-128k-code-ds-auto.json b/data/models/epistemeai_fireball-meta-llama-3.1-8b-instruct-agent-0.003-128k-code-ds-auto.json
index 623bd9c2c8bfaa513dd516b6dc8551699ef2135b..34df651aabdc1d7685c9419a18517c0c9ee2b5a2 100644
--- a/data/models/epistemeai_fireball-meta-llama-3.1-8b-instruct-agent-0.003-128k-code-ds-auto.json
+++ b/data/models/epistemeai_fireball-meta-llama-3.1-8b-instruct-agent-0.003-128k-code-ds-auto.json
@@ -5,7 +5,7 @@
     "developer": "EpistemeAI",
     "inference_platform": "unknown",
     "additional_details": {
-      "precision": "bfloat16",
+      "precision": "float16",
       "architecture": "LlamaForCausalLM",
       "params_billions": "8.03"
     }
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7207
+            "score": 0.7305
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.461
+            "score": 0.4649
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1314
+            "score": 0.1397
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2701
+            "score": 0.2659
           }
         },
         {
@@ -116,7 +116,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3432
+            "score": 0.3209
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3354
+            "score": 0.348
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7305
+            "score": 0.7207
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4649
+            "score": 0.461
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1397
+            "score": 0.1314
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2659
+            "score": 0.2701
           }
         },
         {
@@ -246,7 +246,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3209
+            "score": 0.3432
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.348
+            "score": 0.3354
           }
         }
       ],
diff --git a/data/models/etherll_herplete-llm-llama-3.1-8b.json b/data/models/etherll_herplete-llm-llama-3.1-8b.json
index 1f50fb1261d1ec9c67c961ac513392f51c62e5ca..31e2291931d31d5d1deeb312e00cc5de025980fd 100644
--- a/data/models/etherll_herplete-llm-llama-3.1-8b.json
+++ b/data/models/etherll_herplete-llm-llama-3.1-8b.json
@@ -5,7 +5,7 @@
     "developer": "Etherll",
     "inference_platform": "unknown",
     "additional_details": {
-      "precision": "float16",
+      "precision": "bfloat16",
       "architecture": "LlamaForCausalLM",
       "params_billions": "8.03"
     }
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4672
+            "score": 0.6106
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5013
+            "score": 0.5347
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0279
+            "score": 0.1548
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2861
+            "score": 0.3146
           }
         },
         {
@@ -116,7 +116,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.386
+            "score": 0.3991
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3482
+            "score": 0.3752
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6106
+            "score": 0.4672
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5347
+            "score": 0.5013
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1548
+            "score": 0.0279
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3146
+            "score": 0.2861
           }
         },
         {
@@ -246,7 +246,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3991
+            "score": 0.386
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3752
+            "score": 0.3482
           }
         }
       ],
diff --git a/data/models/goekdeniz-guelmez_josiefied-qwen2.5-0.5b-instruct-abliterated-v1.json b/data/models/goekdeniz-guelmez_josiefied-qwen2.5-0.5b-instruct-abliterated-v1.json
index 57e8dc5e192d9afe5d8658b037afb0f25366b018..4e742d684d75a21064054d5a573ca557e7b1e590 100644
--- a/data/models/goekdeniz-guelmez_josiefied-qwen2.5-0.5b-instruct-abliterated-v1.json
+++ b/data/models/goekdeniz-guelmez_josiefied-qwen2.5-0.5b-instruct-abliterated-v1.json
@@ -5,7 +5,7 @@
     "developer": "Goekdeniz-Guelmez",
     "inference_platform": "unknown",
     "additional_details": {
-      "precision": "float16",
+      "precision": "bfloat16",
       "architecture": "Qwen2ForCausalLM",
       "params_billions": "0.63"
     }
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3417
+            "score": 0.3472
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3292
+            "score": 0.3268
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0023
+            "score": 0.0891
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2576
+            "score": 0.2517
           }
         },
         {
@@ -116,7 +116,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3249
+            "score": 0.3262
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1638
+            "score": 0.1641
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3472
+            "score": 0.3417
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3268
+            "score": 0.3292
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0891
+            "score": 0.0023
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2517
+            "score": 0.2576
           }
         },
         {
@@ -246,7 +246,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3262
+            "score": 0.3249
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1641
+            "score": 0.1638
           }
         }
       ],
diff --git a/data/models/google_gemini-2.5-flash.json b/data/models/google_gemini-2.5-flash.json
index a2e65a21393c95ddfc5f4fe71d47a11fac033db8..5eaa67bbe68ea1014fddc37d9abaae6354738cf4 100644
--- a/data/models/google_gemini-2.5-flash.json
+++ b/data/models/google_gemini-2.5-flash.json
@@ -1269,7 +1269,7 @@
       "generation_config": null
     },
     {
-      "evaluation_id": "terminal-bench-2.0/mini-swe-agent__gemini-2.5-flash/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/gemini-cli__gemini-2.5-flash/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -1293,7 +1293,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-11-03",
+          "evaluation_timestamp": "2025-11-04",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -1302,17 +1302,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 17.1,
+            "score": 15.4,
             "uncertainty": {
               "standard_error": {
-                "value": 2.5
+                "value": 2.3
               },
               "num_samples": 435
             }
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Mini-SWE-Agent\" -m \"Gemini 2.5 Flash\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Gemini CLI\" -m \"Gemini 2.5 Flash\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -1329,7 +1329,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Mini-SWE-Agent\" -m \"Gemini 2.5 Flash\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Gemini CLI\" -m \"Gemini 2.5 Flash\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -1343,7 +1343,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/openhands__gemini-2.5-flash/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/mini-swe-agent__gemini-2.5-flash/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -1367,7 +1367,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-11-02",
+          "evaluation_timestamp": "2025-11-03",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -1376,17 +1376,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 16.4,
+            "score": 17.1,
             "uncertainty": {
               "standard_error": {
-                "value": 2.4
+                "value": 2.5
               },
               "num_samples": 435
             }
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"OpenHands\" -m \"Gemini 2.5 Flash\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Mini-SWE-Agent\" -m \"Gemini 2.5 Flash\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -1403,7 +1403,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"OpenHands\" -m \"Gemini 2.5 Flash\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Mini-SWE-Agent\" -m \"Gemini 2.5 Flash\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -1417,7 +1417,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/gemini-cli__gemini-2.5-flash/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/openhands__gemini-2.5-flash/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -1441,7 +1441,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-11-04",
+          "evaluation_timestamp": "2025-11-02",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -1450,17 +1450,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 15.4,
+            "score": 16.4,
             "uncertainty": {
               "standard_error": {
-                "value": 2.3
+                "value": 2.4
               },
               "num_samples": 435
             }
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Gemini CLI\" -m \"Gemini 2.5 Flash\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"OpenHands\" -m \"Gemini 2.5 Flash\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -1477,7 +1477,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Gemini CLI\" -m \"Gemini 2.5 Flash\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"OpenHands\" -m \"Gemini 2.5 Flash\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
diff --git a/data/models/google_gemini-2.5-pro.json b/data/models/google_gemini-2.5-pro.json
index 64bf8e5b0bbd8066e28305bcfb70c0755706abd7..ad69bc6f71351eff92acf181b72bb1ef3d2ca29a 100644
--- a/data/models/google_gemini-2.5-pro.json
+++ b/data/models/google_gemini-2.5-pro.json
@@ -1269,7 +1269,7 @@
       "generation_config": null
     },
     {
-      "evaluation_id": "terminal-bench-2.0/mini-swe-agent__gemini-2.5-pro/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/terminus-2__gemini-2.5-pro/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -1293,7 +1293,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-11-03",
+          "evaluation_timestamp": "2025-10-31",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -1302,17 +1302,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 26.1,
+            "score": 32.6,
             "uncertainty": {
               "standard_error": {
-                "value": 2.5
+                "value": 3.0
               },
               "num_samples": 435
             }
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Mini-SWE-Agent\" -m \"Gemini 2.5 Pro\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"Gemini 2.5 Pro\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -1329,7 +1329,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Mini-SWE-Agent\" -m \"Gemini 2.5 Pro\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"Gemini 2.5 Pro\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -1343,7 +1343,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/gemini-cli__gemini-2.5-pro/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/mini-swe-agent__gemini-2.5-pro/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -1367,7 +1367,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-11-04",
+          "evaluation_timestamp": "2025-11-03",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -1376,17 +1376,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 19.6,
+            "score": 26.1,
             "uncertainty": {
               "standard_error": {
-                "value": 2.9
+                "value": 2.5
               },
               "num_samples": 435
             }
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Gemini CLI\" -m \"Gemini 2.5 Pro\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Mini-SWE-Agent\" -m \"Gemini 2.5 Pro\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -1403,7 +1403,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Gemini CLI\" -m \"Gemini 2.5 Pro\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Mini-SWE-Agent\" -m \"Gemini 2.5 Pro\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -1417,7 +1417,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/terminus-2__gemini-2.5-pro/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/gemini-cli__gemini-2.5-pro/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -1441,7 +1441,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-10-31",
+          "evaluation_timestamp": "2025-11-04",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -1450,17 +1450,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 32.6,
+            "score": 19.6,
             "uncertainty": {
               "standard_error": {
-                "value": 3.0
+                "value": 2.9
               },
               "num_samples": 435
             }
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"Gemini 2.5 Pro\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Gemini CLI\" -m \"Gemini 2.5 Pro\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -1477,7 +1477,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"Gemini 2.5 Pro\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Gemini CLI\" -m \"Gemini 2.5 Pro\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
diff --git a/data/models/google_gemini-3-flash.json b/data/models/google_gemini-3-flash.json
index 96d81804f9403e5af725c031c3f055444b4c7604..6d70bb6cf77fa0c54cb9eb4fa0ff050319c617e5 100644
--- a/data/models/google_gemini-3-flash.json
+++ b/data/models/google_gemini-3-flash.json
@@ -4,13 +4,13 @@
     "id": "google/gemini-3-flash",
     "developer": "Google",
     "additional_details": {
-      "agent_name": "Gemini CLI",
-      "agent_organization": "Google"
+      "agent_name": "Terminus 2",
+      "agent_organization": "Terminal Bench"
     }
   },
   "evaluations": [
     {
-      "evaluation_id": "terminal-bench-2.0/gemini-cli__gemini-3-flash/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/terminus-2__gemini-3-flash/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -34,7 +34,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-12-23",
+          "evaluation_timestamp": "2026-01-07",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -43,17 +43,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 51.0,
+            "score": 51.7,
             "uncertainty": {
               "standard_error": {
-                "value": 3.0
+                "value": 3.1
               },
               "num_samples": 435
             }
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Gemini CLI\" -m \"Gemini 3 Flash\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"Gemini 3 Flash\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -70,7 +70,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Gemini CLI\" -m \"Gemini 3 Flash\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"Gemini 3 Flash\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -84,7 +84,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/terminus-2__gemini-3-flash/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/gemini-cli__gemini-3-flash/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -108,7 +108,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2026-01-07",
+          "evaluation_timestamp": "2026-03-06",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -117,17 +117,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 51.7,
+            "score": 47.4,
             "uncertainty": {
               "standard_error": {
-                "value": 3.1
+                "value": 3.0
               },
               "num_samples": 435
             }
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"Gemini 3 Flash\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Gemini CLI\" -m \"Gemini 3 Flash\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -144,7 +144,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"Gemini 3 Flash\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Gemini CLI\" -m \"Gemini 3 Flash\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -256,7 +256,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2026-03-06",
+          "evaluation_timestamp": "2025-12-23",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -265,7 +265,7 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 47.4,
+            "score": 51.0,
             "uncertainty": {
               "standard_error": {
                 "value": 3.0
diff --git a/data/models/google_gemini-3-pro-preview.json b/data/models/google_gemini-3-pro-preview.json
index 7edffa00c381bc6c2a68a0a203fbe30120c52254..fdc61e428a001318c9e1c391ace7515f63b19817 100644
--- a/data/models/google_gemini-3-pro-preview.json
+++ b/data/models/google_gemini-3-pro-preview.json
@@ -4,13 +4,13 @@
     "id": "google/gemini-3-pro-preview",
     "developer": "Google",
     "additional_details": {
-      "agent_name": "OpenAI Solo",
-      "agent_framework": "openai_solo"
+      "agent_name": "SmolAgents Code",
+      "agent_framework": "smolagents_code"
     }
   },
   "evaluations": [
     {
-      "evaluation_id": "appworld/test_normal/openai-solo__google_gemini-3-pro-preview/1774263615.0201504",
+      "evaluation_id": "appworld/test_normal/smolagents-code__google_gemini-3-pro-preview/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -42,23 +42,23 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.582,
+            "score": 0.13,
             "uncertainty": {
               "num_samples": 100
             },
             "details": {
-              "average_agent_cost": "8.7",
-              "total_run_cost": "869.55",
-              "average_steps": "33.49",
-              "percent_finished": "0.98"
+              "average_agent_cost": "2.54",
+              "total_run_cost": "254.25",
+              "average_steps": "49.13",
+              "percent_finished": "0.71"
             }
           },
           "generation_config": {
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "OpenAI Solo",
-                  "agent_framework": "openai_solo"
+                  "agent_name": "SmolAgents Code",
+                  "agent_framework": "smolagents_code"
                 }
               }
             }
@@ -70,15 +70,15 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "OpenAI Solo",
-              "agent_framework": "openai_solo"
+              "agent_name": "SmolAgents Code",
+              "agent_framework": "smolagents_code"
             }
           }
         }
       }
     },
     {
-      "evaluation_id": "browsecompplus/claude-code-cli__google_gemini-3-pro-preview/1774263615.0201504",
+      "evaluation_id": "appworld/test_normal/litellm-tool-calling__google_gemini-3-pro-preview/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -91,42 +91,42 @@
         "name": "exgentic",
         "version": "0.1.0"
       },
-      "benchmark": "browsecompplus",
+      "benchmark": "appworld_test_normal",
       "evaluation_results": [
         {
-          "evaluation_name": "browsecompplus",
+          "evaluation_name": "appworld/test_normal",
           "source_data": {
-            "dataset_name": "browsecompplus",
+            "dataset_name": "appworld/test_normal",
             "source_type": "url",
             "url": [
               "https://github.com/Exgentic/exgentic"
             ]
           },
           "metric_config": {
-            "evaluation_description": "BrowseCompPlus benchmark evaluation",
+            "evaluation_description": "AppWorld benchmark evaluation (test_normal subset)",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.51,
+            "score": 0.505,
             "uncertainty": {
               "num_samples": 100
             },
             "details": {
-              "average_agent_cost": "2.85",
-              "total_run_cost": "284.68",
-              "average_steps": "22.88",
-              "percent_finished": "0.7"
+              "average_agent_cost": "1.88",
+              "total_run_cost": "188.19",
+              "average_steps": "21.76",
+              "percent_finished": "0.99"
             }
           },
           "generation_config": {
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "Claude Code CLI",
-                  "agent_framework": "claude_code"
+                  "agent_name": "LiteLLM Tool Calling",
+                  "agent_framework": "tool_calling"
                 }
               }
             }
@@ -138,15 +138,15 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "Claude Code CLI",
-              "agent_framework": "claude_code"
+              "agent_name": "LiteLLM Tool Calling",
+              "agent_framework": "tool_calling"
             }
           }
         }
       }
     },
     {
-      "evaluation_id": "appworld/test_normal/litellm-tool-calling__google_gemini-3-pro-preview/1774263615.0201504",
+      "evaluation_id": "appworld/test_normal/openai-solo__google_gemini-3-pro-preview/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -178,23 +178,23 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.505,
+            "score": 0.582,
             "uncertainty": {
               "num_samples": 100
             },
             "details": {
-              "average_agent_cost": "1.88",
-              "total_run_cost": "188.19",
-              "average_steps": "21.76",
-              "percent_finished": "0.99"
+              "average_agent_cost": "8.7",
+              "total_run_cost": "869.55",
+              "average_steps": "33.49",
+              "percent_finished": "0.98"
             }
           },
           "generation_config": {
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "LiteLLM Tool Calling",
-                  "agent_framework": "tool_calling"
+                  "agent_name": "OpenAI Solo",
+                  "agent_framework": "openai_solo"
                 }
               }
             }
@@ -206,15 +206,15 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "LiteLLM Tool Calling",
-              "agent_framework": "tool_calling"
+              "agent_name": "OpenAI Solo",
+              "agent_framework": "openai_solo"
             }
           }
         }
       }
     },
     {
-      "evaluation_id": "appworld/test_normal/claude-code-cli__google_gemini-3-pro-preview/1774263615.0201504",
+      "evaluation_id": "appworld/test_normal/litellm-tool-calling-with-shortlisting__google_gemini-3-pro-preview/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -246,23 +246,23 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.36,
+            "score": 0.55,
             "uncertainty": {
               "num_samples": 100
             },
             "details": {
-              "average_agent_cost": "3.11",
-              "total_run_cost": "310.55",
-              "average_steps": "38.01",
-              "percent_finished": "0.86"
+              "average_agent_cost": "1.3",
+              "total_run_cost": "130.49",
+              "average_steps": "22.59",
+              "percent_finished": "1.0"
             }
           },
           "generation_config": {
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "Claude Code CLI",
-                  "agent_framework": "claude_code"
+                  "agent_name": "LiteLLM Tool Calling with Shortlisting",
+                  "agent_framework": "tool_calling_with_shortlisting"
                 }
               }
             }
@@ -274,15 +274,15 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "Claude Code CLI",
-              "agent_framework": "claude_code"
+              "agent_name": "LiteLLM Tool Calling with Shortlisting",
+              "agent_framework": "tool_calling_with_shortlisting"
             }
           }
         }
       }
     },
     {
-      "evaluation_id": "appworld/test_normal/smolagents-code__google_gemini-3-pro-preview/1774263615.0201504",
+      "evaluation_id": "browsecompplus/smolagents-code__google_gemini-3-pro-preview/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -295,34 +295,34 @@
         "name": "exgentic",
         "version": "0.1.0"
       },
-      "benchmark": "appworld_test_normal",
+      "benchmark": "browsecompplus",
       "evaluation_results": [
         {
-          "evaluation_name": "appworld/test_normal",
+          "evaluation_name": "browsecompplus",
           "source_data": {
-            "dataset_name": "appworld/test_normal",
+            "dataset_name": "browsecompplus",
             "source_type": "url",
             "url": [
               "https://github.com/Exgentic/exgentic"
             ]
           },
           "metric_config": {
-            "evaluation_description": "AppWorld benchmark evaluation (test_normal subset)",
+            "evaluation_description": "BrowseCompPlus benchmark evaluation",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.13,
+            "score": 0.57,
             "uncertainty": {
               "num_samples": 100
             },
             "details": {
-              "average_agent_cost": "2.54",
-              "total_run_cost": "254.25",
-              "average_steps": "49.13",
-              "percent_finished": "0.71"
+              "average_agent_cost": "2.39",
+              "total_run_cost": "239.0",
+              "average_steps": "29.63",
+              "percent_finished": "0.69"
             }
           },
           "generation_config": {
@@ -350,7 +350,7 @@
       }
     },
     {
-      "evaluation_id": "appworld/test_normal/litellm-tool-calling-with-shortlisting__google_gemini-3-pro-preview/1774263615.0201504",
+      "evaluation_id": "appworld/test_normal/claude-code-cli__google_gemini-3-pro-preview/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -382,23 +382,23 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.55,
+            "score": 0.36,
             "uncertainty": {
               "num_samples": 100
             },
             "details": {
-              "average_agent_cost": "1.3",
-              "total_run_cost": "130.49",
-              "average_steps": "22.59",
-              "percent_finished": "1.0"
+              "average_agent_cost": "3.11",
+              "total_run_cost": "310.55",
+              "average_steps": "38.01",
+              "percent_finished": "0.86"
             }
           },
           "generation_config": {
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "LiteLLM Tool Calling with Shortlisting",
-                  "agent_framework": "tool_calling_with_shortlisting"
+                  "agent_name": "Claude Code CLI",
+                  "agent_framework": "claude_code"
                 }
               }
             }
@@ -410,15 +410,15 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "LiteLLM Tool Calling with Shortlisting",
-              "agent_framework": "tool_calling_with_shortlisting"
+              "agent_name": "Claude Code CLI",
+              "agent_framework": "claude_code"
             }
           }
         }
       }
     },
     {
-      "evaluation_id": "browsecompplus/smolagents-code__google_gemini-3-pro-preview/1774263615.0201504",
+      "evaluation_id": "browsecompplus/claude-code-cli__google_gemini-3-pro-preview/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -450,23 +450,23 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.57,
+            "score": 0.51,
             "uncertainty": {
               "num_samples": 100
             },
             "details": {
-              "average_agent_cost": "2.39",
-              "total_run_cost": "239.0",
-              "average_steps": "29.63",
-              "percent_finished": "0.69"
+              "average_agent_cost": "2.85",
+              "total_run_cost": "284.68",
+              "average_steps": "22.88",
+              "percent_finished": "0.7"
             }
           },
           "generation_config": {
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "SmolAgents Code",
-                  "agent_framework": "smolagents_code"
+                  "agent_name": "Claude Code CLI",
+                  "agent_framework": "claude_code"
                 }
               }
             }
@@ -478,15 +478,15 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "SmolAgents Code",
-              "agent_framework": "smolagents_code"
+              "agent_name": "Claude Code CLI",
+              "agent_framework": "claude_code"
             }
           }
         }
       }
     },
     {
-      "evaluation_id": "browsecompplus/litellm-tool-calling__google_gemini-3-pro-preview/1774263615.0201504",
+      "evaluation_id": "browsecompplus/openai-solo__google_gemini-3-pro-preview/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -518,23 +518,23 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.48,
+            "score": 0.3333,
             "uncertainty": {
-              "num_samples": 100
+              "num_samples": 99
             },
             "details": {
-              "average_agent_cost": "0.44",
-              "total_run_cost": "44.18",
-              "average_steps": "7.85",
-              "percent_finished": "0.99"
+              "average_agent_cost": "0.64",
+              "total_run_cost": "63.79",
+              "average_steps": "8.45",
+              "percent_finished": "0.6061"
             }
           },
           "generation_config": {
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "LiteLLM Tool Calling",
-                  "agent_framework": "tool_calling"
+                  "agent_name": "OpenAI Solo",
+                  "agent_framework": "openai_solo"
                 }
               }
             }
@@ -546,8 +546,8 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "LiteLLM Tool Calling",
-              "agent_framework": "tool_calling"
+              "agent_name": "OpenAI Solo",
+              "agent_framework": "openai_solo"
             }
           }
         }
@@ -622,7 +622,7 @@
       }
     },
     {
-      "evaluation_id": "browsecompplus/openai-solo__google_gemini-3-pro-preview/1774263615.0201504",
+      "evaluation_id": "browsecompplus/litellm-tool-calling__google_gemini-3-pro-preview/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -654,23 +654,23 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3333,
+            "score": 0.48,
             "uncertainty": {
-              "num_samples": 99
+              "num_samples": 100
             },
             "details": {
-              "average_agent_cost": "0.64",
-              "total_run_cost": "63.79",
-              "average_steps": "8.45",
-              "percent_finished": "0.6061"
+              "average_agent_cost": "0.44",
+              "total_run_cost": "44.18",
+              "average_steps": "7.85",
+              "percent_finished": "0.99"
             }
           },
           "generation_config": {
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "OpenAI Solo",
-                  "agent_framework": "openai_solo"
+                  "agent_name": "LiteLLM Tool Calling",
+                  "agent_framework": "tool_calling"
                 }
               }
             }
@@ -682,8 +682,8 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "OpenAI Solo",
-              "agent_framework": "openai_solo"
+              "agent_name": "LiteLLM Tool Calling",
+              "agent_framework": "tool_calling"
             }
           }
         }
@@ -1720,7 +1720,7 @@
       "generation_config": null
     },
     {
-      "evaluation_id": "swe-bench/litellm-tool-calling__google_gemini-3-pro-preview/1774263615.0201504",
+      "evaluation_id": "swe-bench/litellm-tool-calling-with-shortlisting__google_gemini-3-pro-preview/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -1767,8 +1767,8 @@
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "LiteLLM Tool Calling",
-                  "agent_framework": "tool_calling"
+                  "agent_name": "LiteLLM Tool Calling with Shortlisting",
+                  "agent_framework": "tool_calling_with_shortlisting"
                 }
               }
             }
@@ -1780,15 +1780,15 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "LiteLLM Tool Calling",
-              "agent_framework": "tool_calling"
+              "agent_name": "LiteLLM Tool Calling with Shortlisting",
+              "agent_framework": "tool_calling_with_shortlisting"
             }
           }
         }
       }
     },
     {
-      "evaluation_id": "swe-bench/openai-solo__google_gemini-3-pro-preview/1774263615.0201504",
+      "evaluation_id": "swe-bench/smolagents-code__google_gemini-3-pro-preview/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -1820,14 +1820,14 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7234,
+            "score": 0.7576,
             "uncertainty": {
-              "num_samples": 94
+              "num_samples": 99
             },
             "details": {
-              "average_agent_cost": "1.58",
-              "total_run_cost": "148.44",
-              "average_steps": "32.36",
+              "average_agent_cost": "2.21",
+              "total_run_cost": "218.76",
+              "average_steps": "38.1",
               "percent_finished": "1.0"
             }
           },
@@ -1835,8 +1835,8 @@
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "OpenAI Solo",
-                  "agent_framework": "openai_solo"
+                  "agent_name": "SmolAgents Code",
+                  "agent_framework": "smolagents_code"
                 }
               }
             }
@@ -1848,15 +1848,15 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "OpenAI Solo",
-              "agent_framework": "openai_solo"
+              "agent_name": "SmolAgents Code",
+              "agent_framework": "smolagents_code"
             }
           }
         }
       }
     },
     {
-      "evaluation_id": "swe-bench/smolagents-code__google_gemini-3-pro-preview/1774263615.0201504",
+      "evaluation_id": "swe-bench/openai-solo__google_gemini-3-pro-preview/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -1888,14 +1888,14 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7576,
+            "score": 0.7234,
             "uncertainty": {
-              "num_samples": 99
+              "num_samples": 94
             },
             "details": {
-              "average_agent_cost": "2.21",
-              "total_run_cost": "218.76",
-              "average_steps": "38.1",
+              "average_agent_cost": "1.58",
+              "total_run_cost": "148.44",
+              "average_steps": "32.36",
               "percent_finished": "1.0"
             }
           },
@@ -1903,8 +1903,8 @@
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "SmolAgents Code",
-                  "agent_framework": "smolagents_code"
+                  "agent_name": "OpenAI Solo",
+                  "agent_framework": "openai_solo"
                 }
               }
             }
@@ -1916,8 +1916,8 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "SmolAgents Code",
-              "agent_framework": "smolagents_code"
+              "agent_name": "OpenAI Solo",
+              "agent_framework": "openai_solo"
             }
           }
         }
@@ -1992,7 +1992,7 @@
       }
     },
     {
-      "evaluation_id": "swe-bench/litellm-tool-calling-with-shortlisting__google_gemini-3-pro-preview/1774263615.0201504",
+      "evaluation_id": "swe-bench/litellm-tool-calling__google_gemini-3-pro-preview/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -2039,8 +2039,8 @@
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "LiteLLM Tool Calling with Shortlisting",
-                  "agent_framework": "tool_calling_with_shortlisting"
+                  "agent_name": "LiteLLM Tool Calling",
+                  "agent_framework": "tool_calling"
                 }
               }
             }
@@ -2052,15 +2052,15 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "LiteLLM Tool Calling with Shortlisting",
-              "agent_framework": "tool_calling_with_shortlisting"
+              "agent_name": "LiteLLM Tool Calling",
+              "agent_framework": "tool_calling"
             }
           }
         }
       }
     },
     {
-      "evaluation_id": "tau-bench-2/airline/claude-code-cli__google_gemini-3-pro-preview/1774263615.0201504",
+      "evaluation_id": "tau-bench-2/airline/litellm-tool-calling__google_gemini-3-pro-preview/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -2097,9 +2097,9 @@
               "num_samples": 50
             },
             "details": {
-              "average_agent_cost": "0.34",
-              "total_run_cost": "17.45",
-              "average_steps": "12.62",
+              "average_agent_cost": "0.16",
+              "total_run_cost": "8.48",
+              "average_steps": "10.14",
               "percent_finished": "1.0"
             }
           },
@@ -2107,8 +2107,8 @@
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "Claude Code CLI",
-                  "agent_framework": "claude_code"
+                  "agent_name": "LiteLLM Tool Calling",
+                  "agent_framework": "tool_calling"
                 }
               }
             }
@@ -2120,15 +2120,15 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "Claude Code CLI",
-              "agent_framework": "claude_code"
+              "agent_name": "LiteLLM Tool Calling",
+              "agent_framework": "tool_calling"
             }
           }
         }
       }
     },
     {
-      "evaluation_id": "tau-bench-2/airline/openai-solo__google_gemini-3-pro-preview/1774263615.0201504",
+      "evaluation_id": "tau-bench-2/airline/claude-code-cli__google_gemini-3-pro-preview/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -2160,14 +2160,14 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.62,
+            "score": 0.7,
             "uncertainty": {
               "num_samples": 50
             },
             "details": {
-              "average_agent_cost": "0.21",
-              "total_run_cost": "11.18",
-              "average_steps": "10.9",
+              "average_agent_cost": "0.34",
+              "total_run_cost": "17.45",
+              "average_steps": "12.62",
               "percent_finished": "1.0"
             }
           },
@@ -2175,8 +2175,8 @@
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "OpenAI Solo",
-                  "agent_framework": "openai_solo"
+                  "agent_name": "Claude Code CLI",
+                  "agent_framework": "claude_code"
                 }
               }
             }
@@ -2188,15 +2188,15 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "OpenAI Solo",
-              "agent_framework": "openai_solo"
+              "agent_name": "Claude Code CLI",
+              "agent_framework": "claude_code"
             }
           }
         }
       }
     },
     {
-      "evaluation_id": "tau-bench-2/airline/litellm-tool-calling-with-shortlisting__google_gemini-3-pro-preview/1774263615.0201504",
+      "evaluation_id": "tau-bench-2/airline/openai-solo__google_gemini-3-pro-preview/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -2228,14 +2228,14 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7,
+            "score": 0.62,
             "uncertainty": {
               "num_samples": 50
             },
             "details": {
-              "average_agent_cost": "0.16",
-              "total_run_cost": "8.48",
-              "average_steps": "10.14",
+              "average_agent_cost": "0.21",
+              "total_run_cost": "11.18",
+              "average_steps": "10.9",
               "percent_finished": "1.0"
             }
           },
@@ -2243,8 +2243,8 @@
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "LiteLLM Tool Calling with Shortlisting",
-                  "agent_framework": "tool_calling_with_shortlisting"
+                  "agent_name": "OpenAI Solo",
+                  "agent_framework": "openai_solo"
                 }
               }
             }
@@ -2256,15 +2256,15 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "LiteLLM Tool Calling with Shortlisting",
-              "agent_framework": "tool_calling_with_shortlisting"
+              "agent_name": "OpenAI Solo",
+              "agent_framework": "openai_solo"
             }
           }
         }
       }
     },
     {
-      "evaluation_id": "tau-bench-2/airline/litellm-tool-calling__google_gemini-3-pro-preview/1774263615.0201504",
+      "evaluation_id": "tau-bench-2/airline/litellm-tool-calling-with-shortlisting__google_gemini-3-pro-preview/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -2311,8 +2311,8 @@
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "LiteLLM Tool Calling",
-                  "agent_framework": "tool_calling"
+                  "agent_name": "LiteLLM Tool Calling with Shortlisting",
+                  "agent_framework": "tool_calling_with_shortlisting"
                 }
               }
             }
@@ -2324,15 +2324,15 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "LiteLLM Tool Calling",
-              "agent_framework": "tool_calling"
+              "agent_name": "LiteLLM Tool Calling with Shortlisting",
+              "agent_framework": "tool_calling_with_shortlisting"
             }
           }
         }
       }
     },
     {
-      "evaluation_id": "tau-bench-2/retail/smolagents-code__google_gemini-3-pro-preview/1774263615.0201504",
+      "evaluation_id": "tau-bench-2/airline/smolagents-code__google_gemini-3-pro-preview/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -2345,33 +2345,33 @@
         "name": "exgentic",
         "version": "0.1.0"
       },
-      "benchmark": "tau-bench-2_retail",
+      "benchmark": "tau-bench-2_airline",
       "evaluation_results": [
         {
-          "evaluation_name": "tau-bench-2/retail",
+          "evaluation_name": "tau-bench-2/airline",
           "source_data": {
-            "dataset_name": "tau-bench-2/retail",
+            "dataset_name": "tau-bench-2/airline",
             "source_type": "url",
             "url": [
               "https://github.com/Exgentic/exgentic"
             ]
           },
           "metric_config": {
-            "evaluation_description": "Tau Bench 2 benchmark evaluation (retail subset)",
+            "evaluation_description": "Tau Bench 2 benchmark evaluation (airline subset)",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7576,
+            "score": 0.68,
             "uncertainty": {
-              "num_samples": 100
+              "num_samples": 50
             },
             "details": {
-              "average_agent_cost": "0.21",
-              "total_run_cost": "21.43",
-              "average_steps": "11.3",
+              "average_agent_cost": "0.2",
+              "total_run_cost": "10.29",
+              "average_steps": "12.28",
               "percent_finished": "1.0"
             }
           },
@@ -2468,7 +2468,7 @@
       }
     },
     {
-      "evaluation_id": "tau-bench-2/retail/claude-code-cli__google_gemini-3-pro-preview/1774263615.0201504",
+      "evaluation_id": "tau-bench-2/retail/smolagents-code__google_gemini-3-pro-preview/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -2500,14 +2500,14 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7805,
+            "score": 0.7576,
             "uncertainty": {
               "num_samples": 100
             },
             "details": {
-              "average_agent_cost": "0.19",
-              "total_run_cost": "19.38",
-              "average_steps": "11.18",
+              "average_agent_cost": "0.21",
+              "total_run_cost": "21.43",
+              "average_steps": "11.3",
               "percent_finished": "1.0"
             }
           },
@@ -2515,8 +2515,8 @@
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "Claude Code CLI",
-                  "agent_framework": "claude_code"
+                  "agent_name": "SmolAgents Code",
+                  "agent_framework": "smolagents_code"
                 }
               }
             }
@@ -2528,8 +2528,8 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "Claude Code CLI",
-              "agent_framework": "claude_code"
+              "agent_name": "SmolAgents Code",
+              "agent_framework": "smolagents_code"
             }
           }
         }
@@ -2672,7 +2672,7 @@
       }
     },
     {
-      "evaluation_id": "tau-bench-2/airline/smolagents-code__google_gemini-3-pro-preview/1774263615.0201504",
+      "evaluation_id": "tau-bench-2/retail/claude-code-cli__google_gemini-3-pro-preview/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -2685,33 +2685,33 @@
         "name": "exgentic",
         "version": "0.1.0"
       },
-      "benchmark": "tau-bench-2_airline",
+      "benchmark": "tau-bench-2_retail",
       "evaluation_results": [
         {
-          "evaluation_name": "tau-bench-2/airline",
+          "evaluation_name": "tau-bench-2/retail",
           "source_data": {
-            "dataset_name": "tau-bench-2/airline",
+            "dataset_name": "tau-bench-2/retail",
             "source_type": "url",
             "url": [
               "https://github.com/Exgentic/exgentic"
             ]
           },
           "metric_config": {
-            "evaluation_description": "Tau Bench 2 benchmark evaluation (airline subset)",
+            "evaluation_description": "Tau Bench 2 benchmark evaluation (retail subset)",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.68,
+            "score": 0.7805,
             "uncertainty": {
-              "num_samples": 50
+              "num_samples": 100
             },
             "details": {
-              "average_agent_cost": "0.2",
-              "total_run_cost": "10.29",
-              "average_steps": "12.28",
+              "average_agent_cost": "0.19",
+              "total_run_cost": "19.38",
+              "average_steps": "11.18",
               "percent_finished": "1.0"
             }
           },
@@ -2719,8 +2719,8 @@
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "SmolAgents Code",
-                  "agent_framework": "smolagents_code"
+                  "agent_name": "Claude Code CLI",
+                  "agent_framework": "claude_code"
                 }
               }
             }
@@ -2732,15 +2732,15 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "SmolAgents Code",
-              "agent_framework": "smolagents_code"
+              "agent_name": "Claude Code CLI",
+              "agent_framework": "claude_code"
             }
           }
         }
       }
     },
     {
-      "evaluation_id": "tau-bench-2/telecom/openai-solo__google_gemini-3-pro-preview/1774263615.0201504",
+      "evaluation_id": "tau-bench-2/telecom/claude-code-cli__google_gemini-3-pro-preview/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -2772,23 +2772,23 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.8876,
+            "score": 0.6852,
             "uncertainty": {
               "num_samples": 100
             },
             "details": {
-              "average_agent_cost": "0.54",
-              "total_run_cost": "58.29",
-              "average_steps": "10.82",
-              "percent_finished": "0.89"
+              "average_agent_cost": "0.21",
+              "total_run_cost": "25.48",
+              "average_steps": "9.9",
+              "percent_finished": "1.0"
             }
           },
           "generation_config": {
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "OpenAI Solo",
-                  "agent_framework": "openai_solo"
+                  "agent_name": "Claude Code CLI",
+                  "agent_framework": "claude_code"
                 }
               }
             }
@@ -2800,15 +2800,15 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "OpenAI Solo",
-              "agent_framework": "openai_solo"
+              "agent_name": "Claude Code CLI",
+              "agent_framework": "claude_code"
             }
           }
         }
       }
     },
     {
-      "evaluation_id": "tau-bench-2/telecom/smolagents-code__google_gemini-3-pro-preview/1774263615.0201504",
+      "evaluation_id": "tau-bench-2/telecom/litellm-tool-calling__google_gemini-3-pro-preview/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -2840,14 +2840,14 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.88,
+            "score": 0.73,
             "uncertainty": {
               "num_samples": 100
             },
             "details": {
-              "average_agent_cost": "0.35",
-              "total_run_cost": "40.25",
-              "average_steps": "12.71",
+              "average_agent_cost": "0.3",
+              "total_run_cost": "36.75",
+              "average_steps": "14.84",
               "percent_finished": "1.0"
             }
           },
@@ -2855,8 +2855,8 @@
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "SmolAgents Code",
-                  "agent_framework": "smolagents_code"
+                  "agent_name": "LiteLLM Tool Calling",
+                  "agent_framework": "tool_calling"
                 }
               }
             }
@@ -2868,15 +2868,15 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "SmolAgents Code",
-              "agent_framework": "smolagents_code"
+              "agent_name": "LiteLLM Tool Calling",
+              "agent_framework": "tool_calling"
             }
           }
         }
       }
     },
     {
-      "evaluation_id": "tau-bench-2/telecom/claude-code-cli__google_gemini-3-pro-preview/1774263615.0201504",
+      "evaluation_id": "tau-bench-2/telecom/smolagents-code__google_gemini-3-pro-preview/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -2908,14 +2908,14 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6852,
+            "score": 0.88,
             "uncertainty": {
               "num_samples": 100
             },
             "details": {
-              "average_agent_cost": "0.21",
-              "total_run_cost": "25.48",
-              "average_steps": "9.9",
+              "average_agent_cost": "0.35",
+              "total_run_cost": "40.25",
+              "average_steps": "12.71",
               "percent_finished": "1.0"
             }
           },
@@ -2923,8 +2923,8 @@
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "Claude Code CLI",
-                  "agent_framework": "claude_code"
+                  "agent_name": "SmolAgents Code",
+                  "agent_framework": "smolagents_code"
                 }
               }
             }
@@ -2936,15 +2936,15 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "Claude Code CLI",
-              "agent_framework": "claude_code"
+              "agent_name": "SmolAgents Code",
+              "agent_framework": "smolagents_code"
             }
           }
         }
       }
     },
     {
-      "evaluation_id": "tau-bench-2/telecom/litellm-tool-calling-with-shortlisting__google_gemini-3-pro-preview/1774263615.0201504",
+      "evaluation_id": "tau-bench-2/telecom/openai-solo__google_gemini-3-pro-preview/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -2976,23 +2976,23 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.73,
+            "score": 0.8876,
             "uncertainty": {
               "num_samples": 100
             },
             "details": {
-              "average_agent_cost": "0.3",
-              "total_run_cost": "36.75",
-              "average_steps": "14.84",
-              "percent_finished": "1.0"
+              "average_agent_cost": "0.54",
+              "total_run_cost": "58.29",
+              "average_steps": "10.82",
+              "percent_finished": "0.89"
             }
           },
           "generation_config": {
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "LiteLLM Tool Calling with Shortlisting",
-                  "agent_framework": "tool_calling_with_shortlisting"
+                  "agent_name": "OpenAI Solo",
+                  "agent_framework": "openai_solo"
                 }
               }
             }
@@ -3004,15 +3004,15 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "LiteLLM Tool Calling with Shortlisting",
-              "agent_framework": "tool_calling_with_shortlisting"
+              "agent_name": "OpenAI Solo",
+              "agent_framework": "openai_solo"
             }
           }
         }
       }
     },
     {
-      "evaluation_id": "tau-bench-2/telecom/litellm-tool-calling__google_gemini-3-pro-preview/1774263615.0201504",
+      "evaluation_id": "tau-bench-2/telecom/litellm-tool-calling-with-shortlisting__google_gemini-3-pro-preview/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -3059,8 +3059,8 @@
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "LiteLLM Tool Calling",
-                  "agent_framework": "tool_calling"
+                  "agent_name": "LiteLLM Tool Calling with Shortlisting",
+                  "agent_framework": "tool_calling_with_shortlisting"
                 }
               }
             }
@@ -3072,8 +3072,8 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "LiteLLM Tool Calling",
-              "agent_framework": "tool_calling"
+              "agent_name": "LiteLLM Tool Calling with Shortlisting",
+              "agent_framework": "tool_calling_with_shortlisting"
             }
           }
         }
diff --git a/data/models/google_gemini-3-pro.json b/data/models/google_gemini-3-pro.json
index 01e84795b0cee23dd2bc66c9e2c84da542f9aae9..3f400faaadf810745e49d759105088e642b483cc 100644
--- a/data/models/google_gemini-3-pro.json
+++ b/data/models/google_gemini-3-pro.json
@@ -84,7 +84,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/terminus-2__gemini-3-pro/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/ante__gemini-3-pro/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -108,7 +108,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-11-21",
+          "evaluation_timestamp": "2026-01-06",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -117,17 +117,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 56.9,
+            "score": 69.4,
             "uncertainty": {
               "standard_error": {
-                "value": 2.5
+                "value": 2.1
               },
               "num_samples": 435
             }
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"Gemini 3 Pro\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Ante\" -m \"Gemini 3 Pro\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -144,7 +144,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"Gemini 3 Pro\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Ante\" -m \"Gemini 3 Pro\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -158,7 +158,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/codebrain-1__gemini-3-pro/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/droid__gemini-3-pro/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -182,7 +182,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2026-02-05",
+          "evaluation_timestamp": "2025-12-24",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -191,17 +191,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 62.2,
+            "score": 61.1,
             "uncertainty": {
               "standard_error": {
-                "value": 2.6
+                "value": 2.8
               },
               "num_samples": 435
             }
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"CodeBrain-1\" -m \"Gemini 3 Pro\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Droid\" -m \"Gemini 3 Pro\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -218,7 +218,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"CodeBrain-1\" -m \"Gemini 3 Pro\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Droid\" -m \"Gemini 3 Pro\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -232,7 +232,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/ii-agent__gemini-3-pro/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/codebrain-1__gemini-3-pro/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -256,7 +256,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-12-23",
+          "evaluation_timestamp": "2026-02-05",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -265,17 +265,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 61.8,
+            "score": 62.2,
             "uncertainty": {
               "standard_error": {
-                "value": 2.8
+                "value": 2.6
               },
               "num_samples": 435
             }
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"II-Agent\" -m \"Gemini 3 Pro\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"CodeBrain-1\" -m \"Gemini 3 Pro\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -292,7 +292,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"II-Agent\" -m \"Gemini 3 Pro\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"CodeBrain-1\" -m \"Gemini 3 Pro\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -306,7 +306,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/ante__gemini-3-pro/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/ii-agent__gemini-3-pro/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -330,7 +330,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2026-01-06",
+          "evaluation_timestamp": "2025-12-23",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -339,17 +339,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 69.4,
+            "score": 61.8,
             "uncertainty": {
               "standard_error": {
-                "value": 2.1
+                "value": 2.8
               },
               "num_samples": 435
             }
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Ante\" -m \"Gemini 3 Pro\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"II-Agent\" -m \"Gemini 3 Pro\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -366,7 +366,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Ante\" -m \"Gemini 3 Pro\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"II-Agent\" -m \"Gemini 3 Pro\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -380,7 +380,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/droid__gemini-3-pro/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/letta-code__gemini-3-pro/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -404,7 +404,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-12-24",
+          "evaluation_timestamp": "2025-12-17",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -413,17 +413,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 61.1,
+            "score": 56.0,
             "uncertainty": {
               "standard_error": {
-                "value": 2.8
+                "value": 3.0
               },
               "num_samples": 435
             }
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Droid\" -m \"Gemini 3 Pro\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Letta Code\" -m \"Gemini 3 Pro\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -440,7 +440,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Droid\" -m \"Gemini 3 Pro\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Letta Code\" -m \"Gemini 3 Pro\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -454,7 +454,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/letta-code__gemini-3-pro/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/terminus-2__gemini-3-pro/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -478,7 +478,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-12-17",
+          "evaluation_timestamp": "2025-11-21",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -487,17 +487,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 56.0,
+            "score": 56.9,
             "uncertainty": {
               "standard_error": {
-                "value": 3.0
+                "value": 2.5
               },
               "num_samples": 435
             }
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Letta Code\" -m \"Gemini 3 Pro\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"Gemini 3 Pro\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -514,7 +514,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Letta Code\" -m \"Gemini 3 Pro\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"Gemini 3 Pro\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
diff --git a/data/models/google_gemini_3_pro.json b/data/models/google_gemini_3_pro.json
index 8f4f634348fdc10ff492053d2a6241085b80ddd7..104ce8e17e340df7c6fe6dc4bc1f7866f9c1cc71 100644
--- a/data/models/google_gemini_3_pro.json
+++ b/data/models/google_gemini_3_pro.json
@@ -6,78 +6,6 @@
     "inference_platform": "unknown"
   },
   "evaluations": [
-    {
-      "evaluation_id": "ace/google_gemini-3-pro/1773260200",
-      "retrieved_timestamp": "1773260200",
-      "source_metadata": {
-        "source_name": "Mercor ACE Leaderboard",
-        "source_type": "evaluation_run",
-        "source_organization_name": "Mercor",
-        "source_organization_url": "https://www.mercor.com",
-        "evaluator_relationship": "first_party"
-      },
-      "eval_library": {
-        "name": "archipelago",
-        "version": "1.0.0"
-      },
-      "benchmark": "ace",
-      "evaluation_results": [
-        {
-          "evaluation_name": "Overall Score",
-          "source_data": {
-            "dataset_name": "ace",
-            "source_type": "hf_dataset",
-            "hf_repo": "Mercor/ACE"
-          },
-          "metric_config": {
-            "evaluation_description": "Overall ACE score (paper snapshot, approximate).",
-            "lower_is_better": false,
-            "score_type": "continuous",
-            "min_score": 0,
-            "max_score": 1
-          },
-          "score_details": {
-            "score": 0.47
-          },
-          "generation_config": {
-            "additional_details": {
-              "run_setting": "High",
-              "value_quality": "approximate"
-            }
-          }
-        },
-        {
-          "evaluation_name": "Gaming Score",
-          "source_data": {
-            "dataset_name": "ace",
-            "source_type": "hf_dataset",
-            "hf_repo": "Mercor/ACE"
-          },
-          "metric_config": {
-            "evaluation_description": "Gaming domain score.",
-            "lower_is_better": false,
-            "score_type": "continuous",
-            "min_score": 0,
-            "max_score": 1
-          },
-          "score_details": {
-            "score": 0.509
-          },
-          "generation_config": {
-            "additional_details": {
-              "run_setting": "High"
-            }
-          }
-        }
-      ],
-      "detailed_evaluation_results": null,
-      "generation_config": {
-        "additional_details": {
-          "run_setting": "High",
-          "value_quality": "approximate"
-        }
-      }
-    },
     {
       "evaluation_id": "apex-agents/google_gemini-3-pro/1773260200",
       "retrieved_timestamp": "1773260200",
@@ -277,6 +205,78 @@
         }
       }
     },
+    {
+      "evaluation_id": "ace/google_gemini-3-pro/1773260200",
+      "retrieved_timestamp": "1773260200",
+      "source_metadata": {
+        "source_name": "Mercor ACE Leaderboard",
+        "source_type": "evaluation_run",
+        "source_organization_name": "Mercor",
+        "source_organization_url": "https://www.mercor.com",
+        "evaluator_relationship": "first_party"
+      },
+      "eval_library": {
+        "name": "archipelago",
+        "version": "1.0.0"
+      },
+      "benchmark": "ace",
+      "evaluation_results": [
+        {
+          "evaluation_name": "Overall Score",
+          "source_data": {
+            "dataset_name": "ace",
+            "source_type": "hf_dataset",
+            "hf_repo": "Mercor/ACE"
+          },
+          "metric_config": {
+            "evaluation_description": "Overall ACE score (paper snapshot, approximate).",
+            "lower_is_better": false,
+            "score_type": "continuous",
+            "min_score": 0,
+            "max_score": 1
+          },
+          "score_details": {
+            "score": 0.47
+          },
+          "generation_config": {
+            "additional_details": {
+              "run_setting": "High",
+              "value_quality": "approximate"
+            }
+          }
+        },
+        {
+          "evaluation_name": "Gaming Score",
+          "source_data": {
+            "dataset_name": "ace",
+            "source_type": "hf_dataset",
+            "hf_repo": "Mercor/ACE"
+          },
+          "metric_config": {
+            "evaluation_description": "Gaming domain score.",
+            "lower_is_better": false,
+            "score_type": "continuous",
+            "min_score": 0,
+            "max_score": 1
+          },
+          "score_details": {
+            "score": 0.509
+          },
+          "generation_config": {
+            "additional_details": {
+              "run_setting": "High"
+            }
+          }
+        }
+      ],
+      "detailed_evaluation_results": null,
+      "generation_config": {
+        "additional_details": {
+          "run_setting": "High",
+          "value_quality": "approximate"
+        }
+      }
+    },
     {
       "evaluation_id": "apex-v1/google_gemini-3-pro/1773260200",
       "retrieved_timestamp": "1773260200",
diff --git a/data/models/google_gemma-3-27b-it.json b/data/models/google_gemma-3-27b-it.json
index 0d22aa7a55f613493f23d93430a44590b7aa715d..31e90c4548397bec1dec70a558a4830dc0c4f7c9 100644
--- a/data/models/google_gemma-3-27b-it.json
+++ b/data/models/google_gemma-3-27b-it.json
@@ -10,8 +10,8 @@
   },
   "evaluations": [
     {
-      "evaluation_id": "global-mmlu-lite/google_gemma-3-27b-it/1773936583.743359",
-      "retrieved_timestamp": "1773936583.743359",
+      "evaluation_id": "global-mmlu-lite/google_gemma-3-27b-it/1773936496.366405",
+      "retrieved_timestamp": "1773936496.366405",
       "source_metadata": {
         "source_name": "Global MMLU Lite Leaderboard",
         "source_type": "documentation",
@@ -525,8 +525,8 @@
       "generation_config": null
     },
     {
-      "evaluation_id": "global-mmlu-lite/google_gemma-3-27b-it/1773936496.366405",
-      "retrieved_timestamp": "1773936496.366405",
+      "evaluation_id": "global-mmlu-lite/google_gemma-3-27b-it/1773936583.743359",
+      "retrieved_timestamp": "1773936583.743359",
       "source_metadata": {
         "source_name": "Global MMLU Lite Leaderboard",
         "source_type": "documentation",
diff --git a/data/models/google_gemma-3-4b-it.json b/data/models/google_gemma-3-4b-it.json
index c07b03d8abed5cf353cb3849af3ecfd74770cc92..a4a8d0cbbb50ae74df70e1b97a9540a4077ec070 100644
--- a/data/models/google_gemma-3-4b-it.json
+++ b/data/models/google_gemma-3-4b-it.json
@@ -10,8 +10,8 @@
   },
   "evaluations": [
     {
-      "evaluation_id": "global-mmlu-lite/google_gemma-3-4b-it/1773936583.743359",
-      "retrieved_timestamp": "1773936583.743359",
+      "evaluation_id": "global-mmlu-lite/google_gemma-3-4b-it/1773936496.366405",
+      "retrieved_timestamp": "1773936496.366405",
       "source_metadata": {
         "source_name": "Global MMLU Lite Leaderboard",
         "source_type": "documentation",
@@ -525,8 +525,8 @@
       "generation_config": null
     },
     {
-      "evaluation_id": "global-mmlu-lite/google_gemma-3-4b-it/1773936496.366405",
-      "retrieved_timestamp": "1773936496.366405",
+      "evaluation_id": "global-mmlu-lite/google_gemma-3-4b-it/1773936583.743359",
+      "retrieved_timestamp": "1773936583.743359",
       "source_metadata": {
         "source_name": "Global MMLU Lite Leaderboard",
         "source_type": "documentation",
diff --git a/data/models/guilhermenaturaumana_nature-reason-1.2-reallysmall.json b/data/models/guilhermenaturaumana_nature-reason-1.2-reallysmall.json
index 58b844aaea3cd18e9a2e6beb1696adc0f352442e..e6b795b4a42b62e10b5be417dff9c55ab19686de 100644
--- a/data/models/guilhermenaturaumana_nature-reason-1.2-reallysmall.json
+++ b/data/models/guilhermenaturaumana_nature-reason-1.2-reallysmall.json
@@ -5,7 +5,7 @@
     "developer": "GuilhermeNaturaUmana",
     "inference_platform": "unknown",
     "additional_details": {
-      "precision": "bfloat16",
+      "precision": "float16",
       "architecture": "Qwen2ForCausalLM",
       "params_billions": "7.616"
     }
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4791
+            "score": 0.4985
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5649
+            "score": 0.5645
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.25
+            "score": 0.2576
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2995
+            "score": 0.3003
           }
         },
         {
@@ -116,7 +116,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4439
+            "score": 0.4373
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4408
+            "score": 0.4429
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4985
+            "score": 0.4791
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5645
+            "score": 0.5649
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2576
+            "score": 0.25
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3003
+            "score": 0.2995
           }
         },
         {
@@ -246,7 +246,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4373
+            "score": 0.4439
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4429
+            "score": 0.4408
           }
         }
       ],
diff --git a/data/models/huggingfacetb_smollm2-360m-instruct.json b/data/models/huggingfacetb_smollm2-360m-instruct.json
index b9a479d91c3b9226f2e42a0a5392df69dc01d9df..a4edda6b87f3cb7e0eeabaee9333bba91d019d12 100644
--- a/data/models/huggingfacetb_smollm2-360m-instruct.json
+++ b/data/models/huggingfacetb_smollm2-360m-instruct.json
@@ -5,9 +5,9 @@
     "developer": "HuggingFaceTB",
     "inference_platform": "unknown",
     "additional_details": {
-      "precision": "bfloat16",
+      "precision": "float16",
       "architecture": "LlamaForCausalLM",
-      "params_billions": "0.36"
+      "params_billions": "0.362"
     }
   },
   "evaluations": [
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3842
+            "score": 0.083
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3144
+            "score": 0.3053
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0151
+            "score": 0.0083
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.255
+            "score": 0.2651
           }
         },
         {
@@ -116,7 +116,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3461
+            "score": 0.3423
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1117
+            "score": 0.1126
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.083
+            "score": 0.3842
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3053
+            "score": 0.3144
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0083
+            "score": 0.0151
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2651
+            "score": 0.255
           }
         },
         {
@@ -246,7 +246,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3423
+            "score": 0.3461
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1126
+            "score": 0.1117
           }
         }
       ],
diff --git a/data/models/infly_inf-orm-llama3.1-70b.json b/data/models/infly_inf-orm-llama3.1-70b.json
index e7947ee940015eb0652da9a52891a9ab47739595..82e76ad6cd43b3a105b801967d5f616a3924844a 100644
--- a/data/models/infly_inf-orm-llama3.1-70b.json
+++ b/data/models/infly_inf-orm-llama3.1-70b.json
@@ -9,10 +9,10 @@
   },
   "evaluations": [
     {
-      "evaluation_id": "reward-bench-2/infly_INF-ORM-Llama3.1-70B/1766412838.146816",
+      "evaluation_id": "reward-bench/infly_INF-ORM-Llama3.1-70B/1766412838.146816",
       "retrieved_timestamp": "1766412838.146816",
       "source_metadata": {
-        "source_name": "RewardBench 2",
+        "source_name": "RewardBench",
         "source_type": "documentation",
         "source_organization_name": "Allen Institute for AI",
         "source_organization_url": "https://allenai.org",
@@ -31,104 +31,128 @@
         {
           "evaluation_name": "Score",
           "metric_config": {
-            "evaluation_description": "Overall RewardBench 2 Score (mean of all metrics)",
+            "evaluation_description": "Overall RewardBench Score",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7648
+            "score": 0.9511
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Factuality",
+          "evaluation_name": "Chat",
           "metric_config": {
-            "evaluation_description": "Factuality score - measures factual accuracy",
+            "evaluation_description": "Chat accuracy - includes easy chat subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7411
+            "score": 0.9665
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Precise IF",
+          "evaluation_name": "Chat Hard",
           "metric_config": {
-            "evaluation_description": "Precise Instruction Following score",
+            "evaluation_description": "Chat Hard accuracy - includes hard chat subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4188
+            "score": 0.9101
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Math",
+          "evaluation_name": "Safety",
           "metric_config": {
-            "evaluation_description": "Math score - measures mathematical reasoning",
+            "evaluation_description": "Safety accuracy - includes safety subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6995
+            "score": 0.9365
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Safety",
+          "evaluation_name": "Reasoning",
           "metric_config": {
-            "evaluation_description": "Safety score - measures safety awareness",
+            "evaluation_description": "Reasoning accuracy - includes code and math subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9644
+            "score": 0.9912
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
-        },
+        }
+      ],
+      "detailed_evaluation_results": null,
+      "generation_config": null
+    },
+    {
+      "evaluation_id": "reward-bench-2/infly_INF-ORM-Llama3.1-70B/1766412838.146816",
+      "retrieved_timestamp": "1766412838.146816",
+      "source_metadata": {
+        "source_name": "RewardBench 2",
+        "source_type": "documentation",
+        "source_organization_name": "Allen Institute for AI",
+        "source_organization_url": "https://allenai.org",
+        "evaluator_relationship": "third_party"
+      },
+      "eval_library": {
+        "name": "rewardbench",
+        "version": "0.1.3",
+        "additional_details": {
+          "subsets": "Chat, Chat Hard, Safety, Reasoning",
+          "hf_space": "allenai/reward-bench"
+        }
+      },
+      "benchmark": "reward-bench",
+      "evaluation_results": [
         {
-          "evaluation_name": "Focus",
+          "evaluation_name": "Score",
           "metric_config": {
-            "evaluation_description": "Focus score - measures response focus",
+            "evaluation_description": "Overall RewardBench 2 Score (mean of all metrics)",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.903
+            "score": 0.7648
           },
           "source_data": {
             "dataset_name": "RewardBench 2",
@@ -137,135 +161,111 @@
           }
         },
         {
-          "evaluation_name": "Ties",
+          "evaluation_name": "Factuality",
           "metric_config": {
-            "evaluation_description": "Ties score - ability to identify tie cases",
+            "evaluation_description": "Factuality score - measures factual accuracy",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.8622
+            "score": 0.7411
           },
           "source_data": {
             "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
             "hf_repo": "allenai/reward-bench-2-results"
           }
-        }
-      ],
-      "detailed_evaluation_results": null,
-      "generation_config": null
-    },
-    {
-      "evaluation_id": "reward-bench/infly_INF-ORM-Llama3.1-70B/1766412838.146816",
-      "retrieved_timestamp": "1766412838.146816",
-      "source_metadata": {
-        "source_name": "RewardBench",
-        "source_type": "documentation",
-        "source_organization_name": "Allen Institute for AI",
-        "source_organization_url": "https://allenai.org",
-        "evaluator_relationship": "third_party"
-      },
-      "eval_library": {
-        "name": "rewardbench",
-        "version": "0.1.3",
-        "additional_details": {
-          "subsets": "Chat, Chat Hard, Safety, Reasoning",
-          "hf_space": "allenai/reward-bench"
-        }
-      },
-      "benchmark": "reward-bench",
-      "evaluation_results": [
+        },
         {
-          "evaluation_name": "Score",
+          "evaluation_name": "Precise IF",
           "metric_config": {
-            "evaluation_description": "Overall RewardBench Score",
+            "evaluation_description": "Precise Instruction Following score",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9511
+            "score": 0.4188
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Chat",
+          "evaluation_name": "Math",
           "metric_config": {
-            "evaluation_description": "Chat accuracy - includes easy chat subsets",
+            "evaluation_description": "Math score - measures mathematical reasoning",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9665
+            "score": 0.6995
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Chat Hard",
+          "evaluation_name": "Safety",
           "metric_config": {
-            "evaluation_description": "Chat Hard accuracy - includes hard chat subsets",
+            "evaluation_description": "Safety score - measures safety awareness",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9101
+            "score": 0.9644
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Safety",
+          "evaluation_name": "Focus",
           "metric_config": {
-            "evaluation_description": "Safety accuracy - includes safety subsets",
+            "evaluation_description": "Focus score - measures response focus",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9365
+            "score": 0.903
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Reasoning",
+          "evaluation_name": "Ties",
           "metric_config": {
-            "evaluation_description": "Reasoning accuracy - includes code and math subsets",
+            "evaluation_description": "Ties score - ability to identify tie cases",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9912
+            "score": 0.8622
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         }
       ],
diff --git a/data/models/internlm_internlm2-1_8b-reward.json b/data/models/internlm_internlm2-1_8b-reward.json
index db02a96edd7d4deec66c9db68ed23c5ecfdc96f9..fdd95af043dae0ccf6943006b6d82bc9a69847ba 100644
--- a/data/models/internlm_internlm2-1_8b-reward.json
+++ b/data/models/internlm_internlm2-1_8b-reward.json
@@ -9,10 +9,10 @@
   },
   "evaluations": [
     {
-      "evaluation_id": "reward-bench/internlm_internlm2-1_8b-reward/1766412838.146816",
+      "evaluation_id": "reward-bench-2/internlm_internlm2-1_8b-reward/1766412838.146816",
       "retrieved_timestamp": "1766412838.146816",
       "source_metadata": {
-        "source_name": "RewardBench",
+        "source_name": "RewardBench 2",
         "source_type": "documentation",
         "source_organization_name": "Allen Institute for AI",
         "source_organization_url": "https://allenai.org",
@@ -31,128 +31,104 @@
         {
           "evaluation_name": "Score",
           "metric_config": {
-            "evaluation_description": "Overall RewardBench Score",
+            "evaluation_description": "Overall RewardBench 2 Score (mean of all metrics)",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.8217
+            "score": 0.3902
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Chat",
+          "evaluation_name": "Factuality",
           "metric_config": {
-            "evaluation_description": "Chat accuracy - includes easy chat subsets",
+            "evaluation_description": "Factuality score - measures factual accuracy",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9358
+            "score": 0.2758
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Chat Hard",
+          "evaluation_name": "Precise IF",
           "metric_config": {
-            "evaluation_description": "Chat Hard accuracy - includes hard chat subsets",
+            "evaluation_description": "Precise Instruction Following score",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6623
+            "score": 0.3625
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Safety",
+          "evaluation_name": "Math",
           "metric_config": {
-            "evaluation_description": "Safety accuracy - includes safety subsets",
+            "evaluation_description": "Math score - measures mathematical reasoning",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.8162
+            "score": 0.4426
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Reasoning",
+          "evaluation_name": "Safety",
           "metric_config": {
-            "evaluation_description": "Reasoning accuracy - includes code and math subsets",
+            "evaluation_description": "Safety score - measures safety awareness",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.8724
+            "score": 0.4711
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
-        }
-      ],
-      "detailed_evaluation_results": null,
-      "generation_config": null
-    },
-    {
-      "evaluation_id": "reward-bench-2/internlm_internlm2-1_8b-reward/1766412838.146816",
-      "retrieved_timestamp": "1766412838.146816",
-      "source_metadata": {
-        "source_name": "RewardBench 2",
-        "source_type": "documentation",
-        "source_organization_name": "Allen Institute for AI",
-        "source_organization_url": "https://allenai.org",
-        "evaluator_relationship": "third_party"
-      },
-      "eval_library": {
-        "name": "rewardbench",
-        "version": "0.1.3",
-        "additional_details": {
-          "subsets": "Chat, Chat Hard, Safety, Reasoning",
-          "hf_space": "allenai/reward-bench"
-        }
-      },
-      "benchmark": "reward-bench",
-      "evaluation_results": [
+        },
         {
-          "evaluation_name": "Score",
+          "evaluation_name": "Focus",
           "metric_config": {
-            "evaluation_description": "Overall RewardBench 2 Score (mean of all metrics)",
+            "evaluation_description": "Focus score - measures response focus",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3902
+            "score": 0.596
           },
           "source_data": {
             "dataset_name": "RewardBench 2",
@@ -161,111 +137,135 @@
           }
         },
         {
-          "evaluation_name": "Factuality",
+          "evaluation_name": "Ties",
           "metric_config": {
-            "evaluation_description": "Factuality score - measures factual accuracy",
+            "evaluation_description": "Ties score - ability to identify tie cases",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2758
+            "score": 0.1934
           },
           "source_data": {
             "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
             "hf_repo": "allenai/reward-bench-2-results"
           }
-        },
+        }
+      ],
+      "detailed_evaluation_results": null,
+      "generation_config": null
+    },
+    {
+      "evaluation_id": "reward-bench/internlm_internlm2-1_8b-reward/1766412838.146816",
+      "retrieved_timestamp": "1766412838.146816",
+      "source_metadata": {
+        "source_name": "RewardBench",
+        "source_type": "documentation",
+        "source_organization_name": "Allen Institute for AI",
+        "source_organization_url": "https://allenai.org",
+        "evaluator_relationship": "third_party"
+      },
+      "eval_library": {
+        "name": "rewardbench",
+        "version": "0.1.3",
+        "additional_details": {
+          "subsets": "Chat, Chat Hard, Safety, Reasoning",
+          "hf_space": "allenai/reward-bench"
+        }
+      },
+      "benchmark": "reward-bench",
+      "evaluation_results": [
         {
-          "evaluation_name": "Precise IF",
+          "evaluation_name": "Score",
           "metric_config": {
-            "evaluation_description": "Precise Instruction Following score",
+            "evaluation_description": "Overall RewardBench Score",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3625
+            "score": 0.8217
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Math",
+          "evaluation_name": "Chat",
           "metric_config": {
-            "evaluation_description": "Math score - measures mathematical reasoning",
+            "evaluation_description": "Chat accuracy - includes easy chat subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4426
+            "score": 0.9358
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Safety",
+          "evaluation_name": "Chat Hard",
           "metric_config": {
-            "evaluation_description": "Safety score - measures safety awareness",
+            "evaluation_description": "Chat Hard accuracy - includes hard chat subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4711
+            "score": 0.6623
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Focus",
+          "evaluation_name": "Safety",
           "metric_config": {
-            "evaluation_description": "Focus score - measures response focus",
+            "evaluation_description": "Safety accuracy - includes safety subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.596
+            "score": 0.8162
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Ties",
+          "evaluation_name": "Reasoning",
           "metric_config": {
-            "evaluation_description": "Ties score - ability to identify tie cases",
+            "evaluation_description": "Reasoning accuracy - includes code and math subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1934
+            "score": 0.8724
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         }
       ],
diff --git a/data/models/internlm_internlm2-7b-reward.json b/data/models/internlm_internlm2-7b-reward.json
index 5907aad77cdf2d42a7b25e1a1a35520112be4497..850f56827380f314c355f2c532b41bbbb69062e8 100644
--- a/data/models/internlm_internlm2-7b-reward.json
+++ b/data/models/internlm_internlm2-7b-reward.json
@@ -9,10 +9,10 @@
   },
   "evaluations": [
     {
-      "evaluation_id": "reward-bench/internlm_internlm2-7b-reward/1766412838.146816",
+      "evaluation_id": "reward-bench-2/internlm_internlm2-7b-reward/1766412838.146816",
       "retrieved_timestamp": "1766412838.146816",
       "source_metadata": {
-        "source_name": "RewardBench",
+        "source_name": "RewardBench 2",
         "source_type": "documentation",
         "source_organization_name": "Allen Institute for AI",
         "source_organization_url": "https://allenai.org",
@@ -31,128 +31,104 @@
         {
           "evaluation_name": "Score",
           "metric_config": {
-            "evaluation_description": "Overall RewardBench Score",
+            "evaluation_description": "Overall RewardBench 2 Score (mean of all metrics)",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.8759
+            "score": 0.5335
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Chat",
+          "evaluation_name": "Factuality",
           "metric_config": {
-            "evaluation_description": "Chat accuracy - includes easy chat subsets",
+            "evaluation_description": "Factuality score - measures factual accuracy",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9916
+            "score": 0.4211
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Chat Hard",
+          "evaluation_name": "Precise IF",
           "metric_config": {
-            "evaluation_description": "Chat Hard accuracy - includes hard chat subsets",
+            "evaluation_description": "Precise Instruction Following score",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6952
+            "score": 0.4
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Safety",
+          "evaluation_name": "Math",
           "metric_config": {
-            "evaluation_description": "Safety accuracy - includes safety subsets",
+            "evaluation_description": "Math score - measures mathematical reasoning",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.8716
+            "score": 0.5628
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Reasoning",
+          "evaluation_name": "Safety",
           "metric_config": {
-            "evaluation_description": "Reasoning accuracy - includes code and math subsets",
+            "evaluation_description": "Safety score - measures safety awareness",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9453
+            "score": 0.5956
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
-        }
-      ],
-      "detailed_evaluation_results": null,
-      "generation_config": null
-    },
-    {
-      "evaluation_id": "reward-bench-2/internlm_internlm2-7b-reward/1766412838.146816",
-      "retrieved_timestamp": "1766412838.146816",
-      "source_metadata": {
-        "source_name": "RewardBench 2",
-        "source_type": "documentation",
-        "source_organization_name": "Allen Institute for AI",
-        "source_organization_url": "https://allenai.org",
-        "evaluator_relationship": "third_party"
-      },
-      "eval_library": {
-        "name": "rewardbench",
-        "version": "0.1.3",
-        "additional_details": {
-          "subsets": "Chat, Chat Hard, Safety, Reasoning",
-          "hf_space": "allenai/reward-bench"
-        }
-      },
-      "benchmark": "reward-bench",
-      "evaluation_results": [
+        },
         {
-          "evaluation_name": "Score",
+          "evaluation_name": "Focus",
           "metric_config": {
-            "evaluation_description": "Overall RewardBench 2 Score (mean of all metrics)",
+            "evaluation_description": "Focus score - measures response focus",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5335
+            "score": 0.7051
           },
           "source_data": {
             "dataset_name": "RewardBench 2",
@@ -161,111 +137,135 @@
           }
         },
         {
-          "evaluation_name": "Factuality",
+          "evaluation_name": "Ties",
           "metric_config": {
-            "evaluation_description": "Factuality score - measures factual accuracy",
+            "evaluation_description": "Ties score - ability to identify tie cases",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4211
+            "score": 0.5164
           },
           "source_data": {
             "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
             "hf_repo": "allenai/reward-bench-2-results"
           }
-        },
+        }
+      ],
+      "detailed_evaluation_results": null,
+      "generation_config": null
+    },
+    {
+      "evaluation_id": "reward-bench/internlm_internlm2-7b-reward/1766412838.146816",
+      "retrieved_timestamp": "1766412838.146816",
+      "source_metadata": {
+        "source_name": "RewardBench",
+        "source_type": "documentation",
+        "source_organization_name": "Allen Institute for AI",
+        "source_organization_url": "https://allenai.org",
+        "evaluator_relationship": "third_party"
+      },
+      "eval_library": {
+        "name": "rewardbench",
+        "version": "0.1.3",
+        "additional_details": {
+          "subsets": "Chat, Chat Hard, Safety, Reasoning",
+          "hf_space": "allenai/reward-bench"
+        }
+      },
+      "benchmark": "reward-bench",
+      "evaluation_results": [
         {
-          "evaluation_name": "Precise IF",
+          "evaluation_name": "Score",
           "metric_config": {
-            "evaluation_description": "Precise Instruction Following score",
+            "evaluation_description": "Overall RewardBench Score",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4
+            "score": 0.8759
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Math",
+          "evaluation_name": "Chat",
           "metric_config": {
-            "evaluation_description": "Math score - measures mathematical reasoning",
+            "evaluation_description": "Chat accuracy - includes easy chat subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5628
+            "score": 0.9916
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Safety",
+          "evaluation_name": "Chat Hard",
           "metric_config": {
-            "evaluation_description": "Safety score - measures safety awareness",
+            "evaluation_description": "Chat Hard accuracy - includes hard chat subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5956
+            "score": 0.6952
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Focus",
+          "evaluation_name": "Safety",
           "metric_config": {
-            "evaluation_description": "Focus score - measures response focus",
+            "evaluation_description": "Safety accuracy - includes safety subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7051
+            "score": 0.8716
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Ties",
+          "evaluation_name": "Reasoning",
           "metric_config": {
-            "evaluation_description": "Ties score - ability to identify tie cases",
+            "evaluation_description": "Reasoning accuracy - includes code and math subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5164
+            "score": 0.9453
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         }
       ],
diff --git a/data/models/jaspionjader_kosmos-evaa-fusion-8b.json b/data/models/jaspionjader_kosmos-evaa-fusion-8b.json
index 1160e36435338576bea29bef2eb39f295798e22d..88cf241ec28671fc887627a1e7bb1af09c15f9cf 100644
--- a/data/models/jaspionjader_kosmos-evaa-fusion-8b.json
+++ b/data/models/jaspionjader_kosmos-evaa-fusion-8b.json
@@ -5,7 +5,7 @@
     "developer": "jaspionjader",
     "inference_platform": "unknown",
     "additional_details": {
-      "precision": "bfloat16",
+      "precision": "float16",
       "architecture": "LlamaForCausalLM",
       "params_billions": "8.03"
     }
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4345
+            "score": 0.4418
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5419
+            "score": 0.5406
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1292
+            "score": 0.1352
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3087
+            "score": 0.3062
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3854
+            "score": 0.386
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4418
+            "score": 0.4345
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5406
+            "score": 0.5419
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1352
+            "score": 0.1292
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3062
+            "score": 0.3087
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.386
+            "score": 0.3854
           }
         }
       ],
diff --git a/data/models/leroydyer_spydazweb_ai_humanai_012_instruct_ia.json b/data/models/leroydyer_spydazweb_ai_humanai_012_instruct_ia.json
index 4462dbdfa0461cc5c2fd5d7ac79308c4e0a0cd93..7b050770aeb59148493da52d2a21dee32c7d2c89 100644
--- a/data/models/leroydyer_spydazweb_ai_humanai_012_instruct_ia.json
+++ b/data/models/leroydyer_spydazweb_ai_humanai_012_instruct_ia.json
@@ -5,7 +5,7 @@
     "developer": "LeroyDyer",
     "inference_platform": "unknown",
     "additional_details": {
-      "precision": "bfloat16",
+      "precision": "float16",
       "architecture": "MistralForCausalLM",
       "params_billions": "7.242"
     }
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3066
+            "score": 0.3036
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4577
+            "score": 0.4575
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2995
+            "score": 0.3012
           }
         },
         {
@@ -116,7 +116,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4254
+            "score": 0.4253
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2318
+            "score": 0.2329
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3036
+            "score": 0.3066
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4575
+            "score": 0.4577
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3012
+            "score": 0.2995
           }
         },
         {
@@ -246,7 +246,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4253
+            "score": 0.4254
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2329
+            "score": 0.2318
           }
         }
       ],
diff --git a/data/models/leroydyer_spydazweb_ai_humanai_012_instruct_xa.json b/data/models/leroydyer_spydazweb_ai_humanai_012_instruct_xa.json
index 90656456ac84eb015314278cafdaa288005eb1ba..199a2574ee197c6be6eb6b38849e4c63ab43b085 100644
--- a/data/models/leroydyer_spydazweb_ai_humanai_012_instruct_xa.json
+++ b/data/models/leroydyer_spydazweb_ai_humanai_012_instruct_xa.json
@@ -5,7 +5,7 @@
     "developer": "LeroyDyer",
     "inference_platform": "unknown",
     "additional_details": {
-      "precision": "bfloat16",
+      "precision": "float16",
       "architecture": "MistralForCausalLM",
       "params_billions": "7.242"
     }
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3579
+            "score": 0.3798
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4477
+            "score": 0.4483
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0423
+            "score": 0.04
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3096
+            "score": 0.3129
           }
         },
         {
@@ -116,7 +116,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4134
+            "score": 0.4148
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2376
+            "score": 0.2389
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3798
+            "score": 0.3579
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4483
+            "score": 0.4477
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.04
+            "score": 0.0423
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3129
+            "score": 0.3096
           }
         },
         {
@@ -246,7 +246,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4148
+            "score": 0.4134
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2389
+            "score": 0.2376
           }
         }
       ],
diff --git a/data/models/lxzgordon_urm-llama-3.1-8b.json b/data/models/lxzgordon_urm-llama-3.1-8b.json
index 2ce56c90ce0d5fb5788660f5b3f1f1e179701786..7f03035f2bd809fb14be27130e313f5b86a26f9a 100644
--- a/data/models/lxzgordon_urm-llama-3.1-8b.json
+++ b/data/models/lxzgordon_urm-llama-3.1-8b.json
@@ -9,10 +9,10 @@
   },
   "evaluations": [
     {
-      "evaluation_id": "reward-bench/LxzGordon_URM-LLaMa-3.1-8B/1766412838.146816",
+      "evaluation_id": "reward-bench-2/LxzGordon_URM-LLaMa-3.1-8B/1766412838.146816",
       "retrieved_timestamp": "1766412838.146816",
       "source_metadata": {
-        "source_name": "RewardBench",
+        "source_name": "RewardBench 2",
         "source_type": "documentation",
         "source_organization_name": "Allen Institute for AI",
         "source_organization_url": "https://allenai.org",
@@ -31,128 +31,104 @@
         {
           "evaluation_name": "Score",
           "metric_config": {
-            "evaluation_description": "Overall RewardBench Score",
+            "evaluation_description": "Overall RewardBench 2 Score (mean of all metrics)",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9294
+            "score": 0.7394
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Chat",
+          "evaluation_name": "Factuality",
           "metric_config": {
-            "evaluation_description": "Chat accuracy - includes easy chat subsets",
+            "evaluation_description": "Factuality score - measures factual accuracy",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9553
+            "score": 0.6884
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Chat Hard",
+          "evaluation_name": "Precise IF",
           "metric_config": {
-            "evaluation_description": "Chat Hard accuracy - includes hard chat subsets",
+            "evaluation_description": "Precise Instruction Following score",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.8816
+            "score": 0.45
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Safety",
+          "evaluation_name": "Math",
           "metric_config": {
-            "evaluation_description": "Safety accuracy - includes safety subsets",
+            "evaluation_description": "Math score - measures mathematical reasoning",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9108
+            "score": 0.6393
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Reasoning",
+          "evaluation_name": "Safety",
           "metric_config": {
-            "evaluation_description": "Reasoning accuracy - includes code and math subsets",
+            "evaluation_description": "Safety score - measures safety awareness",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9698
+            "score": 0.9178
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
-        }
-      ],
-      "detailed_evaluation_results": null,
-      "generation_config": null
-    },
-    {
-      "evaluation_id": "reward-bench-2/LxzGordon_URM-LLaMa-3.1-8B/1766412838.146816",
-      "retrieved_timestamp": "1766412838.146816",
-      "source_metadata": {
-        "source_name": "RewardBench 2",
-        "source_type": "documentation",
-        "source_organization_name": "Allen Institute for AI",
-        "source_organization_url": "https://allenai.org",
-        "evaluator_relationship": "third_party"
-      },
-      "eval_library": {
-        "name": "rewardbench",
-        "version": "0.1.3",
-        "additional_details": {
-          "subsets": "Chat, Chat Hard, Safety, Reasoning",
-          "hf_space": "allenai/reward-bench"
-        }
-      },
-      "benchmark": "reward-bench",
-      "evaluation_results": [
+        },
         {
-          "evaluation_name": "Score",
+          "evaluation_name": "Focus",
           "metric_config": {
-            "evaluation_description": "Overall RewardBench 2 Score (mean of all metrics)",
+            "evaluation_description": "Focus score - measures response focus",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7394
+            "score": 0.9758
           },
           "source_data": {
             "dataset_name": "RewardBench 2",
@@ -161,111 +137,135 @@
           }
         },
         {
-          "evaluation_name": "Factuality",
+          "evaluation_name": "Ties",
           "metric_config": {
-            "evaluation_description": "Factuality score - measures factual accuracy",
+            "evaluation_description": "Ties score - ability to identify tie cases",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6884
+            "score": 0.7653
           },
           "source_data": {
             "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
             "hf_repo": "allenai/reward-bench-2-results"
           }
-        },
+        }
+      ],
+      "detailed_evaluation_results": null,
+      "generation_config": null
+    },
+    {
+      "evaluation_id": "reward-bench/LxzGordon_URM-LLaMa-3.1-8B/1766412838.146816",
+      "retrieved_timestamp": "1766412838.146816",
+      "source_metadata": {
+        "source_name": "RewardBench",
+        "source_type": "documentation",
+        "source_organization_name": "Allen Institute for AI",
+        "source_organization_url": "https://allenai.org",
+        "evaluator_relationship": "third_party"
+      },
+      "eval_library": {
+        "name": "rewardbench",
+        "version": "0.1.3",
+        "additional_details": {
+          "subsets": "Chat, Chat Hard, Safety, Reasoning",
+          "hf_space": "allenai/reward-bench"
+        }
+      },
+      "benchmark": "reward-bench",
+      "evaluation_results": [
         {
-          "evaluation_name": "Precise IF",
+          "evaluation_name": "Score",
           "metric_config": {
-            "evaluation_description": "Precise Instruction Following score",
+            "evaluation_description": "Overall RewardBench Score",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.45
+            "score": 0.9294
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Math",
+          "evaluation_name": "Chat",
           "metric_config": {
-            "evaluation_description": "Math score - measures mathematical reasoning",
+            "evaluation_description": "Chat accuracy - includes easy chat subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6393
+            "score": 0.9553
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Safety",
+          "evaluation_name": "Chat Hard",
           "metric_config": {
-            "evaluation_description": "Safety score - measures safety awareness",
+            "evaluation_description": "Chat Hard accuracy - includes hard chat subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9178
+            "score": 0.8816
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Focus",
+          "evaluation_name": "Safety",
           "metric_config": {
-            "evaluation_description": "Focus score - measures response focus",
+            "evaluation_description": "Safety accuracy - includes safety subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9758
+            "score": 0.9108
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Ties",
+          "evaluation_name": "Reasoning",
           "metric_config": {
-            "evaluation_description": "Ties score - ability to identify tie cases",
+            "evaluation_description": "Reasoning accuracy - includes code and math subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7653
+            "score": 0.9698
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         }
       ],
diff --git a/data/models/magpie-align_llama-3-8b-magpie-align-v0.1.json b/data/models/magpie-align_llama-3-8b-magpie-align-v0.1.json
index 018a3210e6da83ca7e6d3501fd6a7fefdb10449c..2ac3bb48cceaf59e0da754702b99c90edec98998 100644
--- a/data/models/magpie-align_llama-3-8b-magpie-align-v0.1.json
+++ b/data/models/magpie-align_llama-3-8b-magpie-align-v0.1.json
@@ -5,7 +5,7 @@
     "developer": "Magpie-Align",
     "inference_platform": "unknown",
     "additional_details": {
-      "precision": "bfloat16",
+      "precision": "float16",
       "architecture": "LlamaForCausalLM",
       "params_billions": "8.03"
     }
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4118
+            "score": 0.4027
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4811
+            "score": 0.4789
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.034
+            "score": 0.0461
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2752
+            "score": 0.2768
           }
         },
         {
@@ -116,7 +116,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3047
+            "score": 0.3087
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3006
+            "score": 0.3001
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4027
+            "score": 0.4118
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4789
+            "score": 0.4811
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0461
+            "score": 0.034
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2768
+            "score": 0.2752
           }
         },
         {
@@ -246,7 +246,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3087
+            "score": 0.3047
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3001
+            "score": 0.3006
           }
         }
       ],
diff --git a/data/models/microsoft_phi-3-mini-4k-instruct.json b/data/models/microsoft_phi-3-mini-4k-instruct.json
index 9787f21694f92686e734f02c35c722665943d7d4..f0214854e07bd3ad87162726609ad6d31e31396a 100644
--- a/data/models/microsoft_phi-3-mini-4k-instruct.json
+++ b/data/models/microsoft_phi-3-mini-4k-instruct.json
@@ -5,7 +5,7 @@
     "developer": "microsoft",
     "inference_platform": "unknown",
     "additional_details": {
-      "precision": "bfloat16",
+      "precision": "float16",
       "architecture": "Phi3ForCausalLM",
       "params_billions": "3.821"
     }
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5613
+            "score": 0.5477
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5676
+            "score": 0.5491
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1163
+            "score": 0.1639
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3196
+            "score": 0.3322
           }
         },
         {
@@ -116,7 +116,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.395
+            "score": 0.4284
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3866
+            "score": 0.4022
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5477
+            "score": 0.5613
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5491
+            "score": 0.5676
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1639
+            "score": 0.1163
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3322
+            "score": 0.3196
           }
         },
         {
@@ -246,7 +246,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4284
+            "score": 0.395
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4022
+            "score": 0.3866
           }
         }
       ],
diff --git a/data/models/microsoft_phi-4.json b/data/models/microsoft_phi-4.json
index c9fca4565946dbb26825690fda8366b38bda6709..32eb099ab1f2e61ac11a8ea3a80df6bc18e5c656 100644
--- a/data/models/microsoft_phi-4.json
+++ b/data/models/microsoft_phi-4.json
@@ -5,7 +5,7 @@
     "developer": "microsoft",
     "inference_platform": "unknown",
     "additional_details": {
-      "precision": "float16",
+      "precision": "bfloat16",
       "architecture": "Phi3ForCausalLM",
       "params_billions": "14.66"
     }
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0488
+            "score": 0.0585
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6703
+            "score": 0.6691
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2787
+            "score": 0.3165
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.401
+            "score": 0.406
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5295
+            "score": 0.5287
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0585
+            "score": 0.0488
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6691
+            "score": 0.6703
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3165
+            "score": 0.2787
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.406
+            "score": 0.401
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5287
+            "score": 0.5295
           }
         }
       ],
diff --git a/data/models/minimax_minimax-m2.1.json b/data/models/minimax_minimax-m2.1.json
index a5b957c9841bcbc5016fb37de174c988ce273877..33905b0ffaa72b65b1d021a73faac651c1ebfecd 100644
--- a/data/models/minimax_minimax-m2.1.json
+++ b/data/models/minimax_minimax-m2.1.json
@@ -4,13 +4,13 @@
     "id": "minimax/minimax-m2.1",
     "developer": "MiniMax",
     "additional_details": {
-      "agent_name": "Terminus 2",
-      "agent_organization": "Terminal Bench"
+      "agent_name": "Crux",
+      "agent_organization": "Roam"
     }
   },
   "evaluations": [
     {
-      "evaluation_id": "terminal-bench-2.0/terminus-2__minimax-m2.1/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/crux__minimax-m2.1/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -34,7 +34,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-12-23",
+          "evaluation_timestamp": "2025-12-22",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -43,7 +43,7 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 29.2,
+            "score": 36.6,
             "uncertainty": {
               "standard_error": {
                 "value": 2.9
@@ -53,7 +53,7 @@
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"MiniMax M2.1\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Crux\" -m \"MiniMax M2.1\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -70,7 +70,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"MiniMax M2.1\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Crux\" -m \"MiniMax M2.1\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -84,7 +84,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/crux__minimax-m2.1/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/terminus-2__minimax-m2.1/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -108,7 +108,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-12-22",
+          "evaluation_timestamp": "2025-12-23",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -117,7 +117,7 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 36.6,
+            "score": 29.2,
             "uncertainty": {
               "standard_error": {
                 "value": 2.9
@@ -127,7 +127,7 @@
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Crux\" -m \"MiniMax M2.1\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"MiniMax M2.1\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -144,7 +144,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Crux\" -m \"MiniMax M2.1\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"MiniMax M2.1\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
diff --git a/data/models/mistralai_mistral-medium-3.json b/data/models/mistralai_mistral-medium-3.json
index 3d0755e0237b9760231fee380b173b29d57eab4a..8c2cd1ffe5583f8e08ea6a503148c17defbde8f4 100644
--- a/data/models/mistralai_mistral-medium-3.json
+++ b/data/models/mistralai_mistral-medium-3.json
@@ -10,8 +10,8 @@
   },
   "evaluations": [
     {
-      "evaluation_id": "global-mmlu-lite/mistralai_mistral-medium-3/1773936496.366405",
-      "retrieved_timestamp": "1773936496.366405",
+      "evaluation_id": "global-mmlu-lite/mistralai_mistral-medium-3/1773936583.743359",
+      "retrieved_timestamp": "1773936583.743359",
       "source_metadata": {
         "source_name": "Global MMLU Lite Leaderboard",
         "source_type": "documentation",
@@ -525,8 +525,8 @@
       "generation_config": null
     },
     {
-      "evaluation_id": "global-mmlu-lite/mistralai_mistral-medium-3/1773936583.743359",
-      "retrieved_timestamp": "1773936583.743359",
+      "evaluation_id": "global-mmlu-lite/mistralai_mistral-medium-3/1773936496.366405",
+      "retrieved_timestamp": "1773936496.366405",
       "source_metadata": {
         "source_name": "Global MMLU Lite Leaderboard",
         "source_type": "documentation",
diff --git a/data/models/mistralai_mistral-small-2503.json b/data/models/mistralai_mistral-small-2503.json
index 6df0d972b005ae32b060fdc4673d6092e770670f..be5d73de7278abb3c747dbebd44b60d3fa624503 100644
--- a/data/models/mistralai_mistral-small-2503.json
+++ b/data/models/mistralai_mistral-small-2503.json
@@ -10,8 +10,8 @@
   },
   "evaluations": [
     {
-      "evaluation_id": "global-mmlu-lite/mistralai_mistral-small-2503/1773936583.743359",
-      "retrieved_timestamp": "1773936583.743359",
+      "evaluation_id": "global-mmlu-lite/mistralai_mistral-small-2503/1773936496.366405",
+      "retrieved_timestamp": "1773936496.366405",
       "source_metadata": {
         "source_name": "Global MMLU Lite Leaderboard",
         "source_type": "documentation",
@@ -525,8 +525,8 @@
       "generation_config": null
     },
     {
-      "evaluation_id": "global-mmlu-lite/mistralai_mistral-small-2503/1773936496.366405",
-      "retrieved_timestamp": "1773936496.366405",
+      "evaluation_id": "global-mmlu-lite/mistralai_mistral-small-2503/1773936583.743359",
+      "retrieved_timestamp": "1773936583.743359",
       "source_metadata": {
         "source_name": "Global MMLU Lite Leaderboard",
         "source_type": "documentation",
diff --git a/data/models/mistralai_mistral-small-instruct-2409.json b/data/models/mistralai_mistral-small-instruct-2409.json
index 5aac65e94f46e67333b7cb66dd77ae7f5415d17b..02a04ce41b1de063befb30b7d94d3ad197cffb0e 100644
--- a/data/models/mistralai_mistral-small-instruct-2409.json
+++ b/data/models/mistralai_mistral-small-instruct-2409.json
@@ -5,9 +5,9 @@
     "developer": "mistralai",
     "inference_platform": "unknown",
     "additional_details": {
-      "precision": "float16",
+      "precision": "bfloat16",
       "architecture": "MistralForCausalLM",
-      "params_billions": "22.247"
+      "params_billions": "22.05"
     }
   },
   "evaluations": [
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6283
+            "score": 0.667
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.583
+            "score": 0.5213
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2039
+            "score": 0.1435
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3331
+            "score": 0.3238
           }
         },
         {
@@ -116,7 +116,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4063
+            "score": 0.3632
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4099
+            "score": 0.396
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.667
+            "score": 0.6283
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5213
+            "score": 0.583
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1435
+            "score": 0.2039
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3238
+            "score": 0.3331
           }
         },
         {
@@ -246,7 +246,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3632
+            "score": 0.4063
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.396
+            "score": 0.4099
           }
         }
       ],
diff --git a/data/models/mistralai_mixtral-8x7b-v0.1.json b/data/models/mistralai_mixtral-8x7b-v0.1.json
index c3ac844f0072de0a86748b754d6c90570298768c..9d997e3527157e47894ae0f49b424a1634297e78 100644
--- a/data/models/mistralai_mixtral-8x7b-v0.1.json
+++ b/data/models/mistralai_mixtral-8x7b-v0.1.json
@@ -5,7 +5,7 @@
     "developer": "mistralai",
     "inference_platform": "unknown",
     "additional_details": {
-      "precision": "float16",
+      "precision": "bfloat16",
       "architecture": "MixtralForCausalLM",
       "params_billions": "46.703"
     }
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2326
+            "score": 0.2415
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5098
+            "score": 0.5087
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0937
+            "score": 0.102
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3205
+            "score": 0.3138
           }
         },
         {
@@ -116,7 +116,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4413
+            "score": 0.4321
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3871
+            "score": 0.385
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2415
+            "score": 0.2326
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5087
+            "score": 0.5098
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.102
+            "score": 0.0937
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3138
+            "score": 0.3205
           }
         },
         {
@@ -246,7 +246,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4321
+            "score": 0.4413
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.385
+            "score": 0.3871
           }
         }
       ],
diff --git a/data/models/mlabonne_neuraldaredevil-8b-abliterated.json b/data/models/mlabonne_neuraldaredevil-8b-abliterated.json
index 7ef165972eafdeec56d923c82e02fdbbc9479eac..d443de39bb7ed82b00df80190432e583c21fd660 100644
--- a/data/models/mlabonne_neuraldaredevil-8b-abliterated.json
+++ b/data/models/mlabonne_neuraldaredevil-8b-abliterated.json
@@ -5,7 +5,7 @@
     "developer": "mlabonne",
     "inference_platform": "unknown",
     "additional_details": {
-      "precision": "bfloat16",
+      "precision": "float16",
       "architecture": "LlamaForCausalLM",
       "params_billions": "8.03"
     }
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4162
+            "score": 0.7561
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5124
+            "score": 0.5111
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0853
+            "score": 0.0906
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3029
+            "score": 0.3062
           }
         },
         {
@@ -116,7 +116,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.415
+            "score": 0.4019
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3802
+            "score": 0.3841
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7561
+            "score": 0.4162
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5111
+            "score": 0.5124
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0906
+            "score": 0.0853
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3062
+            "score": 0.3029
           }
         },
         {
@@ -246,7 +246,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4019
+            "score": 0.415
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3841
+            "score": 0.3802
           }
         }
       ],
diff --git a/data/models/moonshot-ai_kimi-k2-instruct.json b/data/models/moonshot-ai_kimi-k2-instruct.json
index 758984500ae56b028445a56fb8562c74a90a3a8f..2cfded0145e5c6821159f45b392f6b86e15c7f49 100644
--- a/data/models/moonshot-ai_kimi-k2-instruct.json
+++ b/data/models/moonshot-ai_kimi-k2-instruct.json
@@ -4,13 +4,13 @@
     "id": "moonshot-ai/kimi-k2-instruct",
     "developer": "Moonshot AI",
     "additional_details": {
-      "agent_name": "OpenHands",
-      "agent_organization": "OpenHands"
+      "agent_name": "Terminus 2",
+      "agent_organization": "Terminal Bench"
     }
   },
   "evaluations": [
     {
-      "evaluation_id": "terminal-bench-2.0/openhands__kimi-k2-instruct/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/terminus-2__kimi-k2-instruct/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -34,7 +34,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-11-02",
+          "evaluation_timestamp": "2025-11-01",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -43,17 +43,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 26.7,
+            "score": 27.8,
             "uncertainty": {
               "standard_error": {
-                "value": 2.7
+                "value": 2.5
               },
               "num_samples": 435
             }
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"OpenHands\" -m \"Kimi K2 Instruct\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"Kimi K2 Instruct\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -70,7 +70,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"OpenHands\" -m \"Kimi K2 Instruct\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"Kimi K2 Instruct\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -84,7 +84,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/terminus-2__kimi-k2-instruct/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/openhands__kimi-k2-instruct/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -108,7 +108,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-11-01",
+          "evaluation_timestamp": "2025-11-02",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -117,17 +117,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 27.8,
+            "score": 26.7,
             "uncertainty": {
               "standard_error": {
-                "value": 2.5
+                "value": 2.7
               },
               "num_samples": 435
             }
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"Kimi K2 Instruct\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"OpenHands\" -m \"Kimi K2 Instruct\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -144,7 +144,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"Kimi K2 Instruct\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"OpenHands\" -m \"Kimi K2 Instruct\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
diff --git a/data/models/multiple_multiple.json b/data/models/multiple_multiple.json
index 5fae5f56e342c454584c0143a055e41581a00848..c7a1aa9eb1cb1dfc4d88c122729fc6bae4148158 100644
--- a/data/models/multiple_multiple.json
+++ b/data/models/multiple_multiple.json
@@ -4,13 +4,13 @@
     "id": "multiple/multiple",
     "developer": "Multiple",
     "additional_details": {
-      "agent_name": "Warp",
-      "agent_organization": "Warp"
+      "agent_name": "Abacus AI Desktop",
+      "agent_organization": "Abacus.AI"
     }
   },
   "evaluations": [
     {
-      "evaluation_id": "terminal-bench-2.0/warp__multiple/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/abacus-ai-desktop__multiple/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -34,7 +34,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-11-20",
+          "evaluation_timestamp": "2025-12-11",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -43,7 +43,7 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 59.1,
+            "score": 58.4,
             "uncertainty": {
               "standard_error": {
                 "value": 2.8
@@ -53,7 +53,7 @@
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Warp\" -m \"Multiple\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Abacus AI Desktop\" -m \"Multiple\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -70,7 +70,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Warp\" -m \"Multiple\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Abacus AI Desktop\" -m \"Multiple\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -84,7 +84,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/junie-cli__multiple/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/warp__multiple/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -108,7 +108,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2026-03-07",
+          "evaluation_timestamp": "2025-11-20",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -117,17 +117,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 71.0,
+            "score": 59.1,
             "uncertainty": {
               "standard_error": {
-                "value": 2.9
+                "value": 2.8
               },
               "num_samples": 435
             }
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Junie CLI\" -m \"Multiple\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Warp\" -m \"Multiple\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -144,7 +144,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Junie CLI\" -m \"Multiple\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Warp\" -m \"Multiple\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -158,7 +158,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/abacus-ai-desktop__multiple/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/ob-1__multiple/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -182,7 +182,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-12-11",
+          "evaluation_timestamp": "2026-03-05",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -191,17 +191,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 58.4,
+            "score": 72.4,
             "uncertainty": {
               "standard_error": {
-                "value": 2.8
+                "value": 2.3
               },
               "num_samples": 435
             }
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Abacus AI Desktop\" -m \"Multiple\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"OB-1\" -m \"Multiple\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -218,7 +218,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Abacus AI Desktop\" -m \"Multiple\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"OB-1\" -m \"Multiple\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -256,7 +256,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-12-12",
+          "evaluation_timestamp": "2025-11-11",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -265,10 +265,10 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 61.2,
+            "score": 50.1,
             "uncertainty": {
               "standard_error": {
-                "value": 3.0
+                "value": 2.7
               },
               "num_samples": 435
             }
@@ -330,7 +330,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-11-11",
+          "evaluation_timestamp": "2025-12-12",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -339,10 +339,10 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 50.1,
+            "score": 61.2,
             "uncertainty": {
               "standard_error": {
-                "value": 2.7
+                "value": 3.0
               },
               "num_samples": 435
             }
@@ -380,7 +380,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/ob-1__multiple/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/junie-cli__multiple/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -404,7 +404,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2026-03-05",
+          "evaluation_timestamp": "2026-03-07",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -413,17 +413,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 72.4,
+            "score": 71.0,
             "uncertainty": {
               "standard_error": {
-                "value": 2.3
+                "value": 2.9
               },
               "num_samples": 435
             }
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"OB-1\" -m \"Multiple\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Junie CLI\" -m \"Multiple\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -440,7 +440,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"OB-1\" -m \"Multiple\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Junie CLI\" -m \"Multiple\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
diff --git a/data/models/nicolinho_qrm-gemma-2-27b.json b/data/models/nicolinho_qrm-gemma-2-27b.json
index 1dea90f885df9d34139a9ef21e55b3dcce1a25fd..98185886d3c230ddcd90456c69a5aeed49795fc5 100644
--- a/data/models/nicolinho_qrm-gemma-2-27b.json
+++ b/data/models/nicolinho_qrm-gemma-2-27b.json
@@ -9,10 +9,10 @@
   },
   "evaluations": [
     {
-      "evaluation_id": "reward-bench/nicolinho_QRM-Gemma-2-27B/1766412838.146816",
+      "evaluation_id": "reward-bench-2/nicolinho_QRM-Gemma-2-27B/1766412838.146816",
       "retrieved_timestamp": "1766412838.146816",
       "source_metadata": {
-        "source_name": "RewardBench",
+        "source_name": "RewardBench 2",
         "source_type": "documentation",
         "source_organization_name": "Allen Institute for AI",
         "source_organization_url": "https://allenai.org",
@@ -31,128 +31,104 @@
         {
           "evaluation_name": "Score",
           "metric_config": {
-            "evaluation_description": "Overall RewardBench Score",
+            "evaluation_description": "Overall RewardBench 2 Score (mean of all metrics)",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9444
+            "score": 0.7667
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Chat",
+          "evaluation_name": "Factuality",
           "metric_config": {
-            "evaluation_description": "Chat accuracy - includes easy chat subsets",
+            "evaluation_description": "Factuality score - measures factual accuracy",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9665
+            "score": 0.7853
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Chat Hard",
+          "evaluation_name": "Precise IF",
           "metric_config": {
-            "evaluation_description": "Chat Hard accuracy - includes hard chat subsets",
+            "evaluation_description": "Precise Instruction Following score",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9013
+            "score": 0.3719
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Safety",
+          "evaluation_name": "Math",
           "metric_config": {
-            "evaluation_description": "Safety accuracy - includes safety subsets",
+            "evaluation_description": "Math score - measures mathematical reasoning",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.927
+            "score": 0.6995
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Reasoning",
+          "evaluation_name": "Safety",
           "metric_config": {
-            "evaluation_description": "Reasoning accuracy - includes code and math subsets",
+            "evaluation_description": "Safety score - measures safety awareness",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9826
+            "score": 0.9578
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
-        }
-      ],
-      "detailed_evaluation_results": null,
-      "generation_config": null
-    },
-    {
-      "evaluation_id": "reward-bench-2/nicolinho_QRM-Gemma-2-27B/1766412838.146816",
-      "retrieved_timestamp": "1766412838.146816",
-      "source_metadata": {
-        "source_name": "RewardBench 2",
-        "source_type": "documentation",
-        "source_organization_name": "Allen Institute for AI",
-        "source_organization_url": "https://allenai.org",
-        "evaluator_relationship": "third_party"
-      },
-      "eval_library": {
-        "name": "rewardbench",
-        "version": "0.1.3",
-        "additional_details": {
-          "subsets": "Chat, Chat Hard, Safety, Reasoning",
-          "hf_space": "allenai/reward-bench"
-        }
-      },
-      "benchmark": "reward-bench",
-      "evaluation_results": [
+        },
         {
-          "evaluation_name": "Score",
+          "evaluation_name": "Focus",
           "metric_config": {
-            "evaluation_description": "Overall RewardBench 2 Score (mean of all metrics)",
+            "evaluation_description": "Focus score - measures response focus",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7667
+            "score": 0.9535
           },
           "source_data": {
             "dataset_name": "RewardBench 2",
@@ -161,111 +137,135 @@
           }
         },
         {
-          "evaluation_name": "Factuality",
+          "evaluation_name": "Ties",
           "metric_config": {
-            "evaluation_description": "Factuality score - measures factual accuracy",
+            "evaluation_description": "Ties score - ability to identify tie cases",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7853
+            "score": 0.8321
           },
           "source_data": {
             "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
             "hf_repo": "allenai/reward-bench-2-results"
           }
-        },
+        }
+      ],
+      "detailed_evaluation_results": null,
+      "generation_config": null
+    },
+    {
+      "evaluation_id": "reward-bench/nicolinho_QRM-Gemma-2-27B/1766412838.146816",
+      "retrieved_timestamp": "1766412838.146816",
+      "source_metadata": {
+        "source_name": "RewardBench",
+        "source_type": "documentation",
+        "source_organization_name": "Allen Institute for AI",
+        "source_organization_url": "https://allenai.org",
+        "evaluator_relationship": "third_party"
+      },
+      "eval_library": {
+        "name": "rewardbench",
+        "version": "0.1.3",
+        "additional_details": {
+          "subsets": "Chat, Chat Hard, Safety, Reasoning",
+          "hf_space": "allenai/reward-bench"
+        }
+      },
+      "benchmark": "reward-bench",
+      "evaluation_results": [
         {
-          "evaluation_name": "Precise IF",
+          "evaluation_name": "Score",
           "metric_config": {
-            "evaluation_description": "Precise Instruction Following score",
+            "evaluation_description": "Overall RewardBench Score",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3719
+            "score": 0.9444
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Math",
+          "evaluation_name": "Chat",
           "metric_config": {
-            "evaluation_description": "Math score - measures mathematical reasoning",
+            "evaluation_description": "Chat accuracy - includes easy chat subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6995
+            "score": 0.9665
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Safety",
+          "evaluation_name": "Chat Hard",
           "metric_config": {
-            "evaluation_description": "Safety score - measures safety awareness",
+            "evaluation_description": "Chat Hard accuracy - includes hard chat subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9578
+            "score": 0.9013
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Focus",
+          "evaluation_name": "Safety",
           "metric_config": {
-            "evaluation_description": "Focus score - measures response focus",
+            "evaluation_description": "Safety accuracy - includes safety subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9535
+            "score": 0.927
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Ties",
+          "evaluation_name": "Reasoning",
           "metric_config": {
-            "evaluation_description": "Ties score - ability to identify tie cases",
+            "evaluation_description": "Reasoning accuracy - includes code and math subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.8321
+            "score": 0.9826
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         }
       ],
diff --git a/data/models/nicolinho_qrm-llama3.1-8b-v2.json b/data/models/nicolinho_qrm-llama3.1-8b-v2.json
index 71e586c5d191f366e8b76150e58f0f9807a69f6b..0df8878cad15f33ea391f78f6a5406e147177591 100644
--- a/data/models/nicolinho_qrm-llama3.1-8b-v2.json
+++ b/data/models/nicolinho_qrm-llama3.1-8b-v2.json
@@ -9,10 +9,10 @@
   },
   "evaluations": [
     {
-      "evaluation_id": "reward-bench/nicolinho_QRM-Llama3.1-8B-v2/1766412838.146816",
+      "evaluation_id": "reward-bench-2/nicolinho_QRM-Llama3.1-8B-v2/1766412838.146816",
       "retrieved_timestamp": "1766412838.146816",
       "source_metadata": {
-        "source_name": "RewardBench",
+        "source_name": "RewardBench 2",
         "source_type": "documentation",
         "source_organization_name": "Allen Institute for AI",
         "source_organization_url": "https://allenai.org",
@@ -31,128 +31,104 @@
         {
           "evaluation_name": "Score",
           "metric_config": {
-            "evaluation_description": "Overall RewardBench Score",
+            "evaluation_description": "Overall RewardBench 2 Score (mean of all metrics)",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9314
+            "score": 0.7074
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Chat",
+          "evaluation_name": "Factuality",
           "metric_config": {
-            "evaluation_description": "Chat accuracy - includes easy chat subsets",
+            "evaluation_description": "Factuality score - measures factual accuracy",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9637
+            "score": 0.6653
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Chat Hard",
+          "evaluation_name": "Precise IF",
           "metric_config": {
-            "evaluation_description": "Chat Hard accuracy - includes hard chat subsets",
+            "evaluation_description": "Precise Instruction Following score",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.8684
+            "score": 0.4062
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Safety",
+          "evaluation_name": "Math",
           "metric_config": {
-            "evaluation_description": "Safety accuracy - includes safety subsets",
+            "evaluation_description": "Math score - measures mathematical reasoning",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9257
+            "score": 0.612
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Reasoning",
+          "evaluation_name": "Safety",
           "metric_config": {
-            "evaluation_description": "Reasoning accuracy - includes code and math subsets",
+            "evaluation_description": "Safety score - measures safety awareness",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9677
+            "score": 0.9467
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
-        }
-      ],
-      "detailed_evaluation_results": null,
-      "generation_config": null
-    },
-    {
-      "evaluation_id": "reward-bench-2/nicolinho_QRM-Llama3.1-8B-v2/1766412838.146816",
-      "retrieved_timestamp": "1766412838.146816",
-      "source_metadata": {
-        "source_name": "RewardBench 2",
-        "source_type": "documentation",
-        "source_organization_name": "Allen Institute for AI",
-        "source_organization_url": "https://allenai.org",
-        "evaluator_relationship": "third_party"
-      },
-      "eval_library": {
-        "name": "rewardbench",
-        "version": "0.1.3",
-        "additional_details": {
-          "subsets": "Chat, Chat Hard, Safety, Reasoning",
-          "hf_space": "allenai/reward-bench"
-        }
-      },
-      "benchmark": "reward-bench",
-      "evaluation_results": [
+        },
         {
-          "evaluation_name": "Score",
+          "evaluation_name": "Focus",
           "metric_config": {
-            "evaluation_description": "Overall RewardBench 2 Score (mean of all metrics)",
+            "evaluation_description": "Focus score - measures response focus",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7074
+            "score": 0.8909
           },
           "source_data": {
             "dataset_name": "RewardBench 2",
@@ -161,111 +137,135 @@
           }
         },
         {
-          "evaluation_name": "Factuality",
+          "evaluation_name": "Ties",
           "metric_config": {
-            "evaluation_description": "Factuality score - measures factual accuracy",
+            "evaluation_description": "Ties score - ability to identify tie cases",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6653
+            "score": 0.7234
           },
           "source_data": {
             "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
             "hf_repo": "allenai/reward-bench-2-results"
           }
-        },
+        }
+      ],
+      "detailed_evaluation_results": null,
+      "generation_config": null
+    },
+    {
+      "evaluation_id": "reward-bench/nicolinho_QRM-Llama3.1-8B-v2/1766412838.146816",
+      "retrieved_timestamp": "1766412838.146816",
+      "source_metadata": {
+        "source_name": "RewardBench",
+        "source_type": "documentation",
+        "source_organization_name": "Allen Institute for AI",
+        "source_organization_url": "https://allenai.org",
+        "evaluator_relationship": "third_party"
+      },
+      "eval_library": {
+        "name": "rewardbench",
+        "version": "0.1.3",
+        "additional_details": {
+          "subsets": "Chat, Chat Hard, Safety, Reasoning",
+          "hf_space": "allenai/reward-bench"
+        }
+      },
+      "benchmark": "reward-bench",
+      "evaluation_results": [
         {
-          "evaluation_name": "Precise IF",
+          "evaluation_name": "Score",
           "metric_config": {
-            "evaluation_description": "Precise Instruction Following score",
+            "evaluation_description": "Overall RewardBench Score",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4062
+            "score": 0.9314
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Math",
+          "evaluation_name": "Chat",
           "metric_config": {
-            "evaluation_description": "Math score - measures mathematical reasoning",
+            "evaluation_description": "Chat accuracy - includes easy chat subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.612
+            "score": 0.9637
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Safety",
+          "evaluation_name": "Chat Hard",
           "metric_config": {
-            "evaluation_description": "Safety score - measures safety awareness",
+            "evaluation_description": "Chat Hard accuracy - includes hard chat subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9467
+            "score": 0.8684
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Focus",
+          "evaluation_name": "Safety",
           "metric_config": {
-            "evaluation_description": "Focus score - measures response focus",
+            "evaluation_description": "Safety accuracy - includes safety subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.8909
+            "score": 0.9257
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Ties",
+          "evaluation_name": "Reasoning",
           "metric_config": {
-            "evaluation_description": "Ties score - ability to identify tie cases",
+            "evaluation_description": "Reasoning accuracy - includes code and math subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7234
+            "score": 0.9677
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         }
       ],
diff --git a/data/models/icefog72_icesakev6rp-7b.json b/data/models/nousresearch_yarn-llama-2-7b-128k.json
similarity index 88%
rename from data/models/icefog72_icesakev6rp-7b.json
rename to data/models/nousresearch_yarn-llama-2-7b-128k.json
index f3267e4e350d12bc0c15245dbc590141fe9832d9..031faa4d0ff78244e61988ea0bfc24cefdd224de 100644
--- a/data/models/icefog72_icesakev6rp-7b.json
+++ b/data/models/nousresearch_yarn-llama-2-7b-128k.json
@@ -1,18 +1,18 @@
 {
   "model_info": {
-    "name": "IceSakeV6RP-7b",
-    "id": "icefog72/IceSakeV6RP-7b",
-    "developer": "icefog72",
+    "name": "Yarn-Llama-2-7b-128k",
+    "id": "NousResearch/Yarn-Llama-2-7b-128k",
+    "developer": "NousResearch",
     "inference_platform": "unknown",
     "additional_details": {
-      "precision": "float16",
-      "architecture": "MistralForCausalLM",
-      "params_billions": "7.242"
+      "precision": "bfloat16",
+      "architecture": "LlamaForCausalLM",
+      "params_billions": "7.0"
     }
   },
   "evaluations": [
     {
-      "evaluation_id": "hfopenllm_v2/icefog72_IceSakeV6RP-7b/1773936498.240187",
+      "evaluation_id": "hfopenllm_v2/NousResearch_Yarn-Llama-2-7b-128k/1773936498.240187",
       "retrieved_timestamp": "1773936498.240187",
       "source_metadata": {
         "source_name": "HF Open LLM v2",
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5033
+            "score": 0.1485
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4976
+            "score": 0.3248
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0619
+            "score": 0.0151
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2911
+            "score": 0.2601
           }
         },
         {
@@ -116,7 +116,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.42
+            "score": 0.3967
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3093
+            "score": 0.1791
           }
         }
       ],
diff --git a/data/models/ontocord_wide_3b_sft_stage1.1-ss1-with_generics_intr_math_stories.no_issue.json b/data/models/ontocord_wide_3b_sft_stage1.1-ss1-with_generics_intr_math_stories.no_issue.json
index 486ba5e61208261c68f73d7d2bf88d78b1b36131..f86ab61b521749eb0f8fa030a3c29f5a32d327a1 100644
--- a/data/models/ontocord_wide_3b_sft_stage1.1-ss1-with_generics_intr_math_stories.no_issue.json
+++ b/data/models/ontocord_wide_3b_sft_stage1.1-ss1-with_generics_intr_math_stories.no_issue.json
@@ -5,7 +5,7 @@
     "developer": "ontocord",
     "inference_platform": "unknown",
     "additional_details": {
-      "precision": "bfloat16",
+      "precision": "float16",
       "architecture": "Qwen2ForCausalLM",
       "params_billions": "3.759"
     }
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1128
+            "score": 0.1162
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3171
+            "score": 0.3184
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0113
+            "score": 0.0076
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2685
+            "score": 0.2634
           }
         },
         {
@@ -116,7 +116,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.346
+            "score": 0.3447
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1129
+            "score": 0.1124
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1162
+            "score": 0.1128
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3184
+            "score": 0.3171
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0076
+            "score": 0.0113
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2634
+            "score": 0.2685
           }
         },
         {
@@ -246,7 +246,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3447
+            "score": 0.346
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1124
+            "score": 0.1129
           }
         }
       ],
diff --git a/data/models/openai_gpt-4o-2024-08-06.json b/data/models/openai_gpt-4o-2024-08-06.json
index ca15abfce433f9cf3b132cc5fefadfcef719867a..4523783fb76c33e56985cf8706dfcde93c76d009 100644
--- a/data/models/openai_gpt-4o-2024-08-06.json
+++ b/data/models/openai_gpt-4o-2024-08-06.json
@@ -1900,10 +1900,10 @@
       }
     },
     {
-      "evaluation_id": "reward-bench-2/openai_gpt-4o-2024-08-06/1766412838.146816",
+      "evaluation_id": "reward-bench/openai_gpt-4o-2024-08-06/1766412838.146816",
       "retrieved_timestamp": "1766412838.146816",
       "source_metadata": {
-        "source_name": "RewardBench 2",
+        "source_name": "RewardBench",
         "source_type": "documentation",
         "source_organization_name": "Allen Institute for AI",
         "source_organization_url": "https://allenai.org",
@@ -1922,104 +1922,128 @@
         {
           "evaluation_name": "Score",
           "metric_config": {
-            "evaluation_description": "Overall RewardBench 2 Score (mean of all metrics)",
+            "evaluation_description": "Overall RewardBench Score",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6493
+            "score": 0.8673
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Factuality",
+          "evaluation_name": "Chat",
           "metric_config": {
-            "evaluation_description": "Factuality score - measures factual accuracy",
+            "evaluation_description": "Chat accuracy - includes easy chat subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5684
+            "score": 0.9609
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Precise IF",
+          "evaluation_name": "Chat Hard",
           "metric_config": {
-            "evaluation_description": "Precise Instruction Following score",
+            "evaluation_description": "Chat Hard accuracy - includes hard chat subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3312
+            "score": 0.761
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Math",
+          "evaluation_name": "Safety",
           "metric_config": {
-            "evaluation_description": "Math score - measures mathematical reasoning",
+            "evaluation_description": "Safety accuracy - includes safety subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.623
+            "score": 0.8811
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Safety",
+          "evaluation_name": "Reasoning",
           "metric_config": {
-            "evaluation_description": "Safety score - measures safety awareness",
+            "evaluation_description": "Reasoning accuracy - includes code and math subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.8619
+            "score": 0.8661
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
-        },
+        }
+      ],
+      "detailed_evaluation_results": null,
+      "generation_config": null
+    },
+    {
+      "evaluation_id": "reward-bench-2/openai_gpt-4o-2024-08-06/1766412838.146816",
+      "retrieved_timestamp": "1766412838.146816",
+      "source_metadata": {
+        "source_name": "RewardBench 2",
+        "source_type": "documentation",
+        "source_organization_name": "Allen Institute for AI",
+        "source_organization_url": "https://allenai.org",
+        "evaluator_relationship": "third_party"
+      },
+      "eval_library": {
+        "name": "rewardbench",
+        "version": "0.1.3",
+        "additional_details": {
+          "subsets": "Chat, Chat Hard, Safety, Reasoning",
+          "hf_space": "allenai/reward-bench"
+        }
+      },
+      "benchmark": "reward-bench",
+      "evaluation_results": [
         {
-          "evaluation_name": "Focus",
+          "evaluation_name": "Score",
           "metric_config": {
-            "evaluation_description": "Focus score - measures response focus",
+            "evaluation_description": "Overall RewardBench 2 Score (mean of all metrics)",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7293
+            "score": 0.6493
           },
           "source_data": {
             "dataset_name": "RewardBench 2",
@@ -2028,135 +2052,111 @@
           }
         },
         {
-          "evaluation_name": "Ties",
+          "evaluation_name": "Factuality",
           "metric_config": {
-            "evaluation_description": "Ties score - ability to identify tie cases",
+            "evaluation_description": "Factuality score - measures factual accuracy",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7819
+            "score": 0.5684
           },
           "source_data": {
             "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
             "hf_repo": "allenai/reward-bench-2-results"
           }
-        }
-      ],
-      "detailed_evaluation_results": null,
-      "generation_config": null
-    },
-    {
-      "evaluation_id": "reward-bench/openai_gpt-4o-2024-08-06/1766412838.146816",
-      "retrieved_timestamp": "1766412838.146816",
-      "source_metadata": {
-        "source_name": "RewardBench",
-        "source_type": "documentation",
-        "source_organization_name": "Allen Institute for AI",
-        "source_organization_url": "https://allenai.org",
-        "evaluator_relationship": "third_party"
-      },
-      "eval_library": {
-        "name": "rewardbench",
-        "version": "0.1.3",
-        "additional_details": {
-          "subsets": "Chat, Chat Hard, Safety, Reasoning",
-          "hf_space": "allenai/reward-bench"
-        }
-      },
-      "benchmark": "reward-bench",
-      "evaluation_results": [
+        },
         {
-          "evaluation_name": "Score",
+          "evaluation_name": "Precise IF",
           "metric_config": {
-            "evaluation_description": "Overall RewardBench Score",
+            "evaluation_description": "Precise Instruction Following score",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.8673
+            "score": 0.3312
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Chat",
+          "evaluation_name": "Math",
           "metric_config": {
-            "evaluation_description": "Chat accuracy - includes easy chat subsets",
+            "evaluation_description": "Math score - measures mathematical reasoning",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9609
+            "score": 0.623
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Chat Hard",
+          "evaluation_name": "Safety",
           "metric_config": {
-            "evaluation_description": "Chat Hard accuracy - includes hard chat subsets",
+            "evaluation_description": "Safety score - measures safety awareness",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.761
+            "score": 0.8619
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Safety",
+          "evaluation_name": "Focus",
           "metric_config": {
-            "evaluation_description": "Safety accuracy - includes safety subsets",
+            "evaluation_description": "Focus score - measures response focus",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.8811
+            "score": 0.7293
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Reasoning",
+          "evaluation_name": "Ties",
           "metric_config": {
-            "evaluation_description": "Reasoning accuracy - includes code and math subsets",
+            "evaluation_description": "Ties score - ability to identify tie cases",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.8661
+            "score": 0.7819
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         }
       ],
diff --git a/data/models/openai_gpt-4o-mini-2024-07-18.json b/data/models/openai_gpt-4o-mini-2024-07-18.json
index 1b3fb4c30102ee1f603e3640bb4c4b14c38b8cac..f38f4e1ddedf08dfff3e3ceeb97aeebb3dcce913 100644
--- a/data/models/openai_gpt-4o-mini-2024-07-18.json
+++ b/data/models/openai_gpt-4o-mini-2024-07-18.json
@@ -2124,10 +2124,10 @@
       }
     },
     {
-      "evaluation_id": "reward-bench-2/openai_gpt-4o-mini-2024-07-18/1766412838.146816",
+      "evaluation_id": "reward-bench/openai_gpt-4o-mini-2024-07-18/1766412838.146816",
       "retrieved_timestamp": "1766412838.146816",
       "source_metadata": {
-        "source_name": "RewardBench 2",
+        "source_name": "RewardBench",
         "source_type": "documentation",
         "source_organization_name": "Allen Institute for AI",
         "source_organization_url": "https://allenai.org",
@@ -2146,104 +2146,128 @@
         {
           "evaluation_name": "Score",
           "metric_config": {
-            "evaluation_description": "Overall RewardBench 2 Score (mean of all metrics)",
+            "evaluation_description": "Overall RewardBench Score",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5796
+            "score": 0.8007
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Factuality",
+          "evaluation_name": "Chat",
           "metric_config": {
-            "evaluation_description": "Factuality score - measures factual accuracy",
+            "evaluation_description": "Chat accuracy - includes easy chat subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4105
+            "score": 0.9497
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Precise IF",
+          "evaluation_name": "Chat Hard",
           "metric_config": {
-            "evaluation_description": "Precise Instruction Following score",
+            "evaluation_description": "Chat Hard accuracy - includes hard chat subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3438
+            "score": 0.6075
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Math",
+          "evaluation_name": "Safety",
           "metric_config": {
-            "evaluation_description": "Math score - measures mathematical reasoning",
+            "evaluation_description": "Safety accuracy - includes safety subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5191
+            "score": 0.8081
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Safety",
+          "evaluation_name": "Reasoning",
           "metric_config": {
-            "evaluation_description": "Safety score - measures safety awareness",
+            "evaluation_description": "Reasoning accuracy - includes code and math subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7667
+            "score": 0.8374
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
-        },
+        }
+      ],
+      "detailed_evaluation_results": null,
+      "generation_config": null
+    },
+    {
+      "evaluation_id": "reward-bench-2/openai_gpt-4o-mini-2024-07-18/1766412838.146816",
+      "retrieved_timestamp": "1766412838.146816",
+      "source_metadata": {
+        "source_name": "RewardBench 2",
+        "source_type": "documentation",
+        "source_organization_name": "Allen Institute for AI",
+        "source_organization_url": "https://allenai.org",
+        "evaluator_relationship": "third_party"
+      },
+      "eval_library": {
+        "name": "rewardbench",
+        "version": "0.1.3",
+        "additional_details": {
+          "subsets": "Chat, Chat Hard, Safety, Reasoning",
+          "hf_space": "allenai/reward-bench"
+        }
+      },
+      "benchmark": "reward-bench",
+      "evaluation_results": [
         {
-          "evaluation_name": "Focus",
+          "evaluation_name": "Score",
           "metric_config": {
-            "evaluation_description": "Focus score - measures response focus",
+            "evaluation_description": "Overall RewardBench 2 Score (mean of all metrics)",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7414
+            "score": 0.5796
           },
           "source_data": {
             "dataset_name": "RewardBench 2",
@@ -2252,135 +2276,111 @@
           }
         },
         {
-          "evaluation_name": "Ties",
+          "evaluation_name": "Factuality",
           "metric_config": {
-            "evaluation_description": "Ties score - ability to identify tie cases",
+            "evaluation_description": "Factuality score - measures factual accuracy",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6962
+            "score": 0.4105
           },
           "source_data": {
             "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
             "hf_repo": "allenai/reward-bench-2-results"
           }
-        }
-      ],
-      "detailed_evaluation_results": null,
-      "generation_config": null
-    },
-    {
-      "evaluation_id": "reward-bench/openai_gpt-4o-mini-2024-07-18/1766412838.146816",
-      "retrieved_timestamp": "1766412838.146816",
-      "source_metadata": {
-        "source_name": "RewardBench",
-        "source_type": "documentation",
-        "source_organization_name": "Allen Institute for AI",
-        "source_organization_url": "https://allenai.org",
-        "evaluator_relationship": "third_party"
-      },
-      "eval_library": {
-        "name": "rewardbench",
-        "version": "0.1.3",
-        "additional_details": {
-          "subsets": "Chat, Chat Hard, Safety, Reasoning",
-          "hf_space": "allenai/reward-bench"
-        }
-      },
-      "benchmark": "reward-bench",
-      "evaluation_results": [
+        },
         {
-          "evaluation_name": "Score",
+          "evaluation_name": "Precise IF",
           "metric_config": {
-            "evaluation_description": "Overall RewardBench Score",
+            "evaluation_description": "Precise Instruction Following score",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.8007
+            "score": 0.3438
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Chat",
+          "evaluation_name": "Math",
           "metric_config": {
-            "evaluation_description": "Chat accuracy - includes easy chat subsets",
+            "evaluation_description": "Math score - measures mathematical reasoning",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9497
+            "score": 0.5191
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Chat Hard",
+          "evaluation_name": "Safety",
           "metric_config": {
-            "evaluation_description": "Chat Hard accuracy - includes hard chat subsets",
+            "evaluation_description": "Safety score - measures safety awareness",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6075
+            "score": 0.7667
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Safety",
+          "evaluation_name": "Focus",
           "metric_config": {
-            "evaluation_description": "Safety accuracy - includes safety subsets",
+            "evaluation_description": "Focus score - measures response focus",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.8081
+            "score": 0.7414
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Reasoning",
+          "evaluation_name": "Ties",
           "metric_config": {
-            "evaluation_description": "Reasoning accuracy - includes code and math subsets",
+            "evaluation_description": "Ties score - ability to identify tie cases",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.8374
+            "score": 0.6962
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         }
       ],
diff --git a/data/models/openai_gpt-5-2025-08-07.json b/data/models/openai_gpt-5-2025-08-07.json
index 532bfb57f278c67f06480977b0f49dd924ee82c1..0853492fcc4bbd45f07185718454686350fe1be2 100644
--- a/data/models/openai_gpt-5-2025-08-07.json
+++ b/data/models/openai_gpt-5-2025-08-07.json
@@ -1264,13 +1264,13 @@
       }
     },
     {
-      "evaluation_id": "livecodebenchpro/gpt-5-2025-08-07/1770683238.099205",
-      "retrieved_timestamp": "1770683238.099205",
+      "evaluation_id": "livecodebenchpro/gpt-5-2025-08-07/1760492095.8105888",
+      "retrieved_timestamp": "1760492095.8105888",
       "source_metadata": {
+        "source_organization_name": "New York University,  Princeton University, University of California San Diego, University of Washington and Canyon Crest Academy",
+        "evaluator_relationship": "third_party",
         "source_name": "Live Code Bench Pro",
-        "source_type": "documentation",
-        "source_organization_name": "New York University, Princeton University, University of California San Diego, University of Washington and Canyon Crest Academy",
-        "evaluator_relationship": "third_party"
+        "source_type": "documentation"
       },
       "eval_library": {
         "name": "unknown",
@@ -1280,62 +1280,62 @@
       "evaluation_results": [
         {
           "evaluation_name": "Hard Problems",
+          "metric_config": {
+            "evaluation_description": "Pass@1 on Hard Problems",
+            "lower_is_better": false,
+            "score_type": "continuous",
+            "min_score": 0,
+            "max_score": 1
+          },
+          "score_details": {
+            "score": 0.04225352112676056
+          },
           "source_data": {
             "dataset_name": "Hard Problems",
             "source_type": "url",
             "url": [
               "https://webhook.cp-bench.orzzh.com/leaderboard/llm/difficulty?difficulty=hard&benchmark_mode=live"
             ]
-          },
+          }
+        },
+        {
+          "evaluation_name": "Medium Problems",
           "metric_config": {
-            "evaluation_description": "Pass@1 on Hard Problems",
+            "evaluation_description": "Pass@1 on Medium Problems",
             "lower_is_better": false,
             "score_type": "continuous",
-            "min_score": 0.0,
-            "max_score": 1.0
+            "min_score": 0,
+            "max_score": 1
           },
           "score_details": {
-            "score": 0.0423
-          }
-        },
-        {
-          "evaluation_name": "Medium Problems",
+            "score": 0.4084507042253521
+          },
           "source_data": {
             "dataset_name": "Medium Problems",
             "source_type": "url",
             "url": [
               "https://webhook.cp-bench.orzzh.com/leaderboard/llm/difficulty?difficulty=medium&benchmark_mode=live"
             ]
-          },
+          }
+        },
+        {
+          "evaluation_name": "Easy Problems",
           "metric_config": {
-            "evaluation_description": "Pass@1 on Medium Problems",
+            "evaluation_description": "Pass@1 on Easy Problems",
             "lower_is_better": false,
             "score_type": "continuous",
-            "min_score": 0.0,
-            "max_score": 1.0
+            "min_score": 0,
+            "max_score": 1
           },
           "score_details": {
-            "score": 0.4085
-          }
-        },
-        {
-          "evaluation_name": "Easy Problems",
+            "score": 0.8873239436619719
+          },
           "source_data": {
             "dataset_name": "Easy Problems",
             "source_type": "url",
             "url": [
               "https://webhook.cp-bench.orzzh.com/leaderboard/llm/difficulty?difficulty=easy&benchmark_mode=live"
             ]
-          },
-          "metric_config": {
-            "evaluation_description": "Pass@1 on Easy Problems",
-            "lower_is_better": false,
-            "score_type": "continuous",
-            "min_score": 0.0,
-            "max_score": 1.0
-          },
-          "score_details": {
-            "score": 0.9014
           }
         }
       ],
@@ -1343,13 +1343,13 @@
       "generation_config": null
     },
     {
-      "evaluation_id": "livecodebenchpro/gpt-5-2025-08-07/1760492095.8105888",
-      "retrieved_timestamp": "1760492095.8105888",
+      "evaluation_id": "livecodebenchpro/gpt-5-2025-08-07/1770683238.099205",
+      "retrieved_timestamp": "1770683238.099205",
       "source_metadata": {
-        "source_organization_name": "New York University,  Princeton University, University of California San Diego, University of Washington and Canyon Crest Academy",
-        "evaluator_relationship": "third_party",
         "source_name": "Live Code Bench Pro",
-        "source_type": "documentation"
+        "source_type": "documentation",
+        "source_organization_name": "New York University, Princeton University, University of California San Diego, University of Washington and Canyon Crest Academy",
+        "evaluator_relationship": "third_party"
       },
       "eval_library": {
         "name": "unknown",
@@ -1359,62 +1359,62 @@
       "evaluation_results": [
         {
           "evaluation_name": "Hard Problems",
-          "metric_config": {
-            "evaluation_description": "Pass@1 on Hard Problems",
-            "lower_is_better": false,
-            "score_type": "continuous",
-            "min_score": 0,
-            "max_score": 1
-          },
-          "score_details": {
-            "score": 0.04225352112676056
-          },
           "source_data": {
             "dataset_name": "Hard Problems",
             "source_type": "url",
             "url": [
               "https://webhook.cp-bench.orzzh.com/leaderboard/llm/difficulty?difficulty=hard&benchmark_mode=live"
             ]
-          }
-        },
-        {
-          "evaluation_name": "Medium Problems",
+          },
           "metric_config": {
-            "evaluation_description": "Pass@1 on Medium Problems",
+            "evaluation_description": "Pass@1 on Hard Problems",
             "lower_is_better": false,
             "score_type": "continuous",
-            "min_score": 0,
-            "max_score": 1
+            "min_score": 0.0,
+            "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4084507042253521
-          },
+            "score": 0.0423
+          }
+        },
+        {
+          "evaluation_name": "Medium Problems",
           "source_data": {
             "dataset_name": "Medium Problems",
             "source_type": "url",
             "url": [
               "https://webhook.cp-bench.orzzh.com/leaderboard/llm/difficulty?difficulty=medium&benchmark_mode=live"
             ]
-          }
-        },
-        {
-          "evaluation_name": "Easy Problems",
+          },
           "metric_config": {
-            "evaluation_description": "Pass@1 on Easy Problems",
+            "evaluation_description": "Pass@1 on Medium Problems",
             "lower_is_better": false,
             "score_type": "continuous",
-            "min_score": 0,
-            "max_score": 1
+            "min_score": 0.0,
+            "max_score": 1.0
           },
           "score_details": {
-            "score": 0.8873239436619719
-          },
+            "score": 0.4085
+          }
+        },
+        {
+          "evaluation_name": "Easy Problems",
           "source_data": {
             "dataset_name": "Easy Problems",
             "source_type": "url",
             "url": [
               "https://webhook.cp-bench.orzzh.com/leaderboard/llm/difficulty?difficulty=easy&benchmark_mode=live"
             ]
+          },
+          "metric_config": {
+            "evaluation_description": "Pass@1 on Easy Problems",
+            "lower_is_better": false,
+            "score_type": "continuous",
+            "min_score": 0.0,
+            "max_score": 1.0
+          },
+          "score_details": {
+            "score": 0.9014
           }
         }
       ],
diff --git a/data/models/openai_gpt-5-mini.json b/data/models/openai_gpt-5-mini.json
index 8229a45bea599ef0cf4ec037999fa4d4fdccb65f..c2c25e33d8592b0cf47f06cc9166a5f66ec8f591 100644
--- a/data/models/openai_gpt-5-mini.json
+++ b/data/models/openai_gpt-5-mini.json
@@ -4,13 +4,13 @@
     "id": "openai/gpt-5-mini",
     "developer": "OpenAI",
     "additional_details": {
-      "agent_name": "Codex CLI",
-      "agent_organization": "OpenAI"
+      "agent_name": "Mini-SWE-Agent",
+      "agent_organization": "Princeton"
     }
   },
   "evaluations": [
     {
-      "evaluation_id": "terminal-bench-2.0/codex-cli__gpt-5-mini/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/mini-swe-agent__gpt-5-mini/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -34,7 +34,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-11-04",
+          "evaluation_timestamp": "2025-11-03",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -43,17 +43,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 31.9,
+            "score": 22.2,
             "uncertainty": {
               "standard_error": {
-                "value": 3.0
+                "value": 2.6
               },
               "num_samples": 435
             }
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Codex CLI\" -m \"GPT-5-Mini\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Mini-SWE-Agent\" -m \"GPT-5-Mini\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -70,7 +70,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Codex CLI\" -m \"GPT-5-Mini\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Mini-SWE-Agent\" -m \"GPT-5-Mini\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -84,7 +84,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/openhands__gpt-5-mini/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/terminus-2__gpt-5-mini/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -108,7 +108,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-11-02",
+          "evaluation_timestamp": "2025-10-31",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -117,17 +117,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 29.2,
+            "score": 24.0,
             "uncertainty": {
               "standard_error": {
-                "value": 2.8
+                "value": 2.5
               },
               "num_samples": 435
             }
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"OpenHands\" -m \"GPT-5-Mini\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"GPT-5-Mini\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -144,7 +144,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"OpenHands\" -m \"GPT-5-Mini\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"GPT-5-Mini\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -158,7 +158,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/mini-swe-agent__gpt-5-mini/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/spoox-m__gpt-5-mini/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -182,7 +182,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-11-03",
+          "evaluation_timestamp": "2025-12-24",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -191,17 +191,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 22.2,
+            "score": 34.8,
             "uncertainty": {
               "standard_error": {
-                "value": 2.6
+                "value": 2.7
               },
               "num_samples": 435
             }
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Mini-SWE-Agent\" -m \"GPT-5-Mini\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"spoox-m\" -m \"GPT-5-Mini\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -218,7 +218,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Mini-SWE-Agent\" -m \"GPT-5-Mini\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"spoox-m\" -m \"GPT-5-Mini\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -232,7 +232,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/spoox-m__gpt-5-mini/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/openhands__gpt-5-mini/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -256,7 +256,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-12-24",
+          "evaluation_timestamp": "2025-11-02",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -265,17 +265,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 34.8,
+            "score": 29.2,
             "uncertainty": {
               "standard_error": {
-                "value": 2.7
+                "value": 2.8
               },
               "num_samples": 435
             }
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"spoox-m\" -m \"GPT-5-Mini\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"OpenHands\" -m \"GPT-5-Mini\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -292,7 +292,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"spoox-m\" -m \"GPT-5-Mini\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"OpenHands\" -m \"GPT-5-Mini\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -306,7 +306,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/terminus-2__gpt-5-mini/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/codex-cli__gpt-5-mini/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -330,7 +330,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-10-31",
+          "evaluation_timestamp": "2025-11-04",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -339,17 +339,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 24.0,
+            "score": 31.9,
             "uncertainty": {
               "standard_error": {
-                "value": 2.5
+                "value": 3.0
               },
               "num_samples": 435
             }
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"GPT-5-Mini\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Codex CLI\" -m \"GPT-5-Mini\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -366,7 +366,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"GPT-5-Mini\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Codex CLI\" -m \"GPT-5-Mini\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
diff --git a/data/models/openai_gpt-5-nano.json b/data/models/openai_gpt-5-nano.json
index 9816cdcd5d573c1531a9f756bbbe26744d018229..f1c6d8f032d8015d1380b26ffc2082a7ad57137f 100644
--- a/data/models/openai_gpt-5-nano.json
+++ b/data/models/openai_gpt-5-nano.json
@@ -84,7 +84,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/mini-swe-agent__gpt-5-nano/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/terminus-2__gpt-5-nano/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -108,7 +108,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-11-03",
+          "evaluation_timestamp": "2025-10-31",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -117,7 +117,7 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 7.0,
+            "score": 7.9,
             "uncertainty": {
               "standard_error": {
                 "value": 1.9
@@ -127,7 +127,7 @@
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Mini-SWE-Agent\" -m \"GPT-5-Nano\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"GPT-5-Nano\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -144,7 +144,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Mini-SWE-Agent\" -m \"GPT-5-Nano\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"GPT-5-Nano\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -158,7 +158,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/terminus-2__gpt-5-nano/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/codex-cli__gpt-5-nano/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -182,7 +182,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-10-31",
+          "evaluation_timestamp": "2025-11-04",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -191,17 +191,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 7.9,
+            "score": 11.5,
             "uncertainty": {
               "standard_error": {
-                "value": 1.9
+                "value": 2.3
               },
               "num_samples": 435
             }
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"GPT-5-Nano\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Codex CLI\" -m \"GPT-5-Nano\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -218,7 +218,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"GPT-5-Nano\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Codex CLI\" -m \"GPT-5-Nano\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -232,7 +232,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/codex-cli__gpt-5-nano/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/mini-swe-agent__gpt-5-nano/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -256,7 +256,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-11-04",
+          "evaluation_timestamp": "2025-11-03",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -265,17 +265,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 11.5,
+            "score": 7.0,
             "uncertainty": {
               "standard_error": {
-                "value": 2.3
+                "value": 1.9
               },
               "num_samples": 435
             }
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Codex CLI\" -m \"GPT-5-Nano\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Mini-SWE-Agent\" -m \"GPT-5-Nano\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -292,7 +292,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Codex CLI\" -m \"GPT-5-Nano\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Mini-SWE-Agent\" -m \"GPT-5-Nano\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
diff --git a/data/models/openai_gpt-5.1-codex.json b/data/models/openai_gpt-5.1-codex.json
index a2aac5e629083b81e1729673348d7d31d575cd9b..5ac777453649e155d2cf4ca5c0edb4c1fb8d16a4 100644
--- a/data/models/openai_gpt-5.1-codex.json
+++ b/data/models/openai_gpt-5.1-codex.json
@@ -84,7 +84,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/letta-code__gpt-5.1-codex/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/crux__gpt-5.1-codex/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -108,7 +108,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-12-17",
+          "evaluation_timestamp": "2025-11-16",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -117,17 +117,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 53.5,
+            "score": 57.8,
             "uncertainty": {
               "standard_error": {
-                "value": 2.8
+                "value": 2.9
               },
               "num_samples": 435
             }
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Letta Code\" -m \"GPT-5.1-Codex\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Crux\" -m \"GPT-5.1-Codex\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -144,7 +144,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Letta Code\" -m \"GPT-5.1-Codex\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Crux\" -m \"GPT-5.1-Codex\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -158,7 +158,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/crux__gpt-5.1-codex/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/letta-code__gpt-5.1-codex/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -182,7 +182,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-11-16",
+          "evaluation_timestamp": "2025-12-17",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -191,17 +191,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 57.8,
+            "score": 53.5,
             "uncertainty": {
               "standard_error": {
-                "value": 2.9
+                "value": 2.8
               },
               "num_samples": 435
             }
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Crux\" -m \"GPT-5.1-Codex\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Letta Code\" -m \"GPT-5.1-Codex\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -218,7 +218,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Crux\" -m \"GPT-5.1-Codex\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Letta Code\" -m \"GPT-5.1-Codex\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
diff --git a/data/models/openai_gpt-5.2-2025-12-11.json b/data/models/openai_gpt-5.2-2025-12-11.json
index b70c28d6ee613e835fe13ebe0ae4b3e2cc5d0ae8..c3a672d6300dfa51d07ee396880a48a053600e4c 100644
--- a/data/models/openai_gpt-5.2-2025-12-11.json
+++ b/data/models/openai_gpt-5.2-2025-12-11.json
@@ -4,13 +4,13 @@
     "id": "openai/gpt-5.2-2025-12-11",
     "developer": "OpenAI",
     "additional_details": {
-      "agent_name": "SmolAgents Code",
-      "agent_framework": "smolagents_code"
+      "agent_name": "OpenAI Solo",
+      "agent_framework": "openai_solo"
     }
   },
   "evaluations": [
     {
-      "evaluation_id": "appworld/test_normal/smolagents-code__openai_gpt-5.2-2025-12-11/1774263615.0201504",
+      "evaluation_id": "appworld/test_normal/openai-solo__openai_gpt-5.2-2025-12-11/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -42,23 +42,23 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.071,
+            "score": 0.0,
             "uncertainty": {
               "num_samples": 100
             },
             "details": {
-              "average_agent_cost": "0.55",
-              "total_run_cost": "55.03",
-              "average_steps": "51.59",
-              "percent_finished": "0.61"
+              "average_agent_cost": "0.0",
+              "total_run_cost": "0.0",
+              "average_steps": "0.0",
+              "percent_finished": "0.0"
             }
           },
           "generation_config": {
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "SmolAgents Code",
-                  "agent_framework": "smolagents_code"
+                  "agent_name": "OpenAI Solo",
+                  "agent_framework": "openai_solo"
                 }
               }
             }
@@ -70,15 +70,15 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "SmolAgents Code",
-              "agent_framework": "smolagents_code"
+              "agent_name": "OpenAI Solo",
+              "agent_framework": "openai_solo"
             }
           }
         }
       }
     },
     {
-      "evaluation_id": "appworld/test_normal/openai-solo__openai_gpt-5.2-2025-12-11/1774263615.0201504",
+      "evaluation_id": "appworld/test_normal/smolagents-code__openai_gpt-5.2-2025-12-11/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -110,23 +110,23 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0,
+            "score": 0.071,
             "uncertainty": {
               "num_samples": 100
             },
             "details": {
-              "average_agent_cost": "0.0",
-              "total_run_cost": "0.0",
-              "average_steps": "0.0",
-              "percent_finished": "0.0"
+              "average_agent_cost": "0.55",
+              "total_run_cost": "55.03",
+              "average_steps": "51.59",
+              "percent_finished": "0.61"
             }
           },
           "generation_config": {
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "OpenAI Solo",
-                  "agent_framework": "openai_solo"
+                  "agent_name": "SmolAgents Code",
+                  "agent_framework": "smolagents_code"
                 }
               }
             }
@@ -138,15 +138,15 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "OpenAI Solo",
-              "agent_framework": "openai_solo"
+              "agent_name": "SmolAgents Code",
+              "agent_framework": "smolagents_code"
             }
           }
         }
       }
     },
     {
-      "evaluation_id": "appworld/test_normal/litellm-tool-calling__openai_gpt-5.2-2025-12-11/1774263615.0201504",
+      "evaluation_id": "appworld/test_normal/litellm-tool-calling-with-shortlisting__openai_gpt-5.2-2025-12-11/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -178,23 +178,23 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0,
+            "score": 0.22,
             "uncertainty": {
               "num_samples": 100
             },
             "details": {
-              "average_agent_cost": "0.0",
-              "total_run_cost": "0.0",
-              "average_steps": "0.0",
-              "percent_finished": "0.0"
+              "average_agent_cost": "0.36",
+              "total_run_cost": "36.37",
+              "average_steps": "10.05",
+              "percent_finished": "1.0"
             }
           },
           "generation_config": {
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "LiteLLM Tool Calling",
-                  "agent_framework": "tool_calling"
+                  "agent_name": "LiteLLM Tool Calling with Shortlisting",
+                  "agent_framework": "tool_calling_with_shortlisting"
                 }
               }
             }
@@ -206,15 +206,15 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "LiteLLM Tool Calling",
-              "agent_framework": "tool_calling"
+              "agent_name": "LiteLLM Tool Calling with Shortlisting",
+              "agent_framework": "tool_calling_with_shortlisting"
             }
           }
         }
       }
     },
     {
-      "evaluation_id": "appworld/test_normal/litellm-tool-calling-with-shortlisting__openai_gpt-5.2-2025-12-11/1774263615.0201504",
+      "evaluation_id": "appworld/test_normal/litellm-tool-calling__openai_gpt-5.2-2025-12-11/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -246,23 +246,23 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.22,
+            "score": 0.0,
             "uncertainty": {
               "num_samples": 100
             },
             "details": {
-              "average_agent_cost": "0.36",
-              "total_run_cost": "36.37",
-              "average_steps": "10.05",
-              "percent_finished": "1.0"
+              "average_agent_cost": "0.0",
+              "total_run_cost": "0.0",
+              "average_steps": "0.0",
+              "percent_finished": "0.0"
             }
           },
           "generation_config": {
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "LiteLLM Tool Calling with Shortlisting",
-                  "agent_framework": "tool_calling_with_shortlisting"
+                  "agent_name": "LiteLLM Tool Calling",
+                  "agent_framework": "tool_calling"
                 }
               }
             }
@@ -274,8 +274,8 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "LiteLLM Tool Calling with Shortlisting",
-              "agent_framework": "tool_calling_with_shortlisting"
+              "agent_name": "LiteLLM Tool Calling",
+              "agent_framework": "tool_calling"
             }
           }
         }
@@ -350,7 +350,7 @@
       }
     },
     {
-      "evaluation_id": "browsecompplus/openai-solo__openai_gpt-5.2-2025-12-11/1774263615.0201504",
+      "evaluation_id": "browsecompplus/claude-code-cli__openai_gpt-5.2-2025-12-11/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -382,14 +382,14 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.48,
+            "score": 0.43,
             "uncertainty": {
               "num_samples": 100
             },
             "details": {
-              "average_agent_cost": "0.38",
-              "total_run_cost": "38.21",
-              "average_steps": "14.27",
+              "average_agent_cost": "0.43",
+              "total_run_cost": "43.11",
+              "average_steps": "8.97",
               "percent_finished": "1.0"
             }
           },
@@ -397,8 +397,8 @@
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "OpenAI Solo",
-                  "agent_framework": "openai_solo"
+                  "agent_name": "Claude Code CLI",
+                  "agent_framework": "claude_code"
                 }
               }
             }
@@ -410,15 +410,15 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "OpenAI Solo",
-              "agent_framework": "openai_solo"
+              "agent_name": "Claude Code CLI",
+              "agent_framework": "claude_code"
             }
           }
         }
       }
     },
     {
-      "evaluation_id": "browsecompplus/litellm-tool-calling-with-shortlisting__openai_gpt-5.2-2025-12-11/1774263615.0201504",
+      "evaluation_id": "browsecompplus/openai-solo__openai_gpt-5.2-2025-12-11/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -450,23 +450,23 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.46,
+            "score": 0.48,
             "uncertainty": {
               "num_samples": 100
             },
             "details": {
-              "average_agent_cost": "0.3",
-              "total_run_cost": "29.78",
-              "average_steps": "8.14",
-              "percent_finished": "0.99"
+              "average_agent_cost": "0.38",
+              "total_run_cost": "38.21",
+              "average_steps": "14.27",
+              "percent_finished": "1.0"
             }
           },
           "generation_config": {
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "LiteLLM Tool Calling with Shortlisting",
-                  "agent_framework": "tool_calling_with_shortlisting"
+                  "agent_name": "OpenAI Solo",
+                  "agent_framework": "openai_solo"
                 }
               }
             }
@@ -478,8 +478,8 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "LiteLLM Tool Calling with Shortlisting",
-              "agent_framework": "tool_calling_with_shortlisting"
+              "agent_name": "OpenAI Solo",
+              "agent_framework": "openai_solo"
             }
           }
         }
@@ -554,7 +554,7 @@
       }
     },
     {
-      "evaluation_id": "browsecompplus/smolagents-code__openai_gpt-5.2-2025-12-11/1774263615.0201504",
+      "evaluation_id": "browsecompplus/litellm-tool-calling-with-shortlisting__openai_gpt-5.2-2025-12-11/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -586,14 +586,14 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.26,
+            "score": 0.46,
             "uncertainty": {
               "num_samples": 100
             },
             "details": {
-              "average_agent_cost": "0.17",
-              "total_run_cost": "17.31",
-              "average_steps": "6.57",
+              "average_agent_cost": "0.3",
+              "total_run_cost": "29.78",
+              "average_steps": "8.14",
               "percent_finished": "0.99"
             }
           },
@@ -601,8 +601,8 @@
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "SmolAgents Code",
-                  "agent_framework": "smolagents_code"
+                  "agent_name": "LiteLLM Tool Calling with Shortlisting",
+                  "agent_framework": "tool_calling_with_shortlisting"
                 }
               }
             }
@@ -614,15 +614,15 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "SmolAgents Code",
-              "agent_framework": "smolagents_code"
+              "agent_name": "LiteLLM Tool Calling with Shortlisting",
+              "agent_framework": "tool_calling_with_shortlisting"
             }
           }
         }
       }
     },
     {
-      "evaluation_id": "browsecompplus/claude-code-cli__openai_gpt-5.2-2025-12-11/1774263615.0201504",
+      "evaluation_id": "browsecompplus/smolagents-code__openai_gpt-5.2-2025-12-11/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -654,23 +654,23 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.43,
+            "score": 0.26,
             "uncertainty": {
               "num_samples": 100
             },
             "details": {
-              "average_agent_cost": "0.43",
-              "total_run_cost": "43.11",
-              "average_steps": "8.97",
-              "percent_finished": "1.0"
+              "average_agent_cost": "0.17",
+              "total_run_cost": "17.31",
+              "average_steps": "6.57",
+              "percent_finished": "0.99"
             }
           },
           "generation_config": {
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "Claude Code CLI",
-                  "agent_framework": "claude_code"
+                  "agent_name": "SmolAgents Code",
+                  "agent_framework": "smolagents_code"
                 }
               }
             }
@@ -682,8 +682,8 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "Claude Code CLI",
-              "agent_framework": "claude_code"
+              "agent_name": "SmolAgents Code",
+              "agent_framework": "smolagents_code"
             }
           }
         }
@@ -769,7 +769,7 @@
       "generation_config": null
     },
     {
-      "evaluation_id": "swe-bench/claude-code-cli__openai_gpt-5.2-2025-12-11/1774263615.0201504",
+      "evaluation_id": "swe-bench/litellm-tool-calling__openai_gpt-5.2-2025-12-11/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -801,14 +801,14 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.58,
+            "score": 0.57,
             "uncertainty": {
               "num_samples": 100
             },
             "details": {
-              "average_agent_cost": "0.94",
-              "total_run_cost": "93.98",
-              "average_steps": "23.99",
+              "average_agent_cost": "0.25",
+              "total_run_cost": "24.76",
+              "average_steps": "20.47",
               "percent_finished": "1.0"
             }
           },
@@ -816,8 +816,8 @@
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "Claude Code CLI",
-                  "agent_framework": "claude_code"
+                  "agent_name": "LiteLLM Tool Calling",
+                  "agent_framework": "tool_calling"
                 }
               }
             }
@@ -829,15 +829,15 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "Claude Code CLI",
-              "agent_framework": "claude_code"
+              "agent_name": "LiteLLM Tool Calling",
+              "agent_framework": "tool_calling"
             }
           }
         }
       }
     },
     {
-      "evaluation_id": "swe-bench/litellm-tool-calling-with-shortlisting__openai_gpt-5.2-2025-12-11/1774263615.0201504",
+      "evaluation_id": "swe-bench/openai-solo__openai_gpt-5.2-2025-12-11/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -869,14 +869,14 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.57,
+            "score": 0.5455,
             "uncertainty": {
-              "num_samples": 100
+              "num_samples": 99
             },
             "details": {
-              "average_agent_cost": "0.25",
-              "total_run_cost": "24.76",
-              "average_steps": "20.47",
+              "average_agent_cost": "0.26",
+              "total_run_cost": "25.64",
+              "average_steps": "20.44",
               "percent_finished": "1.0"
             }
           },
@@ -884,8 +884,8 @@
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "LiteLLM Tool Calling with Shortlisting",
-                  "agent_framework": "tool_calling_with_shortlisting"
+                  "agent_name": "OpenAI Solo",
+                  "agent_framework": "openai_solo"
                 }
               }
             }
@@ -897,15 +897,15 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "LiteLLM Tool Calling with Shortlisting",
-              "agent_framework": "tool_calling_with_shortlisting"
+              "agent_name": "OpenAI Solo",
+              "agent_framework": "openai_solo"
             }
           }
         }
       }
     },
     {
-      "evaluation_id": "swe-bench/litellm-tool-calling__openai_gpt-5.2-2025-12-11/1774263615.0201504",
+      "evaluation_id": "swe-bench/smolagents-code__openai_gpt-5.2-2025-12-11/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -937,14 +937,14 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.57,
+            "score": 0.5253,
             "uncertainty": {
-              "num_samples": 100
+              "num_samples": 99
             },
             "details": {
-              "average_agent_cost": "0.25",
-              "total_run_cost": "24.76",
-              "average_steps": "20.47",
+              "average_agent_cost": "0.45",
+              "total_run_cost": "44.58",
+              "average_steps": "19.98",
               "percent_finished": "1.0"
             }
           },
@@ -952,8 +952,8 @@
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "LiteLLM Tool Calling",
-                  "agent_framework": "tool_calling"
+                  "agent_name": "SmolAgents Code",
+                  "agent_framework": "smolagents_code"
                 }
               }
             }
@@ -965,15 +965,15 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "LiteLLM Tool Calling",
-              "agent_framework": "tool_calling"
+              "agent_name": "SmolAgents Code",
+              "agent_framework": "smolagents_code"
             }
           }
         }
       }
     },
     {
-      "evaluation_id": "swe-bench/smolagents-code__openai_gpt-5.2-2025-12-11/1774263615.0201504",
+      "evaluation_id": "swe-bench/claude-code-cli__openai_gpt-5.2-2025-12-11/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -1005,14 +1005,14 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5253,
+            "score": 0.58,
             "uncertainty": {
-              "num_samples": 99
+              "num_samples": 100
             },
             "details": {
-              "average_agent_cost": "0.45",
-              "total_run_cost": "44.58",
-              "average_steps": "19.98",
+              "average_agent_cost": "0.94",
+              "total_run_cost": "93.98",
+              "average_steps": "23.99",
               "percent_finished": "1.0"
             }
           },
@@ -1020,8 +1020,8 @@
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "SmolAgents Code",
-                  "agent_framework": "smolagents_code"
+                  "agent_name": "Claude Code CLI",
+                  "agent_framework": "claude_code"
                 }
               }
             }
@@ -1033,15 +1033,15 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "SmolAgents Code",
-              "agent_framework": "smolagents_code"
+              "agent_name": "Claude Code CLI",
+              "agent_framework": "claude_code"
             }
           }
         }
       }
     },
     {
-      "evaluation_id": "swe-bench/openai-solo__openai_gpt-5.2-2025-12-11/1774263615.0201504",
+      "evaluation_id": "tau-bench-2/airline/openai-solo__openai_gpt-5.2-2025-12-11/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -1054,33 +1054,33 @@
         "name": "exgentic",
         "version": "0.1.0"
       },
-      "benchmark": "swe-bench",
+      "benchmark": "tau-bench-2_airline",
       "evaluation_results": [
         {
-          "evaluation_name": "swe-bench",
+          "evaluation_name": "tau-bench-2/airline",
           "source_data": {
-            "dataset_name": "swe-bench",
+            "dataset_name": "tau-bench-2/airline",
             "source_type": "url",
             "url": [
               "https://github.com/Exgentic/exgentic"
             ]
           },
           "metric_config": {
-            "evaluation_description": "SWE-bench benchmark evaluation",
+            "evaluation_description": "Tau Bench 2 benchmark evaluation (airline subset)",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5455,
+            "score": 0.5,
             "uncertainty": {
-              "num_samples": 99
+              "num_samples": 50
             },
             "details": {
-              "average_agent_cost": "0.26",
-              "total_run_cost": "25.64",
-              "average_steps": "20.44",
+              "average_agent_cost": "0.11",
+              "total_run_cost": "5.77",
+              "average_steps": "11.4",
               "percent_finished": "1.0"
             }
           },
@@ -1109,7 +1109,7 @@
       }
     },
     {
-      "evaluation_id": "tau-bench-2/airline/claude-code-cli__openai_gpt-5.2-2025-12-11/1774263615.0201504",
+      "evaluation_id": "swe-bench/litellm-tool-calling-with-shortlisting__openai_gpt-5.2-2025-12-11/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -1122,33 +1122,33 @@
         "name": "exgentic",
         "version": "0.1.0"
       },
-      "benchmark": "tau-bench-2_airline",
+      "benchmark": "swe-bench",
       "evaluation_results": [
         {
-          "evaluation_name": "tau-bench-2/airline",
+          "evaluation_name": "swe-bench",
           "source_data": {
-            "dataset_name": "tau-bench-2/airline",
+            "dataset_name": "swe-bench",
             "source_type": "url",
             "url": [
               "https://github.com/Exgentic/exgentic"
             ]
           },
           "metric_config": {
-            "evaluation_description": "Tau Bench 2 benchmark evaluation (airline subset)",
+            "evaluation_description": "SWE-bench benchmark evaluation",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.48,
+            "score": 0.57,
             "uncertainty": {
-              "num_samples": 50
+              "num_samples": 100
             },
             "details": {
-              "average_agent_cost": "0.21",
-              "total_run_cost": "11.23",
-              "average_steps": "10.18",
+              "average_agent_cost": "0.25",
+              "total_run_cost": "24.76",
+              "average_steps": "20.47",
               "percent_finished": "1.0"
             }
           },
@@ -1156,8 +1156,8 @@
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "Claude Code CLI",
-                  "agent_framework": "claude_code"
+                  "agent_name": "LiteLLM Tool Calling with Shortlisting",
+                  "agent_framework": "tool_calling_with_shortlisting"
                 }
               }
             }
@@ -1169,15 +1169,15 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "Claude Code CLI",
-              "agent_framework": "claude_code"
+              "agent_name": "LiteLLM Tool Calling with Shortlisting",
+              "agent_framework": "tool_calling_with_shortlisting"
             }
           }
         }
       }
     },
     {
-      "evaluation_id": "tau-bench-2/airline/openai-solo__openai_gpt-5.2-2025-12-11/1774263615.0201504",
+      "evaluation_id": "tau-bench-2/airline/litellm-tool-calling-with-shortlisting__openai_gpt-5.2-2025-12-11/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -1209,14 +1209,14 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5,
+            "score": 0.54,
             "uncertainty": {
               "num_samples": 50
             },
             "details": {
-              "average_agent_cost": "0.11",
-              "total_run_cost": "5.77",
-              "average_steps": "11.4",
+              "average_agent_cost": "0.13",
+              "total_run_cost": "6.96",
+              "average_steps": "11.22",
               "percent_finished": "1.0"
             }
           },
@@ -1224,8 +1224,8 @@
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "OpenAI Solo",
-                  "agent_framework": "openai_solo"
+                  "agent_name": "LiteLLM Tool Calling with Shortlisting",
+                  "agent_framework": "tool_calling_with_shortlisting"
                 }
               }
             }
@@ -1237,15 +1237,15 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "OpenAI Solo",
-              "agent_framework": "openai_solo"
+              "agent_name": "LiteLLM Tool Calling with Shortlisting",
+              "agent_framework": "tool_calling_with_shortlisting"
             }
           }
         }
       }
     },
     {
-      "evaluation_id": "tau-bench-2/airline/litellm-tool-calling__openai_gpt-5.2-2025-12-11/1774263615.0201504",
+      "evaluation_id": "tau-bench-2/airline/claude-code-cli__openai_gpt-5.2-2025-12-11/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -1277,14 +1277,14 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.54,
+            "score": 0.48,
             "uncertainty": {
               "num_samples": 50
             },
             "details": {
-              "average_agent_cost": "0.13",
-              "total_run_cost": "6.96",
-              "average_steps": "11.22",
+              "average_agent_cost": "0.21",
+              "total_run_cost": "11.23",
+              "average_steps": "10.18",
               "percent_finished": "1.0"
             }
           },
@@ -1292,8 +1292,8 @@
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "LiteLLM Tool Calling",
-                  "agent_framework": "tool_calling"
+                  "agent_name": "Claude Code CLI",
+                  "agent_framework": "claude_code"
                 }
               }
             }
@@ -1305,15 +1305,15 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "LiteLLM Tool Calling",
-              "agent_framework": "tool_calling"
+              "agent_name": "Claude Code CLI",
+              "agent_framework": "claude_code"
             }
           }
         }
       }
     },
     {
-      "evaluation_id": "tau-bench-2/airline/litellm-tool-calling-with-shortlisting__openai_gpt-5.2-2025-12-11/1774263615.0201504",
+      "evaluation_id": "tau-bench-2/airline/litellm-tool-calling__openai_gpt-5.2-2025-12-11/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -1360,8 +1360,8 @@
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "LiteLLM Tool Calling with Shortlisting",
-                  "agent_framework": "tool_calling_with_shortlisting"
+                  "agent_name": "LiteLLM Tool Calling",
+                  "agent_framework": "tool_calling"
                 }
               }
             }
@@ -1373,15 +1373,15 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "LiteLLM Tool Calling with Shortlisting",
-              "agent_framework": "tool_calling_with_shortlisting"
+              "agent_name": "LiteLLM Tool Calling",
+              "agent_framework": "tool_calling"
             }
           }
         }
       }
     },
     {
-      "evaluation_id": "tau-bench-2/retail/smolagents-code__openai_gpt-5.2-2025-12-11/1774263615.0201504",
+      "evaluation_id": "tau-bench-2/airline/smolagents-code__openai_gpt-5.2-2025-12-11/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -1394,33 +1394,33 @@
         "name": "exgentic",
         "version": "0.1.0"
       },
-      "benchmark": "tau-bench-2_retail",
+      "benchmark": "tau-bench-2_airline",
       "evaluation_results": [
         {
-          "evaluation_name": "tau-bench-2/retail",
+          "evaluation_name": "tau-bench-2/airline",
           "source_data": {
-            "dataset_name": "tau-bench-2/retail",
+            "dataset_name": "tau-bench-2/airline",
             "source_type": "url",
             "url": [
               "https://github.com/Exgentic/exgentic"
             ]
           },
           "metric_config": {
-            "evaluation_description": "Tau Bench 2 benchmark evaluation (retail subset)",
+            "evaluation_description": "Tau Bench 2 benchmark evaluation (airline subset)",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.68,
+            "score": 0.6,
             "uncertainty": {
-              "num_samples": 100
+              "num_samples": 50
             },
             "details": {
-              "average_agent_cost": "0.25",
-              "total_run_cost": "26.27",
-              "average_steps": "11.08",
+              "average_agent_cost": "0.29",
+              "total_run_cost": "15.28",
+              "average_steps": "10.68",
               "percent_finished": "1.0"
             }
           },
@@ -1449,7 +1449,7 @@
       }
     },
     {
-      "evaluation_id": "tau-bench-2/retail/claude-code-cli__openai_gpt-5.2-2025-12-11/1774263615.0201504",
+      "evaluation_id": "tau-bench-2/retail/openai-solo__openai_gpt-5.2-2025-12-11/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -1481,23 +1481,23 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.51,
+            "score": 0.5354,
             "uncertainty": {
               "num_samples": 100
             },
             "details": {
-              "average_agent_cost": "0.12",
-              "total_run_cost": "12.63",
-              "average_steps": "9.92",
-              "percent_finished": "0.98"
+              "average_agent_cost": "0.11",
+              "total_run_cost": "11.54",
+              "average_steps": "9.55",
+              "percent_finished": "0.99"
             }
           },
           "generation_config": {
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "Claude Code CLI",
-                  "agent_framework": "claude_code"
+                  "agent_name": "OpenAI Solo",
+                  "agent_framework": "openai_solo"
                 }
               }
             }
@@ -1509,15 +1509,15 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "Claude Code CLI",
-              "agent_framework": "claude_code"
+              "agent_name": "OpenAI Solo",
+              "agent_framework": "openai_solo"
             }
           }
         }
       }
     },
     {
-      "evaluation_id": "tau-bench-2/airline/smolagents-code__openai_gpt-5.2-2025-12-11/1774263615.0201504",
+      "evaluation_id": "tau-bench-2/retail/litellm-tool-calling-with-shortlisting__openai_gpt-5.2-2025-12-11/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -1530,33 +1530,33 @@
         "name": "exgentic",
         "version": "0.1.0"
       },
-      "benchmark": "tau-bench-2_airline",
+      "benchmark": "tau-bench-2_retail",
       "evaluation_results": [
         {
-          "evaluation_name": "tau-bench-2/airline",
+          "evaluation_name": "tau-bench-2/retail",
           "source_data": {
-            "dataset_name": "tau-bench-2/airline",
+            "dataset_name": "tau-bench-2/retail",
             "source_type": "url",
             "url": [
               "https://github.com/Exgentic/exgentic"
             ]
           },
           "metric_config": {
-            "evaluation_description": "Tau Bench 2 benchmark evaluation (airline subset)",
+            "evaluation_description": "Tau Bench 2 benchmark evaluation (retail subset)",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6,
+            "score": 0.73,
             "uncertainty": {
-              "num_samples": 50
+              "num_samples": 100
             },
             "details": {
-              "average_agent_cost": "0.29",
-              "total_run_cost": "15.28",
-              "average_steps": "10.68",
+              "average_agent_cost": "0.11",
+              "total_run_cost": "12.27",
+              "average_steps": "10.33",
               "percent_finished": "1.0"
             }
           },
@@ -1564,8 +1564,8 @@
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "SmolAgents Code",
-                  "agent_framework": "smolagents_code"
+                  "agent_name": "LiteLLM Tool Calling with Shortlisting",
+                  "agent_framework": "tool_calling_with_shortlisting"
                 }
               }
             }
@@ -1577,15 +1577,15 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "SmolAgents Code",
-              "agent_framework": "smolagents_code"
+              "agent_name": "LiteLLM Tool Calling with Shortlisting",
+              "agent_framework": "tool_calling_with_shortlisting"
             }
           }
         }
       }
     },
     {
-      "evaluation_id": "tau-bench-2/retail/openai-solo__openai_gpt-5.2-2025-12-11/1774263615.0201504",
+      "evaluation_id": "tau-bench-2/retail/litellm-tool-calling__openai_gpt-5.2-2025-12-11/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -1617,23 +1617,23 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5354,
+            "score": 0.73,
             "uncertainty": {
               "num_samples": 100
             },
             "details": {
               "average_agent_cost": "0.11",
-              "total_run_cost": "11.54",
-              "average_steps": "9.55",
-              "percent_finished": "0.99"
+              "total_run_cost": "12.27",
+              "average_steps": "10.33",
+              "percent_finished": "1.0"
             }
           },
           "generation_config": {
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "OpenAI Solo",
-                  "agent_framework": "openai_solo"
+                  "agent_name": "LiteLLM Tool Calling",
+                  "agent_framework": "tool_calling"
                 }
               }
             }
@@ -1645,15 +1645,15 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "OpenAI Solo",
-              "agent_framework": "openai_solo"
+              "agent_name": "LiteLLM Tool Calling",
+              "agent_framework": "tool_calling"
             }
           }
         }
       }
     },
     {
-      "evaluation_id": "tau-bench-2/retail/litellm-tool-calling__openai_gpt-5.2-2025-12-11/1774263615.0201504",
+      "evaluation_id": "tau-bench-2/retail/claude-code-cli__openai_gpt-5.2-2025-12-11/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -1685,23 +1685,23 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.73,
+            "score": 0.51,
             "uncertainty": {
               "num_samples": 100
             },
             "details": {
-              "average_agent_cost": "0.11",
-              "total_run_cost": "12.27",
-              "average_steps": "10.33",
-              "percent_finished": "1.0"
+              "average_agent_cost": "0.12",
+              "total_run_cost": "12.63",
+              "average_steps": "9.92",
+              "percent_finished": "0.98"
             }
           },
           "generation_config": {
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "LiteLLM Tool Calling",
-                  "agent_framework": "tool_calling"
+                  "agent_name": "Claude Code CLI",
+                  "agent_framework": "claude_code"
                 }
               }
             }
@@ -1713,15 +1713,15 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "LiteLLM Tool Calling",
-              "agent_framework": "tool_calling"
+              "agent_name": "Claude Code CLI",
+              "agent_framework": "claude_code"
             }
           }
         }
       }
     },
     {
-      "evaluation_id": "tau-bench-2/retail/litellm-tool-calling-with-shortlisting__openai_gpt-5.2-2025-12-11/1774263615.0201504",
+      "evaluation_id": "tau-bench-2/retail/smolagents-code__openai_gpt-5.2-2025-12-11/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -1753,14 +1753,14 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.73,
+            "score": 0.68,
             "uncertainty": {
               "num_samples": 100
             },
             "details": {
-              "average_agent_cost": "0.11",
-              "total_run_cost": "12.27",
-              "average_steps": "10.33",
+              "average_agent_cost": "0.25",
+              "total_run_cost": "26.27",
+              "average_steps": "11.08",
               "percent_finished": "1.0"
             }
           },
@@ -1768,8 +1768,8 @@
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "LiteLLM Tool Calling with Shortlisting",
-                  "agent_framework": "tool_calling_with_shortlisting"
+                  "agent_name": "SmolAgents Code",
+                  "agent_framework": "smolagents_code"
                 }
               }
             }
@@ -1781,15 +1781,15 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "LiteLLM Tool Calling with Shortlisting",
-              "agent_framework": "tool_calling_with_shortlisting"
+              "agent_name": "SmolAgents Code",
+              "agent_framework": "smolagents_code"
             }
           }
         }
       }
     },
     {
-      "evaluation_id": "tau-bench-2/telecom/openai-solo__openai_gpt-5.2-2025-12-11/1774263615.0201504",
+      "evaluation_id": "tau-bench-2/telecom/litellm-tool-calling-with-shortlisting__openai_gpt-5.2-2025-12-11/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -1821,23 +1821,23 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.53,
+            "score": 0.5354,
             "uncertainty": {
               "num_samples": 100
             },
             "details": {
-              "average_agent_cost": "0.15",
-              "total_run_cost": "18.88",
-              "average_steps": "9.92",
-              "percent_finished": "1.0"
+              "average_agent_cost": "0.14",
+              "total_run_cost": "19.92",
+              "average_steps": "10.18",
+              "percent_finished": "0.99"
             }
           },
           "generation_config": {
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "OpenAI Solo",
-                  "agent_framework": "openai_solo"
+                  "agent_name": "LiteLLM Tool Calling with Shortlisting",
+                  "agent_framework": "tool_calling_with_shortlisting"
                 }
               }
             }
@@ -1849,15 +1849,15 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "OpenAI Solo",
-              "agent_framework": "openai_solo"
+              "agent_name": "LiteLLM Tool Calling with Shortlisting",
+              "agent_framework": "tool_calling_with_shortlisting"
             }
           }
         }
       }
     },
     {
-      "evaluation_id": "tau-bench-2/telecom/claude-code-cli__openai_gpt-5.2-2025-12-11/1774263615.0201504",
+      "evaluation_id": "tau-bench-2/telecom/smolagents-code__openai_gpt-5.2-2025-12-11/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -1889,14 +1889,14 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.55,
+            "score": 0.71,
             "uncertainty": {
               "num_samples": 100
             },
             "details": {
-              "average_agent_cost": "0.1",
-              "total_run_cost": "15.15",
-              "average_steps": "9.36",
+              "average_agent_cost": "0.3",
+              "total_run_cost": "35.31",
+              "average_steps": "10.11",
               "percent_finished": "1.0"
             }
           },
@@ -1904,8 +1904,8 @@
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "Claude Code CLI",
-                  "agent_framework": "claude_code"
+                  "agent_name": "SmolAgents Code",
+                  "agent_framework": "smolagents_code"
                 }
               }
             }
@@ -1917,15 +1917,15 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "Claude Code CLI",
-              "agent_framework": "claude_code"
+              "agent_name": "SmolAgents Code",
+              "agent_framework": "smolagents_code"
             }
           }
         }
       }
     },
     {
-      "evaluation_id": "tau-bench-2/telecom/litellm-tool-calling-with-shortlisting__openai_gpt-5.2-2025-12-11/1774263615.0201504",
+      "evaluation_id": "tau-bench-2/telecom/openai-solo__openai_gpt-5.2-2025-12-11/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -1957,23 +1957,23 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5354,
+            "score": 0.53,
             "uncertainty": {
               "num_samples": 100
             },
             "details": {
-              "average_agent_cost": "0.14",
-              "total_run_cost": "19.92",
-              "average_steps": "10.18",
-              "percent_finished": "0.99"
+              "average_agent_cost": "0.15",
+              "total_run_cost": "18.88",
+              "average_steps": "9.92",
+              "percent_finished": "1.0"
             }
           },
           "generation_config": {
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "LiteLLM Tool Calling with Shortlisting",
-                  "agent_framework": "tool_calling_with_shortlisting"
+                  "agent_name": "OpenAI Solo",
+                  "agent_framework": "openai_solo"
                 }
               }
             }
@@ -1985,15 +1985,15 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "LiteLLM Tool Calling with Shortlisting",
-              "agent_framework": "tool_calling_with_shortlisting"
+              "agent_name": "OpenAI Solo",
+              "agent_framework": "openai_solo"
             }
           }
         }
       }
     },
     {
-      "evaluation_id": "tau-bench-2/telecom/litellm-tool-calling__openai_gpt-5.2-2025-12-11/1774263615.0201504",
+      "evaluation_id": "tau-bench-2/telecom/claude-code-cli__openai_gpt-5.2-2025-12-11/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -2025,23 +2025,23 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5354,
+            "score": 0.55,
             "uncertainty": {
               "num_samples": 100
             },
             "details": {
-              "average_agent_cost": "0.14",
-              "total_run_cost": "19.92",
-              "average_steps": "10.18",
-              "percent_finished": "0.99"
+              "average_agent_cost": "0.1",
+              "total_run_cost": "15.15",
+              "average_steps": "9.36",
+              "percent_finished": "1.0"
             }
           },
           "generation_config": {
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "LiteLLM Tool Calling",
-                  "agent_framework": "tool_calling"
+                  "agent_name": "Claude Code CLI",
+                  "agent_framework": "claude_code"
                 }
               }
             }
@@ -2053,15 +2053,15 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "LiteLLM Tool Calling",
-              "agent_framework": "tool_calling"
+              "agent_name": "Claude Code CLI",
+              "agent_framework": "claude_code"
             }
           }
         }
       }
     },
     {
-      "evaluation_id": "tau-bench-2/telecom/smolagents-code__openai_gpt-5.2-2025-12-11/1774263615.0201504",
+      "evaluation_id": "tau-bench-2/telecom/litellm-tool-calling__openai_gpt-5.2-2025-12-11/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -2093,23 +2093,23 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.71,
+            "score": 0.5354,
             "uncertainty": {
               "num_samples": 100
             },
             "details": {
-              "average_agent_cost": "0.3",
-              "total_run_cost": "35.31",
-              "average_steps": "10.11",
-              "percent_finished": "1.0"
+              "average_agent_cost": "0.14",
+              "total_run_cost": "19.92",
+              "average_steps": "10.18",
+              "percent_finished": "0.99"
             }
           },
           "generation_config": {
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "SmolAgents Code",
-                  "agent_framework": "smolagents_code"
+                  "agent_name": "LiteLLM Tool Calling",
+                  "agent_framework": "tool_calling"
                 }
               }
             }
@@ -2121,8 +2121,8 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "SmolAgents Code",
-              "agent_framework": "smolagents_code"
+              "agent_name": "LiteLLM Tool Calling",
+              "agent_framework": "tool_calling"
             }
           }
         }
diff --git a/data/models/openai_gpt-5.2.json b/data/models/openai_gpt-5.2.json
index 26fe4dd6a4fc6668b751e0d5655642084b59ba75..1f373630f767c55e79d63767d1456fe1b49fa7e4 100644
--- a/data/models/openai_gpt-5.2.json
+++ b/data/models/openai_gpt-5.2.json
@@ -84,7 +84,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/terminus-2__gpt-5.2/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/codex-cli__gpt-5.2/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -108,7 +108,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-12-12",
+          "evaluation_timestamp": "2025-12-18",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -117,17 +117,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 54.0,
+            "score": 62.9,
             "uncertainty": {
               "standard_error": {
-                "value": 2.9
+                "value": 3.0
               },
               "num_samples": 435
             }
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"GPT-5.2\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Codex CLI\" -m \"GPT-5.2\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -144,7 +144,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"GPT-5.2\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Codex CLI\" -m \"GPT-5.2\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -158,7 +158,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/mux__gpt-5.2/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/terminus-2__gpt-5.2/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -182,7 +182,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2026-01-17",
+          "evaluation_timestamp": "2025-12-12",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -191,11 +191,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 60.7
+            "score": 54.0,
+            "uncertainty": {
+              "standard_error": {
+                "value": 2.9
+              },
+              "num_samples": 435
+            }
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Mux\" -m \"GPT-5.2\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"GPT-5.2\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -212,7 +218,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Mux\" -m \"GPT-5.2\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"GPT-5.2\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -226,7 +232,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/codex-cli__gpt-5.2/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/mux__gpt-5.2/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -250,7 +256,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-12-18",
+          "evaluation_timestamp": "2026-01-17",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -259,17 +265,11 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 62.9,
-            "uncertainty": {
-              "standard_error": {
-                "value": 3.0
-              },
-              "num_samples": 435
-            }
+            "score": 60.7
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Codex CLI\" -m \"GPT-5.2\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Mux\" -m \"GPT-5.2\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -286,7 +286,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Codex CLI\" -m \"GPT-5.2\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Mux\" -m \"GPT-5.2\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
diff --git a/data/models/openai_gpt-5.3-codex.json b/data/models/openai_gpt-5.3-codex.json
index d48b8e986526c7f815b5efdb141e51c853537ca1..71af5af4fde2b8fad2d4e8ea66842bf1cb778d6d 100644
--- a/data/models/openai_gpt-5.3-codex.json
+++ b/data/models/openai_gpt-5.3-codex.json
@@ -84,7 +84,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/mux__gpt-5.3-codex/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/simple-codex__gpt-5.3-codex/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -108,7 +108,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2026-03-06",
+          "evaluation_timestamp": "2026-02-06",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -117,17 +117,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 74.6,
+            "score": 75.1,
             "uncertainty": {
               "standard_error": {
-                "value": 2.5
+                "value": 2.4
               },
               "num_samples": 435
             }
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Mux\" -m \"GPT-5.3-Codex\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Simple Codex\" -m \"GPT-5.3-Codex\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -144,7 +144,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Mux\" -m \"GPT-5.3-Codex\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Simple Codex\" -m \"GPT-5.3-Codex\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -158,7 +158,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/simple-codex__gpt-5.3-codex/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/droid__gpt-5.3-codex/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -182,7 +182,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2026-02-06",
+          "evaluation_timestamp": "2026-02-24",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -191,17 +191,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 75.1,
+            "score": 77.3,
             "uncertainty": {
               "standard_error": {
-                "value": 2.4
+                "value": 2.2
               },
               "num_samples": 435
             }
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Simple Codex\" -m \"GPT-5.3-Codex\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Droid\" -m \"GPT-5.3-Codex\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -218,7 +218,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Simple Codex\" -m \"GPT-5.3-Codex\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Droid\" -m \"GPT-5.3-Codex\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -306,7 +306,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/droid__gpt-5.3-codex/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/mux__gpt-5.3-codex/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -330,7 +330,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2026-02-24",
+          "evaluation_timestamp": "2026-03-06",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -339,17 +339,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 77.3,
+            "score": 74.6,
             "uncertainty": {
               "standard_error": {
-                "value": 2.2
+                "value": 2.5
               },
               "num_samples": 435
             }
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Droid\" -m \"GPT-5.3-Codex\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Mux\" -m \"GPT-5.3-Codex\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -366,7 +366,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Droid\" -m \"GPT-5.3-Codex\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Mux\" -m \"GPT-5.3-Codex\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
diff --git a/data/models/openai_gpt-5.json b/data/models/openai_gpt-5.json
index 539597ca005b6b7d3304665ed895ff7bb0860332..9d09df6c74b83cb2a4dd70946717742ac0b7c9f5 100644
--- a/data/models/openai_gpt-5.json
+++ b/data/models/openai_gpt-5.json
@@ -4,13 +4,13 @@
     "id": "openai/gpt-5",
     "developer": "OpenAI",
     "additional_details": {
-      "agent_name": "Terminus 2",
-      "agent_organization": "Terminal Bench"
+      "agent_name": "OpenHands",
+      "agent_organization": "OpenHands"
     }
   },
   "evaluations": [
     {
-      "evaluation_id": "terminal-bench-2.0/terminus-2__gpt-5/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/openhands__gpt-5/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -34,7 +34,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-10-31",
+          "evaluation_timestamp": "2025-11-02",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -43,17 +43,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 35.2,
+            "score": 43.8,
             "uncertainty": {
               "standard_error": {
-                "value": 3.1
+                "value": 3.0
               },
               "num_samples": 435
             }
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"GPT-5\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"OpenHands\" -m \"GPT-5\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -70,7 +70,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"GPT-5\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"OpenHands\" -m \"GPT-5\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -84,7 +84,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/mini-swe-agent__gpt-5/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/terminus-2__gpt-5/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -108,7 +108,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-11-03",
+          "evaluation_timestamp": "2025-10-31",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -117,17 +117,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 33.9,
+            "score": 35.2,
             "uncertainty": {
               "standard_error": {
-                "value": 2.9
+                "value": 3.1
               },
               "num_samples": 435
             }
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Mini-SWE-Agent\" -m \"GPT-5\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"GPT-5\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -144,7 +144,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Mini-SWE-Agent\" -m \"GPT-5\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"GPT-5\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -158,7 +158,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/openhands__gpt-5/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/mini-swe-agent__gpt-5/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -182,7 +182,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-11-02",
+          "evaluation_timestamp": "2025-11-03",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -191,17 +191,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 43.8,
+            "score": 33.9,
             "uncertainty": {
               "standard_error": {
-                "value": 3.0
+                "value": 2.9
               },
               "num_samples": 435
             }
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"OpenHands\" -m \"GPT-5\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Mini-SWE-Agent\" -m \"GPT-5\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -218,7 +218,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"OpenHands\" -m \"GPT-5\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Mini-SWE-Agent\" -m \"GPT-5\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
diff --git a/data/models/openai_gpt-oss-120b.json b/data/models/openai_gpt-oss-120b.json
index cc688cac8bf3c3ea698efc0de68329e08bff64c1..396f861a54b2b1a7762f9a8f0810f5cd018d5e52 100644
--- a/data/models/openai_gpt-oss-120b.json
+++ b/data/models/openai_gpt-oss-120b.json
@@ -310,7 +310,7 @@
       "generation_config": null
     },
     {
-      "evaluation_id": "terminal-bench-2.0/mini-swe-agent__gpt-oss-120b/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/terminus-2__gpt-oss-120b/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -334,7 +334,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-11-03",
+          "evaluation_timestamp": "2025-11-01",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -343,17 +343,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 14.2,
+            "score": 18.7,
             "uncertainty": {
               "standard_error": {
-                "value": 2.3
+                "value": 2.7
               },
               "num_samples": 435
             }
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Mini-SWE-Agent\" -m \"GPT-OSS-120B\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"GPT-OSS-120B\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -370,7 +370,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Mini-SWE-Agent\" -m \"GPT-OSS-120B\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"GPT-OSS-120B\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -384,7 +384,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/terminus-2__gpt-oss-120b/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/mini-swe-agent__gpt-oss-120b/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -408,7 +408,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-11-01",
+          "evaluation_timestamp": "2025-11-03",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -417,17 +417,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 18.7,
+            "score": 14.2,
             "uncertainty": {
               "standard_error": {
-                "value": 2.7
+                "value": 2.3
               },
               "num_samples": 435
             }
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"GPT-OSS-120B\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Mini-SWE-Agent\" -m \"GPT-OSS-120B\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -444,7 +444,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"GPT-OSS-120B\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Mini-SWE-Agent\" -m \"GPT-OSS-120B\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
diff --git a/data/models/openai_o4-mini-2025-04-16.json b/data/models/openai_o4-mini-2025-04-16.json
index 2445a24c2417bbf08441a2388a2fba31fa9d6f49..751e567f80107ae7403958c0915864809e731407 100644
--- a/data/models/openai_o4-mini-2025-04-16.json
+++ b/data/models/openai_o4-mini-2025-04-16.json
@@ -749,13 +749,13 @@
       }
     },
     {
-      "evaluation_id": "livecodebenchpro/o4-mini-2025-04-16/1770683238.099205",
-      "retrieved_timestamp": "1770683238.099205",
+      "evaluation_id": "livecodebenchpro/o4-mini-2025-04-16/1760492095.8105888",
+      "retrieved_timestamp": "1760492095.8105888",
       "source_metadata": {
+        "source_organization_name": "New York University,  Princeton University, University of California San Diego, University of Washington and Canyon Crest Academy",
+        "evaluator_relationship": "third_party",
         "source_name": "Live Code Bench Pro",
-        "source_type": "documentation",
-        "source_organization_name": "New York University, Princeton University, University of California San Diego, University of Washington and Canyon Crest Academy",
-        "evaluator_relationship": "third_party"
+        "source_type": "documentation"
       },
       "eval_library": {
         "name": "unknown",
@@ -765,62 +765,62 @@
       "evaluation_results": [
         {
           "evaluation_name": "Hard Problems",
+          "metric_config": {
+            "evaluation_description": "Pass@1 on Hard Problems",
+            "lower_is_better": false,
+            "score_type": "continuous",
+            "min_score": 0,
+            "max_score": 1
+          },
+          "score_details": {
+            "score": 0.014084507042253521
+          },
           "source_data": {
             "dataset_name": "Hard Problems",
             "source_type": "url",
             "url": [
               "https://webhook.cp-bench.orzzh.com/leaderboard/llm/difficulty?difficulty=hard&benchmark_mode=live"
             ]
-          },
+          }
+        },
+        {
+          "evaluation_name": "Medium Problems",
           "metric_config": {
-            "evaluation_description": "Pass@1 on Hard Problems",
+            "evaluation_description": "Pass@1 on Medium Problems",
             "lower_is_better": false,
             "score_type": "continuous",
-            "min_score": 0.0,
-            "max_score": 1.0
+            "min_score": 0,
+            "max_score": 1
           },
           "score_details": {
-            "score": 0.0143
-          }
-        },
-        {
-          "evaluation_name": "Medium Problems",
+            "score": 0.30985915492957744
+          },
           "source_data": {
             "dataset_name": "Medium Problems",
             "source_type": "url",
             "url": [
               "https://webhook.cp-bench.orzzh.com/leaderboard/llm/difficulty?difficulty=medium&benchmark_mode=live"
             ]
-          },
+          }
+        },
+        {
+          "evaluation_name": "Easy Problems",
           "metric_config": {
-            "evaluation_description": "Pass@1 on Medium Problems",
+            "evaluation_description": "Pass@1 on Easy Problems",
             "lower_is_better": false,
             "score_type": "continuous",
-            "min_score": 0.0,
-            "max_score": 1.0
+            "min_score": 0,
+            "max_score": 1
           },
           "score_details": {
-            "score": 0.2923
-          }
-        },
-        {
-          "evaluation_name": "Easy Problems",
+            "score": 0.8873239436619719
+          },
           "source_data": {
             "dataset_name": "Easy Problems",
             "source_type": "url",
             "url": [
               "https://webhook.cp-bench.orzzh.com/leaderboard/llm/difficulty?difficulty=easy&benchmark_mode=live"
             ]
-          },
-          "metric_config": {
-            "evaluation_description": "Pass@1 on Easy Problems",
-            "lower_is_better": false,
-            "score_type": "continuous",
-            "min_score": 0.0,
-            "max_score": 1.0
-          },
-          "score_details": {
-            "score": 0.8571
           }
         }
       ],
@@ -828,13 +828,13 @@
       "generation_config": null
     },
     {
-      "evaluation_id": "livecodebenchpro/o4-mini-2025-04-16/1760492095.8105888",
-      "retrieved_timestamp": "1760492095.8105888",
+      "evaluation_id": "livecodebenchpro/o4-mini-2025-04-16/1770683238.099205",
+      "retrieved_timestamp": "1770683238.099205",
       "source_metadata": {
-        "source_organization_name": "New York University,  Princeton University, University of California San Diego, University of Washington and Canyon Crest Academy",
-        "evaluator_relationship": "third_party",
         "source_name": "Live Code Bench Pro",
-        "source_type": "documentation"
+        "source_type": "documentation",
+        "source_organization_name": "New York University, Princeton University, University of California San Diego, University of Washington and Canyon Crest Academy",
+        "evaluator_relationship": "third_party"
       },
       "eval_library": {
         "name": "unknown",
@@ -844,62 +844,62 @@
       "evaluation_results": [
         {
           "evaluation_name": "Hard Problems",
-          "metric_config": {
-            "evaluation_description": "Pass@1 on Hard Problems",
-            "lower_is_better": false,
-            "score_type": "continuous",
-            "min_score": 0,
-            "max_score": 1
-          },
-          "score_details": {
-            "score": 0.014084507042253521
-          },
           "source_data": {
             "dataset_name": "Hard Problems",
             "source_type": "url",
             "url": [
               "https://webhook.cp-bench.orzzh.com/leaderboard/llm/difficulty?difficulty=hard&benchmark_mode=live"
             ]
-          }
-        },
-        {
-          "evaluation_name": "Medium Problems",
+          },
           "metric_config": {
-            "evaluation_description": "Pass@1 on Medium Problems",
+            "evaluation_description": "Pass@1 on Hard Problems",
             "lower_is_better": false,
             "score_type": "continuous",
-            "min_score": 0,
-            "max_score": 1
+            "min_score": 0.0,
+            "max_score": 1.0
           },
           "score_details": {
-            "score": 0.30985915492957744
-          },
+            "score": 0.0143
+          }
+        },
+        {
+          "evaluation_name": "Medium Problems",
           "source_data": {
             "dataset_name": "Medium Problems",
             "source_type": "url",
             "url": [
               "https://webhook.cp-bench.orzzh.com/leaderboard/llm/difficulty?difficulty=medium&benchmark_mode=live"
             ]
-          }
-        },
-        {
-          "evaluation_name": "Easy Problems",
+          },
           "metric_config": {
-            "evaluation_description": "Pass@1 on Easy Problems",
+            "evaluation_description": "Pass@1 on Medium Problems",
             "lower_is_better": false,
             "score_type": "continuous",
-            "min_score": 0,
-            "max_score": 1
+            "min_score": 0.0,
+            "max_score": 1.0
           },
           "score_details": {
-            "score": 0.8873239436619719
-          },
+            "score": 0.2923
+          }
+        },
+        {
+          "evaluation_name": "Easy Problems",
           "source_data": {
             "dataset_name": "Easy Problems",
             "source_type": "url",
             "url": [
               "https://webhook.cp-bench.orzzh.com/leaderboard/llm/difficulty?difficulty=easy&benchmark_mode=live"
             ]
+          },
+          "metric_config": {
+            "evaluation_description": "Pass@1 on Easy Problems",
+            "lower_is_better": false,
+            "score_type": "continuous",
+            "min_score": 0.0,
+            "max_score": 1.0
+          },
+          "score_details": {
+            "score": 0.8571
           }
         }
       ],
diff --git a/data/models/openassistant_oasst-rm-2-pythia-6.9b-epoch-1.json b/data/models/openassistant_oasst-rm-2-pythia-6.9b-epoch-1.json
index 34afb9663c74112d98337da6fd83b3594c465f50..cdfb6729d8ee2c00438e79bd148b5b9825fbce54 100644
--- a/data/models/openassistant_oasst-rm-2-pythia-6.9b-epoch-1.json
+++ b/data/models/openassistant_oasst-rm-2-pythia-6.9b-epoch-1.json
@@ -9,10 +9,10 @@
   },
   "evaluations": [
     {
-      "evaluation_id": "reward-bench/OpenAssistant_oasst-rm-2-pythia-6.9b-epoch-1/1766412838.146816",
+      "evaluation_id": "reward-bench-2/OpenAssistant_oasst-rm-2-pythia-6.9b-epoch-1/1766412838.146816",
       "retrieved_timestamp": "1766412838.146816",
       "source_metadata": {
-        "source_name": "RewardBench",
+        "source_name": "RewardBench 2",
         "source_type": "documentation",
         "source_organization_name": "Allen Institute for AI",
         "source_organization_url": "https://allenai.org",
@@ -31,109 +31,127 @@
         {
           "evaluation_name": "Score",
           "metric_config": {
-            "evaluation_description": "Overall RewardBench Score",
+            "evaluation_description": "Overall RewardBench 2 Score (mean of all metrics)",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.615
+            "score": 0.2653
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Chat",
+          "evaluation_name": "Factuality",
           "metric_config": {
-            "evaluation_description": "Chat accuracy - includes easy chat subsets",
+            "evaluation_description": "Factuality score - measures factual accuracy",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9246
+            "score": 0.3979
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Chat Hard",
+          "evaluation_name": "Precise IF",
           "metric_config": {
-            "evaluation_description": "Chat Hard accuracy - includes hard chat subsets",
+            "evaluation_description": "Precise Instruction Following score",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3728
+            "score": 0.2875
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
+          }
+        },
+        {
+          "evaluation_name": "Math",
+          "metric_config": {
+            "evaluation_description": "Math score - measures mathematical reasoning",
+            "lower_is_better": false,
+            "score_type": "continuous",
+            "min_score": 0.0,
+            "max_score": 1.0
+          },
+          "score_details": {
+            "score": 0.377
+          },
+          "source_data": {
+            "dataset_name": "RewardBench 2",
+            "source_type": "hf_dataset",
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
           "evaluation_name": "Safety",
           "metric_config": {
-            "evaluation_description": "Safety accuracy - includes safety subsets",
+            "evaluation_description": "Safety score - measures safety awareness",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5446
+            "score": 0.3289
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Reasoning",
+          "evaluation_name": "Focus",
           "metric_config": {
-            "evaluation_description": "Reasoning accuracy - includes code and math subsets",
+            "evaluation_description": "Focus score - measures response focus",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5855
+            "score": 0.1535
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Prior Sets (0.5 weight)",
+          "evaluation_name": "Ties",
           "metric_config": {
-            "evaluation_description": "Prior Sets score (weighted 0.5) - includes test sets",
+            "evaluation_description": "Ties score - ability to identify tie cases",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6801
+            "score": 0.047
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         }
       ],
@@ -141,10 +159,10 @@
       "generation_config": null
     },
     {
-      "evaluation_id": "reward-bench-2/OpenAssistant_oasst-rm-2-pythia-6.9b-epoch-1/1766412838.146816",
+      "evaluation_id": "reward-bench/OpenAssistant_oasst-rm-2-pythia-6.9b-epoch-1/1766412838.146816",
       "retrieved_timestamp": "1766412838.146816",
       "source_metadata": {
-        "source_name": "RewardBench 2",
+        "source_name": "RewardBench",
         "source_type": "documentation",
         "source_organization_name": "Allen Institute for AI",
         "source_organization_url": "https://allenai.org",
@@ -163,127 +181,109 @@
         {
           "evaluation_name": "Score",
           "metric_config": {
-            "evaluation_description": "Overall RewardBench 2 Score (mean of all metrics)",
-            "lower_is_better": false,
-            "score_type": "continuous",
-            "min_score": 0.0,
-            "max_score": 1.0
-          },
-          "score_details": {
-            "score": 0.2653
-          },
-          "source_data": {
-            "dataset_name": "RewardBench 2",
-            "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
-          }
-        },
-        {
-          "evaluation_name": "Factuality",
-          "metric_config": {
-            "evaluation_description": "Factuality score - measures factual accuracy",
+            "evaluation_description": "Overall RewardBench Score",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3979
+            "score": 0.615
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Precise IF",
+          "evaluation_name": "Chat",
           "metric_config": {
-            "evaluation_description": "Precise Instruction Following score",
+            "evaluation_description": "Chat accuracy - includes easy chat subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2875
+            "score": 0.9246
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Math",
+          "evaluation_name": "Chat Hard",
           "metric_config": {
-            "evaluation_description": "Math score - measures mathematical reasoning",
+            "evaluation_description": "Chat Hard accuracy - includes hard chat subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.377
+            "score": 0.3728
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
           "evaluation_name": "Safety",
           "metric_config": {
-            "evaluation_description": "Safety score - measures safety awareness",
+            "evaluation_description": "Safety accuracy - includes safety subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3289
+            "score": 0.5446
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Focus",
+          "evaluation_name": "Reasoning",
           "metric_config": {
-            "evaluation_description": "Focus score - measures response focus",
+            "evaluation_description": "Reasoning accuracy - includes code and math subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1535
+            "score": 0.5855
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Ties",
+          "evaluation_name": "Prior Sets (0.5 weight)",
           "metric_config": {
-            "evaluation_description": "Ties score - ability to identify tie cases",
+            "evaluation_description": "Prior Sets score (weighted 0.5) - includes test sets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.047
+            "score": 0.6801
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         }
       ],
diff --git a/data/models/openbmb_ultrarm-13b.json b/data/models/openbmb_ultrarm-13b.json
index 84bdd483e26f91976f0250093c6ea14b4f0ff97c..c52a509adb327ccd9798d5a844c78601940ebb17 100644
--- a/data/models/openbmb_ultrarm-13b.json
+++ b/data/models/openbmb_ultrarm-13b.json
@@ -9,10 +9,10 @@
   },
   "evaluations": [
     {
-      "evaluation_id": "reward-bench/openbmb_UltraRM-13b/1766412838.146816",
+      "evaluation_id": "reward-bench-2/openbmb_UltraRM-13b/1766412838.146816",
       "retrieved_timestamp": "1766412838.146816",
       "source_metadata": {
-        "source_name": "RewardBench",
+        "source_name": "RewardBench 2",
         "source_type": "documentation",
         "source_organization_name": "Allen Institute for AI",
         "source_organization_url": "https://allenai.org",
@@ -31,109 +31,127 @@
         {
           "evaluation_name": "Score",
           "metric_config": {
-            "evaluation_description": "Overall RewardBench Score",
+            "evaluation_description": "Overall RewardBench 2 Score (mean of all metrics)",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6903
+            "score": 0.4683
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Chat",
+          "evaluation_name": "Factuality",
           "metric_config": {
-            "evaluation_description": "Chat accuracy - includes easy chat subsets",
+            "evaluation_description": "Factuality score - measures factual accuracy",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9637
+            "score": 0.5063
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Chat Hard",
+          "evaluation_name": "Precise IF",
           "metric_config": {
-            "evaluation_description": "Chat Hard accuracy - includes hard chat subsets",
+            "evaluation_description": "Precise Instruction Following score",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5548
+            "score": 0.3312
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
+          }
+        },
+        {
+          "evaluation_name": "Math",
+          "metric_config": {
+            "evaluation_description": "Math score - measures mathematical reasoning",
+            "lower_is_better": false,
+            "score_type": "continuous",
+            "min_score": 0.0,
+            "max_score": 1.0
+          },
+          "score_details": {
+            "score": 0.5519
+          },
+          "source_data": {
+            "dataset_name": "RewardBench 2",
+            "source_type": "hf_dataset",
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
           "evaluation_name": "Safety",
           "metric_config": {
-            "evaluation_description": "Safety accuracy - includes safety subsets",
+            "evaluation_description": "Safety score - measures safety awareness",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5986
+            "score": 0.5089
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Reasoning",
+          "evaluation_name": "Focus",
           "metric_config": {
-            "evaluation_description": "Reasoning accuracy - includes code and math subsets",
+            "evaluation_description": "Focus score - measures response focus",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6244
+            "score": 0.6081
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Prior Sets (0.5 weight)",
+          "evaluation_name": "Ties",
           "metric_config": {
-            "evaluation_description": "Prior Sets score (weighted 0.5) - includes test sets",
+            "evaluation_description": "Ties score - ability to identify tie cases",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7294
+            "score": 0.3036
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         }
       ],
@@ -141,10 +159,10 @@
       "generation_config": null
     },
     {
-      "evaluation_id": "reward-bench-2/openbmb_UltraRM-13b/1766412838.146816",
+      "evaluation_id": "reward-bench/openbmb_UltraRM-13b/1766412838.146816",
       "retrieved_timestamp": "1766412838.146816",
       "source_metadata": {
-        "source_name": "RewardBench 2",
+        "source_name": "RewardBench",
         "source_type": "documentation",
         "source_organization_name": "Allen Institute for AI",
         "source_organization_url": "https://allenai.org",
@@ -163,127 +181,109 @@
         {
           "evaluation_name": "Score",
           "metric_config": {
-            "evaluation_description": "Overall RewardBench 2 Score (mean of all metrics)",
-            "lower_is_better": false,
-            "score_type": "continuous",
-            "min_score": 0.0,
-            "max_score": 1.0
-          },
-          "score_details": {
-            "score": 0.4683
-          },
-          "source_data": {
-            "dataset_name": "RewardBench 2",
-            "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
-          }
-        },
-        {
-          "evaluation_name": "Factuality",
-          "metric_config": {
-            "evaluation_description": "Factuality score - measures factual accuracy",
+            "evaluation_description": "Overall RewardBench Score",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5063
+            "score": 0.6903
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Precise IF",
+          "evaluation_name": "Chat",
           "metric_config": {
-            "evaluation_description": "Precise Instruction Following score",
+            "evaluation_description": "Chat accuracy - includes easy chat subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3312
+            "score": 0.9637
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Math",
+          "evaluation_name": "Chat Hard",
           "metric_config": {
-            "evaluation_description": "Math score - measures mathematical reasoning",
+            "evaluation_description": "Chat Hard accuracy - includes hard chat subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5519
+            "score": 0.5548
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
           "evaluation_name": "Safety",
           "metric_config": {
-            "evaluation_description": "Safety score - measures safety awareness",
+            "evaluation_description": "Safety accuracy - includes safety subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5089
+            "score": 0.5986
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Focus",
+          "evaluation_name": "Reasoning",
           "metric_config": {
-            "evaluation_description": "Focus score - measures response focus",
+            "evaluation_description": "Reasoning accuracy - includes code and math subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6081
+            "score": 0.6244
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Ties",
+          "evaluation_name": "Prior Sets (0.5 weight)",
           "metric_config": {
-            "evaluation_description": "Ties score - ability to identify tie cases",
+            "evaluation_description": "Prior Sets score (weighted 0.5) - includes test sets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3036
+            "score": 0.7294
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         }
       ],
diff --git a/data/models/pku-alignment_beaver-7b-v1.0-cost.json b/data/models/pku-alignment_beaver-7b-v1.0-cost.json
index 3777eba3edfdc470c669a503ac85994bf8139135..8e786484059e3101c1249c1cce8c4b2be81faa5a 100644
--- a/data/models/pku-alignment_beaver-7b-v1.0-cost.json
+++ b/data/models/pku-alignment_beaver-7b-v1.0-cost.json
@@ -9,10 +9,10 @@
   },
   "evaluations": [
     {
-      "evaluation_id": "reward-bench-2/PKU-Alignment_beaver-7b-v1.0-cost/1766412838.146816",
+      "evaluation_id": "reward-bench/PKU-Alignment_beaver-7b-v1.0-cost/1766412838.146816",
       "retrieved_timestamp": "1766412838.146816",
       "source_metadata": {
-        "source_name": "RewardBench 2",
+        "source_name": "RewardBench",
         "source_type": "documentation",
         "source_organization_name": "Allen Institute for AI",
         "source_organization_url": "https://allenai.org",
@@ -31,127 +31,109 @@
         {
           "evaluation_name": "Score",
           "metric_config": {
-            "evaluation_description": "Overall RewardBench 2 Score (mean of all metrics)",
-            "lower_is_better": false,
-            "score_type": "continuous",
-            "min_score": 0.0,
-            "max_score": 1.0
-          },
-          "score_details": {
-            "score": 0.3332
-          },
-          "source_data": {
-            "dataset_name": "RewardBench 2",
-            "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
-          }
-        },
-        {
-          "evaluation_name": "Factuality",
-          "metric_config": {
-            "evaluation_description": "Factuality score - measures factual accuracy",
+            "evaluation_description": "Overall RewardBench Score",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3263
+            "score": 0.5798
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Precise IF",
+          "evaluation_name": "Chat",
           "metric_config": {
-            "evaluation_description": "Precise Instruction Following score",
+            "evaluation_description": "Chat accuracy - includes easy chat subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2313
+            "score": 0.6173
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Math",
+          "evaluation_name": "Chat Hard",
           "metric_config": {
-            "evaluation_description": "Math score - measures mathematical reasoning",
+            "evaluation_description": "Chat Hard accuracy - includes hard chat subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3989
+            "score": 0.4232
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
           "evaluation_name": "Safety",
           "metric_config": {
-            "evaluation_description": "Safety score - measures safety awareness",
+            "evaluation_description": "Safety accuracy - includes safety subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7589
+            "score": 0.7351
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Focus",
+          "evaluation_name": "Reasoning",
           "metric_config": {
-            "evaluation_description": "Focus score - measures response focus",
+            "evaluation_description": "Reasoning accuracy - includes code and math subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2939
+            "score": 0.5482
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Ties",
+          "evaluation_name": "Prior Sets (0.5 weight)",
           "metric_config": {
-            "evaluation_description": "Ties score - ability to identify tie cases",
+            "evaluation_description": "Prior Sets score (weighted 0.5) - includes test sets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": -0.01
+            "score": 0.57
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         }
       ],
@@ -159,10 +141,10 @@
       "generation_config": null
     },
     {
-      "evaluation_id": "reward-bench/PKU-Alignment_beaver-7b-v1.0-cost/1766412838.146816",
+      "evaluation_id": "reward-bench-2/PKU-Alignment_beaver-7b-v1.0-cost/1766412838.146816",
       "retrieved_timestamp": "1766412838.146816",
       "source_metadata": {
-        "source_name": "RewardBench",
+        "source_name": "RewardBench 2",
         "source_type": "documentation",
         "source_organization_name": "Allen Institute for AI",
         "source_organization_url": "https://allenai.org",
@@ -181,109 +163,127 @@
         {
           "evaluation_name": "Score",
           "metric_config": {
-            "evaluation_description": "Overall RewardBench Score",
+            "evaluation_description": "Overall RewardBench 2 Score (mean of all metrics)",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5798
+            "score": 0.3332
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Chat",
+          "evaluation_name": "Factuality",
           "metric_config": {
-            "evaluation_description": "Chat accuracy - includes easy chat subsets",
+            "evaluation_description": "Factuality score - measures factual accuracy",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6173
+            "score": 0.3263
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Chat Hard",
+          "evaluation_name": "Precise IF",
           "metric_config": {
-            "evaluation_description": "Chat Hard accuracy - includes hard chat subsets",
+            "evaluation_description": "Precise Instruction Following score",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4232
+            "score": 0.2313
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
+          }
+        },
+        {
+          "evaluation_name": "Math",
+          "metric_config": {
+            "evaluation_description": "Math score - measures mathematical reasoning",
+            "lower_is_better": false,
+            "score_type": "continuous",
+            "min_score": 0.0,
+            "max_score": 1.0
+          },
+          "score_details": {
+            "score": 0.3989
+          },
+          "source_data": {
+            "dataset_name": "RewardBench 2",
+            "source_type": "hf_dataset",
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
           "evaluation_name": "Safety",
           "metric_config": {
-            "evaluation_description": "Safety accuracy - includes safety subsets",
+            "evaluation_description": "Safety score - measures safety awareness",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7351
+            "score": 0.7589
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Reasoning",
+          "evaluation_name": "Focus",
           "metric_config": {
-            "evaluation_description": "Reasoning accuracy - includes code and math subsets",
+            "evaluation_description": "Focus score - measures response focus",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5482
+            "score": 0.2939
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Prior Sets (0.5 weight)",
+          "evaluation_name": "Ties",
           "metric_config": {
-            "evaluation_description": "Prior Sets score (weighted 0.5) - includes test sets",
+            "evaluation_description": "Ties score - ability to identify tie cases",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.57
+            "score": -0.01
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         }
       ],
diff --git a/data/models/pku-alignment_beaver-7b-v1.0-reward.json b/data/models/pku-alignment_beaver-7b-v1.0-reward.json
index ee66fd95461643d78856676dc7b45eb953fc109f..adf890d6a20deeb5311651870c4e5638866b9733 100644
--- a/data/models/pku-alignment_beaver-7b-v1.0-reward.json
+++ b/data/models/pku-alignment_beaver-7b-v1.0-reward.json
@@ -9,10 +9,10 @@
   },
   "evaluations": [
     {
-      "evaluation_id": "reward-bench/PKU-Alignment_beaver-7b-v1.0-reward/1766412838.146816",
+      "evaluation_id": "reward-bench-2/PKU-Alignment_beaver-7b-v1.0-reward/1766412838.146816",
       "retrieved_timestamp": "1766412838.146816",
       "source_metadata": {
-        "source_name": "RewardBench",
+        "source_name": "RewardBench 2",
         "source_type": "documentation",
         "source_organization_name": "Allen Institute for AI",
         "source_organization_url": "https://allenai.org",
@@ -31,109 +31,127 @@
         {
           "evaluation_name": "Score",
           "metric_config": {
-            "evaluation_description": "Overall RewardBench Score",
+            "evaluation_description": "Overall RewardBench 2 Score (mean of all metrics)",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4727
+            "score": 0.1606
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Chat",
+          "evaluation_name": "Factuality",
           "metric_config": {
-            "evaluation_description": "Chat accuracy - includes easy chat subsets",
+            "evaluation_description": "Factuality score - measures factual accuracy",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.8184
+            "score": 0.2105
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Chat Hard",
+          "evaluation_name": "Precise IF",
           "metric_config": {
-            "evaluation_description": "Chat Hard accuracy - includes hard chat subsets",
+            "evaluation_description": "Precise Instruction Following score",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2873
+            "score": 0.2938
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
+          }
+        },
+        {
+          "evaluation_name": "Math",
+          "metric_config": {
+            "evaluation_description": "Math score - measures mathematical reasoning",
+            "lower_is_better": false,
+            "score_type": "continuous",
+            "min_score": 0.0,
+            "max_score": 1.0
+          },
+          "score_details": {
+            "score": 0.2623
+          },
+          "source_data": {
+            "dataset_name": "RewardBench 2",
+            "source_type": "hf_dataset",
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
           "evaluation_name": "Safety",
           "metric_config": {
-            "evaluation_description": "Safety accuracy - includes safety subsets",
+            "evaluation_description": "Safety score - measures safety awareness",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3757
+            "score": 0.1422
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Reasoning",
+          "evaluation_name": "Focus",
           "metric_config": {
-            "evaluation_description": "Reasoning accuracy - includes code and math subsets",
+            "evaluation_description": "Focus score - measures response focus",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.346
+            "score": 0.0646
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Prior Sets (0.5 weight)",
+          "evaluation_name": "Ties",
           "metric_config": {
-            "evaluation_description": "Prior Sets score (weighted 0.5) - includes test sets",
+            "evaluation_description": "Ties score - ability to identify tie cases",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5993
+            "score": -0.01
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         }
       ],
@@ -141,10 +159,10 @@
       "generation_config": null
     },
     {
-      "evaluation_id": "reward-bench-2/PKU-Alignment_beaver-7b-v1.0-reward/1766412838.146816",
+      "evaluation_id": "reward-bench/PKU-Alignment_beaver-7b-v1.0-reward/1766412838.146816",
       "retrieved_timestamp": "1766412838.146816",
       "source_metadata": {
-        "source_name": "RewardBench 2",
+        "source_name": "RewardBench",
         "source_type": "documentation",
         "source_organization_name": "Allen Institute for AI",
         "source_organization_url": "https://allenai.org",
@@ -163,127 +181,109 @@
         {
           "evaluation_name": "Score",
           "metric_config": {
-            "evaluation_description": "Overall RewardBench 2 Score (mean of all metrics)",
-            "lower_is_better": false,
-            "score_type": "continuous",
-            "min_score": 0.0,
-            "max_score": 1.0
-          },
-          "score_details": {
-            "score": 0.1606
-          },
-          "source_data": {
-            "dataset_name": "RewardBench 2",
-            "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
-          }
-        },
-        {
-          "evaluation_name": "Factuality",
-          "metric_config": {
-            "evaluation_description": "Factuality score - measures factual accuracy",
+            "evaluation_description": "Overall RewardBench Score",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2105
+            "score": 0.4727
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Precise IF",
+          "evaluation_name": "Chat",
           "metric_config": {
-            "evaluation_description": "Precise Instruction Following score",
+            "evaluation_description": "Chat accuracy - includes easy chat subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2938
+            "score": 0.8184
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Math",
+          "evaluation_name": "Chat Hard",
           "metric_config": {
-            "evaluation_description": "Math score - measures mathematical reasoning",
+            "evaluation_description": "Chat Hard accuracy - includes hard chat subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2623
+            "score": 0.2873
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
           "evaluation_name": "Safety",
           "metric_config": {
-            "evaluation_description": "Safety score - measures safety awareness",
+            "evaluation_description": "Safety accuracy - includes safety subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1422
+            "score": 0.3757
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Focus",
+          "evaluation_name": "Reasoning",
           "metric_config": {
-            "evaluation_description": "Focus score - measures response focus",
+            "evaluation_description": "Reasoning accuracy - includes code and math subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0646
+            "score": 0.346
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Ties",
+          "evaluation_name": "Prior Sets (0.5 weight)",
           "metric_config": {
-            "evaluation_description": "Ties score - ability to identify tie cases",
+            "evaluation_description": "Prior Sets score (weighted 0.5) - includes test sets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": -0.01
+            "score": 0.5993
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         }
       ],
diff --git a/data/models/pku-alignment_beaver-7b-v2.0-reward.json b/data/models/pku-alignment_beaver-7b-v2.0-reward.json
index 4c7c399de00819c04f2b08eddfc902f45548a34f..e6954fa8026e0ae406f243f530096227275cb53f 100644
--- a/data/models/pku-alignment_beaver-7b-v2.0-reward.json
+++ b/data/models/pku-alignment_beaver-7b-v2.0-reward.json
@@ -9,10 +9,10 @@
   },
   "evaluations": [
     {
-      "evaluation_id": "reward-bench/PKU-Alignment_beaver-7b-v2.0-reward/1766412838.146816",
+      "evaluation_id": "reward-bench-2/PKU-Alignment_beaver-7b-v2.0-reward/1766412838.146816",
       "retrieved_timestamp": "1766412838.146816",
       "source_metadata": {
-        "source_name": "RewardBench",
+        "source_name": "RewardBench 2",
         "source_type": "documentation",
         "source_organization_name": "Allen Institute for AI",
         "source_organization_url": "https://allenai.org",
@@ -31,109 +31,127 @@
         {
           "evaluation_name": "Score",
           "metric_config": {
-            "evaluation_description": "Overall RewardBench Score",
+            "evaluation_description": "Overall RewardBench 2 Score (mean of all metrics)",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6366
+            "score": 0.2544
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Chat",
+          "evaluation_name": "Factuality",
           "metric_config": {
-            "evaluation_description": "Chat accuracy - includes easy chat subsets",
+            "evaluation_description": "Factuality score - measures factual accuracy",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.8994
+            "score": 0.2168
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Chat Hard",
+          "evaluation_name": "Precise IF",
           "metric_config": {
-            "evaluation_description": "Chat Hard accuracy - includes hard chat subsets",
+            "evaluation_description": "Precise Instruction Following score",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.364
+            "score": 0.2562
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
+          }
+        },
+        {
+          "evaluation_name": "Math",
+          "metric_config": {
+            "evaluation_description": "Math score - measures mathematical reasoning",
+            "lower_is_better": false,
+            "score_type": "continuous",
+            "min_score": 0.0,
+            "max_score": 1.0
+          },
+          "score_details": {
+            "score": 0.3825
+          },
+          "source_data": {
+            "dataset_name": "RewardBench 2",
+            "source_type": "hf_dataset",
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
           "evaluation_name": "Safety",
           "metric_config": {
-            "evaluation_description": "Safety accuracy - includes safety subsets",
+            "evaluation_description": "Safety score - measures safety awareness",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6041
+            "score": 0.3156
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Reasoning",
+          "evaluation_name": "Focus",
           "metric_config": {
-            "evaluation_description": "Reasoning accuracy - includes code and math subsets",
+            "evaluation_description": "Focus score - measures response focus",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6887
+            "score": 0.2606
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Prior Sets (0.5 weight)",
+          "evaluation_name": "Ties",
           "metric_config": {
-            "evaluation_description": "Prior Sets score (weighted 0.5) - includes test sets",
+            "evaluation_description": "Ties score - ability to identify tie cases",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6171
+            "score": 0.0944
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         }
       ],
@@ -141,10 +159,10 @@
       "generation_config": null
     },
     {
-      "evaluation_id": "reward-bench-2/PKU-Alignment_beaver-7b-v2.0-reward/1766412838.146816",
+      "evaluation_id": "reward-bench/PKU-Alignment_beaver-7b-v2.0-reward/1766412838.146816",
       "retrieved_timestamp": "1766412838.146816",
       "source_metadata": {
-        "source_name": "RewardBench 2",
+        "source_name": "RewardBench",
         "source_type": "documentation",
         "source_organization_name": "Allen Institute for AI",
         "source_organization_url": "https://allenai.org",
@@ -163,127 +181,109 @@
         {
           "evaluation_name": "Score",
           "metric_config": {
-            "evaluation_description": "Overall RewardBench 2 Score (mean of all metrics)",
-            "lower_is_better": false,
-            "score_type": "continuous",
-            "min_score": 0.0,
-            "max_score": 1.0
-          },
-          "score_details": {
-            "score": 0.2544
-          },
-          "source_data": {
-            "dataset_name": "RewardBench 2",
-            "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
-          }
-        },
-        {
-          "evaluation_name": "Factuality",
-          "metric_config": {
-            "evaluation_description": "Factuality score - measures factual accuracy",
+            "evaluation_description": "Overall RewardBench Score",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2168
+            "score": 0.6366
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Precise IF",
+          "evaluation_name": "Chat",
           "metric_config": {
-            "evaluation_description": "Precise Instruction Following score",
+            "evaluation_description": "Chat accuracy - includes easy chat subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2562
+            "score": 0.8994
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Math",
+          "evaluation_name": "Chat Hard",
           "metric_config": {
-            "evaluation_description": "Math score - measures mathematical reasoning",
+            "evaluation_description": "Chat Hard accuracy - includes hard chat subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3825
+            "score": 0.364
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
           "evaluation_name": "Safety",
           "metric_config": {
-            "evaluation_description": "Safety score - measures safety awareness",
+            "evaluation_description": "Safety accuracy - includes safety subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3156
+            "score": 0.6041
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Focus",
+          "evaluation_name": "Reasoning",
           "metric_config": {
-            "evaluation_description": "Focus score - measures response focus",
+            "evaluation_description": "Reasoning accuracy - includes code and math subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2606
+            "score": 0.6887
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Ties",
+          "evaluation_name": "Prior Sets (0.5 weight)",
           "metric_config": {
-            "evaluation_description": "Ties score - ability to identify tie cases",
+            "evaluation_description": "Prior Sets score (weighted 0.5) - includes test sets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0944
+            "score": 0.6171
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         }
       ],
diff --git a/data/models/primeintellect_intellect-1.json b/data/models/primeintellect_intellect-1.json
index b8fa0710a43fde559062289de677b131f6527599..7d9ec915394b34f60309abc9ed073a5aa8bce5ab 100644
--- a/data/models/primeintellect_intellect-1.json
+++ b/data/models/primeintellect_intellect-1.json
@@ -5,7 +5,7 @@
     "developer": "PrimeIntellect",
     "inference_platform": "unknown",
     "additional_details": {
-      "precision": "bfloat16",
+      "precision": "float16",
       "architecture": "LlamaForCausalLM",
       "params_billions": "10.211"
     }
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.276
+            "score": 0.274
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2534
+            "score": 0.25
           }
         },
         {
@@ -116,7 +116,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3339
+            "score": 0.3753
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1123
+            "score": 0.112
           }
         }
       ],
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.274
+            "score": 0.276
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.25
+            "score": 0.2534
           }
         },
         {
@@ -246,7 +246,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3753
+            "score": 0.3339
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.112
+            "score": 0.1123
           }
         }
       ],
diff --git a/data/models/princeton-nlp_llama-3-8b-prolong-512k-instruct.json b/data/models/princeton-nlp_llama-3-8b-prolong-512k-instruct.json
index b88fd125d78454888c7b70c3de2f72cbe2fd7732..e065032f9e09241e38d49be10f5ffa3d463b4775 100644
--- a/data/models/princeton-nlp_llama-3-8b-prolong-512k-instruct.json
+++ b/data/models/princeton-nlp_llama-3-8b-prolong-512k-instruct.json
@@ -140,136 +140,6 @@
       ],
       "detailed_evaluation_results": null,
       "generation_config": null
-    },
-    {
-      "evaluation_id": "hfopenllm_v2/princeton-nlp_Llama-3-8B-ProLong-512k-Instruct/1773936498.240187",
-      "retrieved_timestamp": "1773936498.240187",
-      "source_metadata": {
-        "source_name": "HF Open LLM v2",
-        "source_type": "documentation",
-        "source_organization_name": "Hugging Face",
-        "evaluator_relationship": "third_party"
-      },
-      "eval_library": {
-        "name": "lm-evaluation-harness",
-        "version": "0.4.0",
-        "additional_details": {
-          "fork": "https://github.com/huggingface/lm-evaluation-harness/tree/adding_all_changess"
-        }
-      },
-      "benchmark": "hfopenllm_v2",
-      "evaluation_results": [
-        {
-          "evaluation_name": "IFEval",
-          "source_data": {
-            "dataset_name": "IFEval",
-            "source_type": "hf_dataset",
-            "hf_repo": "google/IFEval"
-          },
-          "metric_config": {
-            "evaluation_description": "Accuracy on IFEval",
-            "lower_is_better": false,
-            "score_type": "continuous",
-            "min_score": 0.0,
-            "max_score": 1.0
-          },
-          "score_details": {
-            "score": 0.3978
-          }
-        },
-        {
-          "evaluation_name": "BBH",
-          "source_data": {
-            "dataset_name": "BBH",
-            "source_type": "hf_dataset",
-            "hf_repo": "SaylorTwift/bbh"
-          },
-          "metric_config": {
-            "evaluation_description": "Accuracy on BBH",
-            "lower_is_better": false,
-            "score_type": "continuous",
-            "min_score": 0.0,
-            "max_score": 1.0
-          },
-          "score_details": {
-            "score": 0.4983
-          }
-        },
-        {
-          "evaluation_name": "MATH Level 5",
-          "source_data": {
-            "dataset_name": "MATH Level 5",
-            "source_type": "hf_dataset",
-            "hf_repo": "DigitalLearningGmbH/MATH-lighteval"
-          },
-          "metric_config": {
-            "evaluation_description": "Exact Match on MATH Level 5",
-            "lower_is_better": false,
-            "score_type": "continuous",
-            "min_score": 0.0,
-            "max_score": 1.0
-          },
-          "score_details": {
-            "score": 0.0582
-          }
-        },
-        {
-          "evaluation_name": "GPQA",
-          "source_data": {
-            "dataset_name": "GPQA",
-            "source_type": "hf_dataset",
-            "hf_repo": "Idavidrein/gpqa"
-          },
-          "metric_config": {
-            "evaluation_description": "Accuracy on GPQA",
-            "lower_is_better": false,
-            "score_type": "continuous",
-            "min_score": 0.0,
-            "max_score": 1.0
-          },
-          "score_details": {
-            "score": 0.281
-          }
-        },
-        {
-          "evaluation_name": "MUSR",
-          "source_data": {
-            "dataset_name": "MUSR",
-            "source_type": "hf_dataset",
-            "hf_repo": "TAUR-Lab/MuSR"
-          },
-          "metric_config": {
-            "evaluation_description": "Accuracy on MUSR",
-            "lower_is_better": false,
-            "score_type": "continuous",
-            "min_score": 0.0,
-            "max_score": 1.0
-          },
-          "score_details": {
-            "score": 0.425
-          }
-        },
-        {
-          "evaluation_name": "MMLU-PRO",
-          "source_data": {
-            "dataset_name": "MMLU-PRO",
-            "source_type": "hf_dataset",
-            "hf_repo": "TIGER-Lab/MMLU-Pro"
-          },
-          "metric_config": {
-            "evaluation_description": "Accuracy on MMLU-PRO",
-            "lower_is_better": false,
-            "score_type": "continuous",
-            "min_score": 0.0,
-            "max_score": 1.0
-          },
-          "score_details": {
-            "score": 0.3246
-          }
-        }
-      ],
-      "detailed_evaluation_results": null,
-      "generation_config": null
     }
   ]
 }
\ No newline at end of file
diff --git a/data/models/prithivmlmods_calcium-opus-14b-elite.json b/data/models/prithivmlmods_calcium-opus-14b-elite.json
index 746fd41957e7795e0f0f3751181ce9bfef3d8e70..89a0dd9277acb0b40655f39809af8ab4d96076ef 100644
--- a/data/models/prithivmlmods_calcium-opus-14b-elite.json
+++ b/data/models/prithivmlmods_calcium-opus-14b-elite.json
@@ -5,7 +5,7 @@
     "developer": "prithivMLmods",
     "inference_platform": "unknown",
     "additional_details": {
-      "precision": "float16",
+      "precision": "bfloat16",
       "architecture": "Qwen2ForCausalLM",
       "params_billions": "14.766"
     }
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6064
+            "score": 0.6052
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6296
+            "score": 0.6317
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3708
+            "score": 0.4789
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3733
+            "score": 0.3742
           }
         },
         {
@@ -116,7 +116,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4873
+            "score": 0.486
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5307
+            "score": 0.5302
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6052
+            "score": 0.6064
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6317
+            "score": 0.6296
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4789
+            "score": 0.3708
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3742
+            "score": 0.3733
           }
         },
         {
@@ -246,7 +246,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.486
+            "score": 0.4873
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5302
+            "score": 0.5307
           }
         }
       ],
diff --git a/data/models/qingy2019_qwen2.5-math-14b-instruct.json b/data/models/qingy2019_qwen2.5-math-14b-instruct.json
index d07b0024c79975f453423bba6d277d902ff3056c..21a12461d0cce8974037575db54605a0da19b661 100644
--- a/data/models/qingy2019_qwen2.5-math-14b-instruct.json
+++ b/data/models/qingy2019_qwen2.5-math-14b-instruct.json
@@ -5,7 +5,7 @@
     "developer": "qingy2019",
     "inference_platform": "unknown",
     "additional_details": {
-      "precision": "float16",
+      "precision": "bfloat16",
       "architecture": "Qwen2ForCausalLM",
       "params_billions": "14.0"
     }
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6066
+            "score": 0.6005
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.635
+            "score": 0.6356
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3716
+            "score": 0.2764
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3725
+            "score": 0.3691
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5331
+            "score": 0.5339
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6005
+            "score": 0.6066
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6356
+            "score": 0.635
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2764
+            "score": 0.3716
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3691
+            "score": 0.3725
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5339
+            "score": 0.5331
           }
         }
       ],
diff --git a/data/models/quazim0t0_casa-14b-sce.json b/data/models/quazim0t0_casa-14b-sce.json
index 5121da283045b50c1becfc23584ab4044d6d9721..04555b72d4f62f43f693bfccc1fce90b488f6f62 100644
--- a/data/models/quazim0t0_casa-14b-sce.json
+++ b/data/models/quazim0t0_casa-14b-sce.json
@@ -5,7 +5,7 @@
     "developer": "Quazim0t0",
     "inference_platform": "unknown",
     "additional_details": {
-      "precision": "bfloat16",
+      "precision": "float16",
       "architecture": "LlamaForCausalLM",
       "params_billions": "14.66"
     }
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6718
+            "score": 0.6654
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6891
+            "score": 0.6901
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4985
+            "score": 0.4698
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3339
+            "score": 0.3331
           }
         },
         {
@@ -116,7 +116,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4323
+            "score": 0.431
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5408
+            "score": 0.5426
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6654
+            "score": 0.6718
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6901
+            "score": 0.6891
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4698
+            "score": 0.4985
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3331
+            "score": 0.3339
           }
         },
         {
@@ -246,7 +246,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.431
+            "score": 0.4323
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5426
+            "score": 0.5408
           }
         }
       ],
diff --git a/data/models/quazim0t0_odb-14b-sce.json b/data/models/quazim0t0_odb-14b-sce.json
index b2854fae2e7ea9ad5a32eb4ec453ef9c1365f1b7..0894dd13c3bc882b56c1b90b77e354b0b8fcf1b3 100644
--- a/data/models/quazim0t0_odb-14b-sce.json
+++ b/data/models/quazim0t0_odb-14b-sce.json
@@ -6,8 +6,8 @@
     "inference_platform": "unknown",
     "additional_details": {
       "precision": "bfloat16",
-      "architecture": "LlamaForCausalLM",
-      "params_billions": "14.66",
+      "architecture": "Unknown",
+      "params_billions": "0.0",
       "model_id_aliases": [
         "Quazim0t0/ODB-14b-sce"
       ]
@@ -15,7 +15,7 @@
   },
   "evaluations": [
     {
-      "evaluation_id": "hfopenllm_v2/Quazim0t0_ODB-14b-sce/1773936498.240187",
+      "evaluation_id": "hfopenllm_v2/Quazim0t0_ODB-14B-sce/1773936498.240187",
       "retrieved_timestamp": "1773936498.240187",
       "source_metadata": {
         "source_name": "HF Open LLM v2",
@@ -47,7 +47,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7016
+            "score": 0.2922
           }
         },
         {
@@ -65,7 +65,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6942
+            "score": 0.6559
           }
         },
         {
@@ -83,7 +83,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4116
+            "score": 0.2545
           }
         },
         {
@@ -101,7 +101,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3624
+            "score": 0.2659
           }
         },
         {
@@ -119,7 +119,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4571
+            "score": 0.3929
           }
         },
         {
@@ -137,7 +137,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5411
+            "score": 0.5207
           }
         }
       ],
@@ -145,7 +145,7 @@
       "generation_config": null
     },
     {
-      "evaluation_id": "hfopenllm_v2/Quazim0t0_ODB-14B-sce/1773936498.240187",
+      "evaluation_id": "hfopenllm_v2/Quazim0t0_ODB-14b-sce/1773936498.240187",
       "retrieved_timestamp": "1773936498.240187",
       "source_metadata": {
         "source_name": "HF Open LLM v2",
@@ -177,7 +177,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2922
+            "score": 0.7016
           }
         },
         {
@@ -195,7 +195,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6559
+            "score": 0.6942
           }
         },
         {
@@ -213,7 +213,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2545
+            "score": 0.4116
           }
         },
         {
@@ -231,7 +231,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2659
+            "score": 0.3624
           }
         },
         {
@@ -249,7 +249,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3929
+            "score": 0.4571
           }
         },
         {
@@ -267,7 +267,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5207
+            "score": 0.5411
           }
         }
       ],
diff --git a/data/models/qwen_qwen2.5-0.5b-instruct.json b/data/models/qwen_qwen2.5-0.5b-instruct.json
index 09847e1fd5f51b0203501d1e930a33e69907de86..c0e268fa987678ac81eb89b230a531c20916f2db 100644
--- a/data/models/qwen_qwen2.5-0.5b-instruct.json
+++ b/data/models/qwen_qwen2.5-0.5b-instruct.json
@@ -5,9 +5,9 @@
     "developer": "Qwen",
     "inference_platform": "unknown",
     "additional_details": {
-      "precision": "float16",
+      "precision": "bfloat16",
       "architecture": "Qwen2ForCausalLM",
-      "params_billions": "0.494"
+      "params_billions": "0.5"
     }
   },
   "evaluations": [
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3153
+            "score": 0.3071
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3322
+            "score": 0.3341
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1035
+            "score": 0.0
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2592
+            "score": 0.2576
           }
         },
         {
@@ -116,7 +116,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3342
+            "score": 0.3329
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.172
+            "score": 0.1697
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3071
+            "score": 0.3153
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3341
+            "score": 0.3322
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0
+            "score": 0.1035
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2576
+            "score": 0.2592
           }
         },
         {
@@ -246,7 +246,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3329
+            "score": 0.3342
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1697
+            "score": 0.172
           }
         }
       ],
diff --git a/data/models/ray2333_grm-gemma2-2b-rewardmodel-ft.json b/data/models/ray2333_grm-gemma2-2b-rewardmodel-ft.json
index cd8835eaf989dbd622c51262fef9b72b10534d67..24dd55ac376e51965493e81885df295559db7184 100644
--- a/data/models/ray2333_grm-gemma2-2b-rewardmodel-ft.json
+++ b/data/models/ray2333_grm-gemma2-2b-rewardmodel-ft.json
@@ -9,10 +9,10 @@
   },
   "evaluations": [
     {
-      "evaluation_id": "reward-bench/Ray2333_GRM-gemma2-2B-rewardmodel-ft/1766412838.146816",
+      "evaluation_id": "reward-bench-2/Ray2333_GRM-gemma2-2B-rewardmodel-ft/1766412838.146816",
       "retrieved_timestamp": "1766412838.146816",
       "source_metadata": {
-        "source_name": "RewardBench",
+        "source_name": "RewardBench 2",
         "source_type": "documentation",
         "source_organization_name": "Allen Institute for AI",
         "source_organization_url": "https://allenai.org",
@@ -31,128 +31,104 @@
         {
           "evaluation_name": "Score",
           "metric_config": {
-            "evaluation_description": "Overall RewardBench Score",
+            "evaluation_description": "Overall RewardBench 2 Score (mean of all metrics)",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.8839
+            "score": 0.5966
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Chat",
+          "evaluation_name": "Factuality",
           "metric_config": {
-            "evaluation_description": "Chat accuracy - includes easy chat subsets",
+            "evaluation_description": "Factuality score - measures factual accuracy",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9302
+            "score": 0.5305
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Chat Hard",
+          "evaluation_name": "Precise IF",
           "metric_config": {
-            "evaluation_description": "Chat Hard accuracy - includes hard chat subsets",
+            "evaluation_description": "Precise Instruction Following score",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7719
+            "score": 0.3125
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Safety",
+          "evaluation_name": "Math",
           "metric_config": {
-            "evaluation_description": "Safety accuracy - includes safety subsets",
+            "evaluation_description": "Math score - measures mathematical reasoning",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9216
+            "score": 0.5902
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Reasoning",
+          "evaluation_name": "Safety",
           "metric_config": {
-            "evaluation_description": "Reasoning accuracy - includes code and math subsets",
+            "evaluation_description": "Safety score - measures safety awareness",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.912
+            "score": 0.9222
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
-        }
-      ],
-      "detailed_evaluation_results": null,
-      "generation_config": null
-    },
-    {
-      "evaluation_id": "reward-bench-2/Ray2333_GRM-gemma2-2B-rewardmodel-ft/1766412838.146816",
-      "retrieved_timestamp": "1766412838.146816",
-      "source_metadata": {
-        "source_name": "RewardBench 2",
-        "source_type": "documentation",
-        "source_organization_name": "Allen Institute for AI",
-        "source_organization_url": "https://allenai.org",
-        "evaluator_relationship": "third_party"
-      },
-      "eval_library": {
-        "name": "rewardbench",
-        "version": "0.1.3",
-        "additional_details": {
-          "subsets": "Chat, Chat Hard, Safety, Reasoning",
-          "hf_space": "allenai/reward-bench"
-        }
-      },
-      "benchmark": "reward-bench",
-      "evaluation_results": [
+        },
         {
-          "evaluation_name": "Score",
+          "evaluation_name": "Focus",
           "metric_config": {
-            "evaluation_description": "Overall RewardBench 2 Score (mean of all metrics)",
+            "evaluation_description": "Focus score - measures response focus",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5966
+            "score": 0.7455
           },
           "source_data": {
             "dataset_name": "RewardBench 2",
@@ -161,111 +137,135 @@
           }
         },
         {
-          "evaluation_name": "Factuality",
+          "evaluation_name": "Ties",
           "metric_config": {
-            "evaluation_description": "Factuality score - measures factual accuracy",
+            "evaluation_description": "Ties score - ability to identify tie cases",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5305
+            "score": 0.4788
           },
           "source_data": {
             "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
             "hf_repo": "allenai/reward-bench-2-results"
           }
-        },
+        }
+      ],
+      "detailed_evaluation_results": null,
+      "generation_config": null
+    },
+    {
+      "evaluation_id": "reward-bench/Ray2333_GRM-gemma2-2B-rewardmodel-ft/1766412838.146816",
+      "retrieved_timestamp": "1766412838.146816",
+      "source_metadata": {
+        "source_name": "RewardBench",
+        "source_type": "documentation",
+        "source_organization_name": "Allen Institute for AI",
+        "source_organization_url": "https://allenai.org",
+        "evaluator_relationship": "third_party"
+      },
+      "eval_library": {
+        "name": "rewardbench",
+        "version": "0.1.3",
+        "additional_details": {
+          "subsets": "Chat, Chat Hard, Safety, Reasoning",
+          "hf_space": "allenai/reward-bench"
+        }
+      },
+      "benchmark": "reward-bench",
+      "evaluation_results": [
         {
-          "evaluation_name": "Precise IF",
+          "evaluation_name": "Score",
           "metric_config": {
-            "evaluation_description": "Precise Instruction Following score",
+            "evaluation_description": "Overall RewardBench Score",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3125
+            "score": 0.8839
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Math",
+          "evaluation_name": "Chat",
           "metric_config": {
-            "evaluation_description": "Math score - measures mathematical reasoning",
+            "evaluation_description": "Chat accuracy - includes easy chat subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5902
+            "score": 0.9302
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Safety",
+          "evaluation_name": "Chat Hard",
           "metric_config": {
-            "evaluation_description": "Safety score - measures safety awareness",
+            "evaluation_description": "Chat Hard accuracy - includes hard chat subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9222
+            "score": 0.7719
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Focus",
+          "evaluation_name": "Safety",
           "metric_config": {
-            "evaluation_description": "Focus score - measures response focus",
+            "evaluation_description": "Safety accuracy - includes safety subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7455
+            "score": 0.9216
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Ties",
+          "evaluation_name": "Reasoning",
           "metric_config": {
-            "evaluation_description": "Ties score - ability to identify tie cases",
+            "evaluation_description": "Reasoning accuracy - includes code and math subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4788
+            "score": 0.912
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         }
       ],
diff --git a/data/models/ray2333_grm-llama3-8b-rewardmodel-ft.json b/data/models/ray2333_grm-llama3-8b-rewardmodel-ft.json
index 294d09da30917c4eff496ef892b03ff9d96db067..569e87e2d1650530a990e95b347a974efc9f47d2 100644
--- a/data/models/ray2333_grm-llama3-8b-rewardmodel-ft.json
+++ b/data/models/ray2333_grm-llama3-8b-rewardmodel-ft.json
@@ -9,10 +9,10 @@
   },
   "evaluations": [
     {
-      "evaluation_id": "reward-bench/Ray2333_GRM-Llama3-8B-rewardmodel-ft/1766412838.146816",
+      "evaluation_id": "reward-bench-2/Ray2333_GRM-Llama3-8B-rewardmodel-ft/1766412838.146816",
       "retrieved_timestamp": "1766412838.146816",
       "source_metadata": {
-        "source_name": "RewardBench",
+        "source_name": "RewardBench 2",
         "source_type": "documentation",
         "source_organization_name": "Allen Institute for AI",
         "source_organization_url": "https://allenai.org",
@@ -31,128 +31,104 @@
         {
           "evaluation_name": "Score",
           "metric_config": {
-            "evaluation_description": "Overall RewardBench Score",
+            "evaluation_description": "Overall RewardBench 2 Score (mean of all metrics)",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9154
+            "score": 0.6766
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Chat",
+          "evaluation_name": "Factuality",
           "metric_config": {
-            "evaluation_description": "Chat accuracy - includes easy chat subsets",
+            "evaluation_description": "Factuality score - measures factual accuracy",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9553
+            "score": 0.6274
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Chat Hard",
+          "evaluation_name": "Precise IF",
           "metric_config": {
-            "evaluation_description": "Chat Hard accuracy - includes hard chat subsets",
+            "evaluation_description": "Precise Instruction Following score",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.8618
+            "score": 0.35
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Safety",
+          "evaluation_name": "Math",
           "metric_config": {
-            "evaluation_description": "Safety accuracy - includes safety subsets",
+            "evaluation_description": "Math score - measures mathematical reasoning",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9081
+            "score": 0.5847
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Reasoning",
+          "evaluation_name": "Safety",
           "metric_config": {
-            "evaluation_description": "Reasoning accuracy - includes code and math subsets",
+            "evaluation_description": "Safety score - measures safety awareness",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9362
+            "score": 0.9222
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
-        }
-      ],
-      "detailed_evaluation_results": null,
-      "generation_config": null
-    },
-    {
-      "evaluation_id": "reward-bench-2/Ray2333_GRM-Llama3-8B-rewardmodel-ft/1766412838.146816",
-      "retrieved_timestamp": "1766412838.146816",
-      "source_metadata": {
-        "source_name": "RewardBench 2",
-        "source_type": "documentation",
-        "source_organization_name": "Allen Institute for AI",
-        "source_organization_url": "https://allenai.org",
-        "evaluator_relationship": "third_party"
-      },
-      "eval_library": {
-        "name": "rewardbench",
-        "version": "0.1.3",
-        "additional_details": {
-          "subsets": "Chat, Chat Hard, Safety, Reasoning",
-          "hf_space": "allenai/reward-bench"
-        }
-      },
-      "benchmark": "reward-bench",
-      "evaluation_results": [
+        },
         {
-          "evaluation_name": "Score",
+          "evaluation_name": "Focus",
           "metric_config": {
-            "evaluation_description": "Overall RewardBench 2 Score (mean of all metrics)",
+            "evaluation_description": "Focus score - measures response focus",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6766
+            "score": 0.8929
           },
           "source_data": {
             "dataset_name": "RewardBench 2",
@@ -161,111 +137,135 @@
           }
         },
         {
-          "evaluation_name": "Factuality",
+          "evaluation_name": "Ties",
           "metric_config": {
-            "evaluation_description": "Factuality score - measures factual accuracy",
+            "evaluation_description": "Ties score - ability to identify tie cases",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6274
+            "score": 0.6824
           },
           "source_data": {
             "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
             "hf_repo": "allenai/reward-bench-2-results"
           }
-        },
+        }
+      ],
+      "detailed_evaluation_results": null,
+      "generation_config": null
+    },
+    {
+      "evaluation_id": "reward-bench/Ray2333_GRM-Llama3-8B-rewardmodel-ft/1766412838.146816",
+      "retrieved_timestamp": "1766412838.146816",
+      "source_metadata": {
+        "source_name": "RewardBench",
+        "source_type": "documentation",
+        "source_organization_name": "Allen Institute for AI",
+        "source_organization_url": "https://allenai.org",
+        "evaluator_relationship": "third_party"
+      },
+      "eval_library": {
+        "name": "rewardbench",
+        "version": "0.1.3",
+        "additional_details": {
+          "subsets": "Chat, Chat Hard, Safety, Reasoning",
+          "hf_space": "allenai/reward-bench"
+        }
+      },
+      "benchmark": "reward-bench",
+      "evaluation_results": [
         {
-          "evaluation_name": "Precise IF",
+          "evaluation_name": "Score",
           "metric_config": {
-            "evaluation_description": "Precise Instruction Following score",
+            "evaluation_description": "Overall RewardBench Score",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.35
+            "score": 0.9154
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Math",
+          "evaluation_name": "Chat",
           "metric_config": {
-            "evaluation_description": "Math score - measures mathematical reasoning",
+            "evaluation_description": "Chat accuracy - includes easy chat subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5847
+            "score": 0.9553
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Safety",
+          "evaluation_name": "Chat Hard",
           "metric_config": {
-            "evaluation_description": "Safety score - measures safety awareness",
+            "evaluation_description": "Chat Hard accuracy - includes hard chat subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9222
+            "score": 0.8618
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Focus",
+          "evaluation_name": "Safety",
           "metric_config": {
-            "evaluation_description": "Focus score - measures response focus",
+            "evaluation_description": "Safety accuracy - includes safety subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.8929
+            "score": 0.9081
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Ties",
+          "evaluation_name": "Reasoning",
           "metric_config": {
-            "evaluation_description": "Ties score - ability to identify tie cases",
+            "evaluation_description": "Reasoning accuracy - includes code and math subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6824
+            "score": 0.9362
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         }
       ],
diff --git a/data/models/ray2333_grm-llama3-8b-sftreg.json b/data/models/ray2333_grm-llama3-8b-sftreg.json
index 15f35c842dfd5169bfd85bae53f76a90d5850421..bd70639489991e3e8880cad041284119bd35ecc9 100644
--- a/data/models/ray2333_grm-llama3-8b-sftreg.json
+++ b/data/models/ray2333_grm-llama3-8b-sftreg.json
@@ -9,10 +9,10 @@
   },
   "evaluations": [
     {
-      "evaluation_id": "reward-bench-2/Ray2333_GRM-llama3-8B-sftreg/1766412838.146816",
+      "evaluation_id": "reward-bench/Ray2333_GRM-llama3-8B-sftreg/1766412838.146816",
       "retrieved_timestamp": "1766412838.146816",
       "source_metadata": {
-        "source_name": "RewardBench 2",
+        "source_name": "RewardBench",
         "source_type": "documentation",
         "source_organization_name": "Allen Institute for AI",
         "source_organization_url": "https://allenai.org",
@@ -31,127 +31,109 @@
         {
           "evaluation_name": "Score",
           "metric_config": {
-            "evaluation_description": "Overall RewardBench 2 Score (mean of all metrics)",
-            "lower_is_better": false,
-            "score_type": "continuous",
-            "min_score": 0.0,
-            "max_score": 1.0
-          },
-          "score_details": {
-            "score": 0.6089
-          },
-          "source_data": {
-            "dataset_name": "RewardBench 2",
-            "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
-          }
-        },
-        {
-          "evaluation_name": "Factuality",
-          "metric_config": {
-            "evaluation_description": "Factuality score - measures factual accuracy",
+            "evaluation_description": "Overall RewardBench Score",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6189
+            "score": 0.8542
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Precise IF",
+          "evaluation_name": "Chat",
           "metric_config": {
-            "evaluation_description": "Precise Instruction Following score",
+            "evaluation_description": "Chat accuracy - includes easy chat subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3875
+            "score": 0.986
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Math",
+          "evaluation_name": "Chat Hard",
           "metric_config": {
-            "evaluation_description": "Math score - measures mathematical reasoning",
+            "evaluation_description": "Chat Hard accuracy - includes hard chat subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5792
+            "score": 0.6776
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
           "evaluation_name": "Safety",
           "metric_config": {
-            "evaluation_description": "Safety score - measures safety awareness",
+            "evaluation_description": "Safety accuracy - includes safety subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7867
+            "score": 0.8919
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Focus",
+          "evaluation_name": "Reasoning",
           "metric_config": {
-            "evaluation_description": "Focus score - measures response focus",
+            "evaluation_description": "Reasoning accuracy - includes code and math subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6828
+            "score": 0.9229
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Ties",
+          "evaluation_name": "Prior Sets (0.5 weight)",
           "metric_config": {
-            "evaluation_description": "Ties score - ability to identify tie cases",
+            "evaluation_description": "Prior Sets score (weighted 0.5) - includes test sets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5981
+            "score": 0.7309
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         }
       ],
@@ -159,10 +141,10 @@
       "generation_config": null
     },
     {
-      "evaluation_id": "reward-bench/Ray2333_GRM-llama3-8B-sftreg/1766412838.146816",
+      "evaluation_id": "reward-bench-2/Ray2333_GRM-llama3-8B-sftreg/1766412838.146816",
       "retrieved_timestamp": "1766412838.146816",
       "source_metadata": {
-        "source_name": "RewardBench",
+        "source_name": "RewardBench 2",
         "source_type": "documentation",
         "source_organization_name": "Allen Institute for AI",
         "source_organization_url": "https://allenai.org",
@@ -181,109 +163,127 @@
         {
           "evaluation_name": "Score",
           "metric_config": {
-            "evaluation_description": "Overall RewardBench Score",
+            "evaluation_description": "Overall RewardBench 2 Score (mean of all metrics)",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.8542
+            "score": 0.6089
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Chat",
+          "evaluation_name": "Factuality",
           "metric_config": {
-            "evaluation_description": "Chat accuracy - includes easy chat subsets",
+            "evaluation_description": "Factuality score - measures factual accuracy",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.986
+            "score": 0.6189
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Chat Hard",
+          "evaluation_name": "Precise IF",
           "metric_config": {
-            "evaluation_description": "Chat Hard accuracy - includes hard chat subsets",
+            "evaluation_description": "Precise Instruction Following score",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6776
+            "score": 0.3875
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
+          }
+        },
+        {
+          "evaluation_name": "Math",
+          "metric_config": {
+            "evaluation_description": "Math score - measures mathematical reasoning",
+            "lower_is_better": false,
+            "score_type": "continuous",
+            "min_score": 0.0,
+            "max_score": 1.0
+          },
+          "score_details": {
+            "score": 0.5792
+          },
+          "source_data": {
+            "dataset_name": "RewardBench 2",
+            "source_type": "hf_dataset",
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
           "evaluation_name": "Safety",
           "metric_config": {
-            "evaluation_description": "Safety accuracy - includes safety subsets",
+            "evaluation_description": "Safety score - measures safety awareness",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.8919
+            "score": 0.7867
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Reasoning",
+          "evaluation_name": "Focus",
           "metric_config": {
-            "evaluation_description": "Reasoning accuracy - includes code and math subsets",
+            "evaluation_description": "Focus score - measures response focus",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9229
+            "score": 0.6828
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Prior Sets (0.5 weight)",
+          "evaluation_name": "Ties",
           "metric_config": {
-            "evaluation_description": "Prior Sets score (weighted 0.5) - includes test sets",
+            "evaluation_description": "Ties score - ability to identify tie cases",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7309
+            "score": 0.5981
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         }
       ],
diff --git a/data/models/recoilme_recoilme-gemma-2-9b-v0.2.json b/data/models/recoilme_recoilme-gemma-2-9b-v0.2.json
index 34121094195afd5811c50d769ba5e5e07669b30d..83bfdb05cda442c3bac351d424fa26cf0ae864fe 100644
--- a/data/models/recoilme_recoilme-gemma-2-9b-v0.2.json
+++ b/data/models/recoilme_recoilme-gemma-2-9b-v0.2.json
@@ -5,7 +5,7 @@
     "developer": "recoilme",
     "inference_platform": "unknown",
     "additional_details": {
-      "precision": "bfloat16",
+      "precision": "float16",
       "architecture": "Gemma2ForCausalLM",
       "params_billions": "10.159"
     }
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2747
+            "score": 0.7592
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6031
+            "score": 0.6026
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0831
+            "score": 0.0529
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3305
+            "score": 0.3289
           }
         },
         {
@@ -116,7 +116,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4686
+            "score": 0.4099
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4122
+            "score": 0.4163
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7592
+            "score": 0.2747
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6026
+            "score": 0.6031
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0529
+            "score": 0.0831
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3289
+            "score": 0.3305
           }
         },
         {
@@ -246,7 +246,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4099
+            "score": 0.4686
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4163
+            "score": 0.4122
           }
         }
       ],
diff --git a/data/models/recoilme_recoilme-gemma-2-9b-v0.3.json b/data/models/recoilme_recoilme-gemma-2-9b-v0.3.json
index 812871dcfb75c54e3765d2c8d03eeadc60d898aa..d5cadb462419994ffdabe8b6cdbd73be57e99fa8 100644
--- a/data/models/recoilme_recoilme-gemma-2-9b-v0.3.json
+++ b/data/models/recoilme_recoilme-gemma-2-9b-v0.3.json
@@ -5,7 +5,7 @@
     "developer": "recoilme",
     "inference_platform": "unknown",
     "additional_details": {
-      "precision": "float16",
+      "precision": "bfloat16",
       "architecture": "Gemma2ForCausalLM",
       "params_billions": "10.159"
     }
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7439
+            "score": 0.5761
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5993
+            "score": 0.602
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0876
+            "score": 0.1888
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3238
+            "score": 0.3372
           }
         },
         {
@@ -116,7 +116,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4204
+            "score": 0.4632
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4072
+            "score": 0.4039
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5761
+            "score": 0.7439
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.602
+            "score": 0.5993
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1888
+            "score": 0.0876
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3372
+            "score": 0.3238
           }
         },
         {
@@ -246,7 +246,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4632
+            "score": 0.4204
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4039
+            "score": 0.4072
           }
         }
       ],
diff --git a/data/models/replete-ai_replete-llm-qwen2-7b.json b/data/models/replete-ai_replete-llm-qwen2-7b.json
index e51b10d1bb4ff7d76603042a5cdf25b16b9bc87f..627d67572ee0cd0135e173767115d5ee7360b5e6 100644
--- a/data/models/replete-ai_replete-llm-qwen2-7b.json
+++ b/data/models/replete-ai_replete-llm-qwen2-7b.json
@@ -5,7 +5,7 @@
     "developer": "Replete-AI",
     "inference_platform": "unknown",
     "additional_details": {
-      "precision": "bfloat16",
+      "precision": "float16",
       "architecture": "Qwen2ForCausalLM",
       "params_billions": "7.616"
     }
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0932
+            "score": 0.0905
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2977
+            "score": 0.2985
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2475
+            "score": 0.2534
           }
         },
         {
@@ -116,7 +116,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3941
+            "score": 0.3848
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1157
+            "score": 0.1158
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0905
+            "score": 0.0932
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2985
+            "score": 0.2977
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2534
+            "score": 0.2475
           }
         },
         {
@@ -246,7 +246,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3848
+            "score": 0.3941
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1158
+            "score": 0.1157
           }
         }
       ],
diff --git a/data/models/sfairxc_fsfairx-llama3-rm-v0.1.json b/data/models/sfairxc_fsfairx-llama3-rm-v0.1.json
index ecef2ed14b1e2210796bfe9e4943404f7ebd3b7c..83ff30916d3f35c6333d5f652927c45d63836756 100644
--- a/data/models/sfairxc_fsfairx-llama3-rm-v0.1.json
+++ b/data/models/sfairxc_fsfairx-llama3-rm-v0.1.json
@@ -9,10 +9,10 @@
   },
   "evaluations": [
     {
-      "evaluation_id": "reward-bench-2/sfairXC_FsfairX-LLaMA3-RM-v0.1/1766412838.146816",
+      "evaluation_id": "reward-bench/sfairXC_FsfairX-LLaMA3-RM-v0.1/1766412838.146816",
       "retrieved_timestamp": "1766412838.146816",
       "source_metadata": {
-        "source_name": "RewardBench 2",
+        "source_name": "RewardBench",
         "source_type": "documentation",
         "source_organization_name": "Allen Institute for AI",
         "source_organization_url": "https://allenai.org",
@@ -31,127 +31,109 @@
         {
           "evaluation_name": "Score",
           "metric_config": {
-            "evaluation_description": "Overall RewardBench 2 Score (mean of all metrics)",
-            "lower_is_better": false,
-            "score_type": "continuous",
-            "min_score": 0.0,
-            "max_score": 1.0
-          },
-          "score_details": {
-            "score": 0.6292
-          },
-          "source_data": {
-            "dataset_name": "RewardBench 2",
-            "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
-          }
-        },
-        {
-          "evaluation_name": "Factuality",
-          "metric_config": {
-            "evaluation_description": "Factuality score - measures factual accuracy",
+            "evaluation_description": "Overall RewardBench Score",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5916
+            "score": 0.8338
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Precise IF",
+          "evaluation_name": "Chat",
           "metric_config": {
-            "evaluation_description": "Precise Instruction Following score",
+            "evaluation_description": "Chat accuracy - includes easy chat subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4188
+            "score": 0.9944
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Math",
+          "evaluation_name": "Chat Hard",
           "metric_config": {
-            "evaluation_description": "Math score - measures mathematical reasoning",
+            "evaluation_description": "Chat Hard accuracy - includes hard chat subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6284
+            "score": 0.6513
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
           "evaluation_name": "Safety",
           "metric_config": {
-            "evaluation_description": "Safety score - measures safety awareness",
+            "evaluation_description": "Safety accuracy - includes safety subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7667
+            "score": 0.8676
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Focus",
+          "evaluation_name": "Reasoning",
           "metric_config": {
-            "evaluation_description": "Focus score - measures response focus",
+            "evaluation_description": "Reasoning accuracy - includes code and math subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7051
+            "score": 0.8644
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Ties",
+          "evaluation_name": "Prior Sets (0.5 weight)",
           "metric_config": {
-            "evaluation_description": "Ties score - ability to identify tie cases",
+            "evaluation_description": "Prior Sets score (weighted 0.5) - includes test sets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6647
+            "score": 0.7492
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         }
       ],
@@ -159,10 +141,10 @@
       "generation_config": null
     },
     {
-      "evaluation_id": "reward-bench/sfairXC_FsfairX-LLaMA3-RM-v0.1/1766412838.146816",
+      "evaluation_id": "reward-bench-2/sfairXC_FsfairX-LLaMA3-RM-v0.1/1766412838.146816",
       "retrieved_timestamp": "1766412838.146816",
       "source_metadata": {
-        "source_name": "RewardBench",
+        "source_name": "RewardBench 2",
         "source_type": "documentation",
         "source_organization_name": "Allen Institute for AI",
         "source_organization_url": "https://allenai.org",
@@ -181,109 +163,127 @@
         {
           "evaluation_name": "Score",
           "metric_config": {
-            "evaluation_description": "Overall RewardBench Score",
+            "evaluation_description": "Overall RewardBench 2 Score (mean of all metrics)",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.8338
+            "score": 0.6292
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Chat",
+          "evaluation_name": "Factuality",
           "metric_config": {
-            "evaluation_description": "Chat accuracy - includes easy chat subsets",
+            "evaluation_description": "Factuality score - measures factual accuracy",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9944
+            "score": 0.5916
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Chat Hard",
+          "evaluation_name": "Precise IF",
           "metric_config": {
-            "evaluation_description": "Chat Hard accuracy - includes hard chat subsets",
+            "evaluation_description": "Precise Instruction Following score",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6513
+            "score": 0.4188
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
+          }
+        },
+        {
+          "evaluation_name": "Math",
+          "metric_config": {
+            "evaluation_description": "Math score - measures mathematical reasoning",
+            "lower_is_better": false,
+            "score_type": "continuous",
+            "min_score": 0.0,
+            "max_score": 1.0
+          },
+          "score_details": {
+            "score": 0.6284
+          },
+          "source_data": {
+            "dataset_name": "RewardBench 2",
+            "source_type": "hf_dataset",
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
           "evaluation_name": "Safety",
           "metric_config": {
-            "evaluation_description": "Safety accuracy - includes safety subsets",
+            "evaluation_description": "Safety score - measures safety awareness",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.8676
+            "score": 0.7667
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Reasoning",
+          "evaluation_name": "Focus",
           "metric_config": {
-            "evaluation_description": "Reasoning accuracy - includes code and math subsets",
+            "evaluation_description": "Focus score - measures response focus",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.8644
+            "score": 0.7051
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Prior Sets (0.5 weight)",
+          "evaluation_name": "Ties",
           "metric_config": {
-            "evaluation_description": "Prior Sets score (weighted 0.5) - includes test sets",
+            "evaluation_description": "Ties score - ability to identify tie cases",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7492
+            "score": 0.6647
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         }
       ],
diff --git a/data/models/shikaichen_ldl-reward-gemma-2-27b-v0.1.json b/data/models/shikaichen_ldl-reward-gemma-2-27b-v0.1.json
index 988f599afd76311b87e49f16160d0ca534436cdd..4a85b178092e7e5acaf395eb054cb8adc61e2891 100644
--- a/data/models/shikaichen_ldl-reward-gemma-2-27b-v0.1.json
+++ b/data/models/shikaichen_ldl-reward-gemma-2-27b-v0.1.json
@@ -9,10 +9,10 @@
   },
   "evaluations": [
     {
-      "evaluation_id": "reward-bench-2/ShikaiChen_LDL-Reward-Gemma-2-27B-v0.1/1766412838.146816",
+      "evaluation_id": "reward-bench/ShikaiChen_LDL-Reward-Gemma-2-27B-v0.1/1766412838.146816",
       "retrieved_timestamp": "1766412838.146816",
       "source_metadata": {
-        "source_name": "RewardBench 2",
+        "source_name": "RewardBench",
         "source_type": "documentation",
         "source_organization_name": "Allen Institute for AI",
         "source_organization_url": "https://allenai.org",
@@ -31,104 +31,128 @@
         {
           "evaluation_name": "Score",
           "metric_config": {
-            "evaluation_description": "Overall RewardBench 2 Score (mean of all metrics)",
+            "evaluation_description": "Overall RewardBench Score",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7249
+            "score": 0.9499
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Factuality",
+          "evaluation_name": "Chat",
           "metric_config": {
-            "evaluation_description": "Factuality score - measures factual accuracy",
+            "evaluation_description": "Chat accuracy - includes easy chat subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7558
+            "score": 0.9637
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Precise IF",
+          "evaluation_name": "Chat Hard",
           "metric_config": {
-            "evaluation_description": "Precise Instruction Following score",
+            "evaluation_description": "Chat Hard accuracy - includes hard chat subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.35
+            "score": 0.9079
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Math",
+          "evaluation_name": "Safety",
           "metric_config": {
-            "evaluation_description": "Math score - measures mathematical reasoning",
+            "evaluation_description": "Safety accuracy - includes safety subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6448
+            "score": 0.9378
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Safety",
+          "evaluation_name": "Reasoning",
           "metric_config": {
-            "evaluation_description": "Safety score - measures safety awareness",
+            "evaluation_description": "Reasoning accuracy - includes code and math subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9222
+            "score": 0.9903
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
-        },
+        }
+      ],
+      "detailed_evaluation_results": null,
+      "generation_config": null
+    },
+    {
+      "evaluation_id": "reward-bench-2/ShikaiChen_LDL-Reward-Gemma-2-27B-v0.1/1766412838.146816",
+      "retrieved_timestamp": "1766412838.146816",
+      "source_metadata": {
+        "source_name": "RewardBench 2",
+        "source_type": "documentation",
+        "source_organization_name": "Allen Institute for AI",
+        "source_organization_url": "https://allenai.org",
+        "evaluator_relationship": "third_party"
+      },
+      "eval_library": {
+        "name": "rewardbench",
+        "version": "0.1.3",
+        "additional_details": {
+          "subsets": "Chat, Chat Hard, Safety, Reasoning",
+          "hf_space": "allenai/reward-bench"
+        }
+      },
+      "benchmark": "reward-bench",
+      "evaluation_results": [
         {
-          "evaluation_name": "Focus",
+          "evaluation_name": "Score",
           "metric_config": {
-            "evaluation_description": "Focus score - measures response focus",
+            "evaluation_description": "Overall RewardBench 2 Score (mean of all metrics)",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9131
+            "score": 0.7249
           },
           "source_data": {
             "dataset_name": "RewardBench 2",
@@ -137,135 +161,111 @@
           }
         },
         {
-          "evaluation_name": "Ties",
+          "evaluation_name": "Factuality",
           "metric_config": {
-            "evaluation_description": "Ties score - ability to identify tie cases",
+            "evaluation_description": "Factuality score - measures factual accuracy",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7633
+            "score": 0.7558
           },
           "source_data": {
             "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
             "hf_repo": "allenai/reward-bench-2-results"
           }
-        }
-      ],
-      "detailed_evaluation_results": null,
-      "generation_config": null
-    },
-    {
-      "evaluation_id": "reward-bench/ShikaiChen_LDL-Reward-Gemma-2-27B-v0.1/1766412838.146816",
-      "retrieved_timestamp": "1766412838.146816",
-      "source_metadata": {
-        "source_name": "RewardBench",
-        "source_type": "documentation",
-        "source_organization_name": "Allen Institute for AI",
-        "source_organization_url": "https://allenai.org",
-        "evaluator_relationship": "third_party"
-      },
-      "eval_library": {
-        "name": "rewardbench",
-        "version": "0.1.3",
-        "additional_details": {
-          "subsets": "Chat, Chat Hard, Safety, Reasoning",
-          "hf_space": "allenai/reward-bench"
-        }
-      },
-      "benchmark": "reward-bench",
-      "evaluation_results": [
+        },
         {
-          "evaluation_name": "Score",
+          "evaluation_name": "Precise IF",
           "metric_config": {
-            "evaluation_description": "Overall RewardBench Score",
+            "evaluation_description": "Precise Instruction Following score",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9499
+            "score": 0.35
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Chat",
+          "evaluation_name": "Math",
           "metric_config": {
-            "evaluation_description": "Chat accuracy - includes easy chat subsets",
+            "evaluation_description": "Math score - measures mathematical reasoning",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9637
+            "score": 0.6448
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Chat Hard",
+          "evaluation_name": "Safety",
           "metric_config": {
-            "evaluation_description": "Chat Hard accuracy - includes hard chat subsets",
+            "evaluation_description": "Safety score - measures safety awareness",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9079
+            "score": 0.9222
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Safety",
+          "evaluation_name": "Focus",
           "metric_config": {
-            "evaluation_description": "Safety accuracy - includes safety subsets",
+            "evaluation_description": "Focus score - measures response focus",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9378
+            "score": 0.9131
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Reasoning",
+          "evaluation_name": "Ties",
           "metric_config": {
-            "evaluation_description": "Reasoning accuracy - includes code and math subsets",
+            "evaluation_description": "Ties score - ability to identify tie cases",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9903
+            "score": 0.7633
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         }
       ],
diff --git a/data/models/skywork_skywork-reward-gemma-2-27b.json b/data/models/skywork_skywork-reward-gemma-2-27b.json
index 0b4cc11a7f17a4535cc37f935fdae034a6214bce..c2b742dbc17aa9720f66d090e08eb784ec7accdc 100644
--- a/data/models/skywork_skywork-reward-gemma-2-27b.json
+++ b/data/models/skywork_skywork-reward-gemma-2-27b.json
@@ -9,10 +9,10 @@
   },
   "evaluations": [
     {
-      "evaluation_id": "reward-bench/Skywork_Skywork-Reward-Gemma-2-27B/1766412838.146816",
+      "evaluation_id": "reward-bench-2/Skywork_Skywork-Reward-Gemma-2-27B/1766412838.146816",
       "retrieved_timestamp": "1766412838.146816",
       "source_metadata": {
-        "source_name": "RewardBench",
+        "source_name": "RewardBench 2",
         "source_type": "documentation",
         "source_organization_name": "Allen Institute for AI",
         "source_organization_url": "https://allenai.org",
@@ -31,128 +31,104 @@
         {
           "evaluation_name": "Score",
           "metric_config": {
-            "evaluation_description": "Overall RewardBench Score",
+            "evaluation_description": "Overall RewardBench 2 Score (mean of all metrics)",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.938
+            "score": 0.7576
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Chat",
+          "evaluation_name": "Factuality",
           "metric_config": {
-            "evaluation_description": "Chat accuracy - includes easy chat subsets",
+            "evaluation_description": "Factuality score - measures factual accuracy",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9581
+            "score": 0.7368
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Chat Hard",
+          "evaluation_name": "Precise IF",
           "metric_config": {
-            "evaluation_description": "Chat Hard accuracy - includes hard chat subsets",
+            "evaluation_description": "Precise Instruction Following score",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9145
+            "score": 0.4031
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Safety",
+          "evaluation_name": "Math",
           "metric_config": {
-            "evaluation_description": "Safety accuracy - includes safety subsets",
+            "evaluation_description": "Math score - measures mathematical reasoning",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9189
+            "score": 0.7049
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Reasoning",
+          "evaluation_name": "Safety",
           "metric_config": {
-            "evaluation_description": "Reasoning accuracy - includes code and math subsets",
+            "evaluation_description": "Safety score - measures safety awareness",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9606
+            "score": 0.9422
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
-        }
-      ],
-      "detailed_evaluation_results": null,
-      "generation_config": null
-    },
-    {
-      "evaluation_id": "reward-bench-2/Skywork_Skywork-Reward-Gemma-2-27B/1766412838.146816",
-      "retrieved_timestamp": "1766412838.146816",
-      "source_metadata": {
-        "source_name": "RewardBench 2",
-        "source_type": "documentation",
-        "source_organization_name": "Allen Institute for AI",
-        "source_organization_url": "https://allenai.org",
-        "evaluator_relationship": "third_party"
-      },
-      "eval_library": {
-        "name": "rewardbench",
-        "version": "0.1.3",
-        "additional_details": {
-          "subsets": "Chat, Chat Hard, Safety, Reasoning",
-          "hf_space": "allenai/reward-bench"
-        }
-      },
-      "benchmark": "reward-bench",
-      "evaluation_results": [
+        },
         {
-          "evaluation_name": "Score",
+          "evaluation_name": "Focus",
           "metric_config": {
-            "evaluation_description": "Overall RewardBench 2 Score (mean of all metrics)",
+            "evaluation_description": "Focus score - measures response focus",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7576
+            "score": 0.9323
           },
           "source_data": {
             "dataset_name": "RewardBench 2",
@@ -161,111 +137,135 @@
           }
         },
         {
-          "evaluation_name": "Factuality",
+          "evaluation_name": "Ties",
           "metric_config": {
-            "evaluation_description": "Factuality score - measures factual accuracy",
+            "evaluation_description": "Ties score - ability to identify tie cases",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7368
+            "score": 0.8261
           },
           "source_data": {
             "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
             "hf_repo": "allenai/reward-bench-2-results"
           }
-        },
+        }
+      ],
+      "detailed_evaluation_results": null,
+      "generation_config": null
+    },
+    {
+      "evaluation_id": "reward-bench/Skywork_Skywork-Reward-Gemma-2-27B/1766412838.146816",
+      "retrieved_timestamp": "1766412838.146816",
+      "source_metadata": {
+        "source_name": "RewardBench",
+        "source_type": "documentation",
+        "source_organization_name": "Allen Institute for AI",
+        "source_organization_url": "https://allenai.org",
+        "evaluator_relationship": "third_party"
+      },
+      "eval_library": {
+        "name": "rewardbench",
+        "version": "0.1.3",
+        "additional_details": {
+          "subsets": "Chat, Chat Hard, Safety, Reasoning",
+          "hf_space": "allenai/reward-bench"
+        }
+      },
+      "benchmark": "reward-bench",
+      "evaluation_results": [
         {
-          "evaluation_name": "Precise IF",
+          "evaluation_name": "Score",
           "metric_config": {
-            "evaluation_description": "Precise Instruction Following score",
+            "evaluation_description": "Overall RewardBench Score",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4031
+            "score": 0.938
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Math",
+          "evaluation_name": "Chat",
           "metric_config": {
-            "evaluation_description": "Math score - measures mathematical reasoning",
+            "evaluation_description": "Chat accuracy - includes easy chat subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7049
+            "score": 0.9581
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Safety",
+          "evaluation_name": "Chat Hard",
           "metric_config": {
-            "evaluation_description": "Safety score - measures safety awareness",
+            "evaluation_description": "Chat Hard accuracy - includes hard chat subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9422
+            "score": 0.9145
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Focus",
+          "evaluation_name": "Safety",
           "metric_config": {
-            "evaluation_description": "Focus score - measures response focus",
+            "evaluation_description": "Safety accuracy - includes safety subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9323
+            "score": 0.9189
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Ties",
+          "evaluation_name": "Reasoning",
           "metric_config": {
-            "evaluation_description": "Ties score - ability to identify tie cases",
+            "evaluation_description": "Reasoning accuracy - includes code and math subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.8261
+            "score": 0.9606
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         }
       ],
diff --git a/data/models/skywork_skywork-vl-reward-7b.json b/data/models/skywork_skywork-vl-reward-7b.json
index d1caca7afd32adac0ce3eaccc5894c6b1d1db99d..651d1416fd84d9618565234fc2f23befa272cb51 100644
--- a/data/models/skywork_skywork-vl-reward-7b.json
+++ b/data/models/skywork_skywork-vl-reward-7b.json
@@ -9,10 +9,10 @@
   },
   "evaluations": [
     {
-      "evaluation_id": "reward-bench/Skywork_Skywork-VL-Reward-7B/1766412838.146816",
+      "evaluation_id": "reward-bench-2/Skywork_Skywork-VL-Reward-7B/1766412838.146816",
       "retrieved_timestamp": "1766412838.146816",
       "source_metadata": {
-        "source_name": "RewardBench",
+        "source_name": "RewardBench 2",
         "source_type": "documentation",
         "source_organization_name": "Allen Institute for AI",
         "source_organization_url": "https://allenai.org",
@@ -31,128 +31,104 @@
         {
           "evaluation_name": "Score",
           "metric_config": {
-            "evaluation_description": "Overall RewardBench Score",
+            "evaluation_description": "Overall RewardBench 2 Score (mean of all metrics)",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9007
+            "score": 0.6885
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Chat",
+          "evaluation_name": "Factuality",
           "metric_config": {
-            "evaluation_description": "Chat accuracy - includes easy chat subsets",
+            "evaluation_description": "Factuality score - measures factual accuracy",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.8994
+            "score": 0.6063
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Chat Hard",
+          "evaluation_name": "Precise IF",
           "metric_config": {
-            "evaluation_description": "Chat Hard accuracy - includes hard chat subsets",
+            "evaluation_description": "Precise Instruction Following score",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.875
+            "score": 0.35
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Safety",
+          "evaluation_name": "Math",
           "metric_config": {
-            "evaluation_description": "Safety accuracy - includes safety subsets",
+            "evaluation_description": "Math score - measures mathematical reasoning",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9108
+            "score": 0.6339
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Reasoning",
+          "evaluation_name": "Safety",
           "metric_config": {
-            "evaluation_description": "Reasoning accuracy - includes code and math subsets",
+            "evaluation_description": "Safety score - measures safety awareness",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9176
+            "score": 0.8911
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
-        }
-      ],
-      "detailed_evaluation_results": null,
-      "generation_config": null
-    },
-    {
-      "evaluation_id": "reward-bench-2/Skywork_Skywork-VL-Reward-7B/1766412838.146816",
-      "retrieved_timestamp": "1766412838.146816",
-      "source_metadata": {
-        "source_name": "RewardBench 2",
-        "source_type": "documentation",
-        "source_organization_name": "Allen Institute for AI",
-        "source_organization_url": "https://allenai.org",
-        "evaluator_relationship": "third_party"
-      },
-      "eval_library": {
-        "name": "rewardbench",
-        "version": "0.1.3",
-        "additional_details": {
-          "subsets": "Chat, Chat Hard, Safety, Reasoning",
-          "hf_space": "allenai/reward-bench"
-        }
-      },
-      "benchmark": "reward-bench",
-      "evaluation_results": [
+        },
         {
-          "evaluation_name": "Score",
+          "evaluation_name": "Focus",
           "metric_config": {
-            "evaluation_description": "Overall RewardBench 2 Score (mean of all metrics)",
+            "evaluation_description": "Focus score - measures response focus",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6885
+            "score": 0.8909
           },
           "source_data": {
             "dataset_name": "RewardBench 2",
@@ -161,111 +137,135 @@
           }
         },
         {
-          "evaluation_name": "Factuality",
+          "evaluation_name": "Ties",
           "metric_config": {
-            "evaluation_description": "Factuality score - measures factual accuracy",
+            "evaluation_description": "Ties score - ability to identify tie cases",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6063
+            "score": 0.7586
           },
           "source_data": {
             "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
             "hf_repo": "allenai/reward-bench-2-results"
           }
-        },
+        }
+      ],
+      "detailed_evaluation_results": null,
+      "generation_config": null
+    },
+    {
+      "evaluation_id": "reward-bench/Skywork_Skywork-VL-Reward-7B/1766412838.146816",
+      "retrieved_timestamp": "1766412838.146816",
+      "source_metadata": {
+        "source_name": "RewardBench",
+        "source_type": "documentation",
+        "source_organization_name": "Allen Institute for AI",
+        "source_organization_url": "https://allenai.org",
+        "evaluator_relationship": "third_party"
+      },
+      "eval_library": {
+        "name": "rewardbench",
+        "version": "0.1.3",
+        "additional_details": {
+          "subsets": "Chat, Chat Hard, Safety, Reasoning",
+          "hf_space": "allenai/reward-bench"
+        }
+      },
+      "benchmark": "reward-bench",
+      "evaluation_results": [
         {
-          "evaluation_name": "Precise IF",
+          "evaluation_name": "Score",
           "metric_config": {
-            "evaluation_description": "Precise Instruction Following score",
+            "evaluation_description": "Overall RewardBench Score",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.35
+            "score": 0.9007
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Math",
+          "evaluation_name": "Chat",
           "metric_config": {
-            "evaluation_description": "Math score - measures mathematical reasoning",
+            "evaluation_description": "Chat accuracy - includes easy chat subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6339
+            "score": 0.8994
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Safety",
+          "evaluation_name": "Chat Hard",
           "metric_config": {
-            "evaluation_description": "Safety score - measures safety awareness",
+            "evaluation_description": "Chat Hard accuracy - includes hard chat subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.8911
+            "score": 0.875
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Focus",
+          "evaluation_name": "Safety",
           "metric_config": {
-            "evaluation_description": "Focus score - measures response focus",
+            "evaluation_description": "Safety accuracy - includes safety subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.8909
+            "score": 0.9108
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Ties",
+          "evaluation_name": "Reasoning",
           "metric_config": {
-            "evaluation_description": "Ties score - ability to identify tie cases",
+            "evaluation_description": "Reasoning accuracy - includes code and math subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7586
+            "score": 0.9176
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         }
       ],
diff --git a/data/models/sometimesanotion_qwenvergence-14b-v3-reason.json b/data/models/sometimesanotion_qwenvergence-14b-v3-reason.json
index 1f18d691fd936d47f7bbe51ac3217aef426c667e..a439bc62eb51d7fa9519bb2716501909fa712711 100644
--- a/data/models/sometimesanotion_qwenvergence-14b-v3-reason.json
+++ b/data/models/sometimesanotion_qwenvergence-14b-v3-reason.json
@@ -5,7 +5,7 @@
     "developer": "sometimesanotion",
     "inference_platform": "unknown",
     "additional_details": {
-      "precision": "bfloat16",
+      "precision": "float16",
       "architecture": "Qwen2ForCausalLM",
       "params_billions": "14.0"
     }
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5278
+            "score": 0.5367
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6557
+            "score": 0.6561
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3119
+            "score": 0.358
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3842
+            "score": 0.3867
           }
         },
         {
@@ -116,7 +116,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4754
+            "score": 0.474
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5396
+            "score": 0.5395
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5367
+            "score": 0.5278
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6561
+            "score": 0.6557
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.358
+            "score": 0.3119
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3867
+            "score": 0.3842
           }
         },
         {
@@ -246,7 +246,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.474
+            "score": 0.4754
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5395
+            "score": 0.5396
           }
         }
       ],
diff --git a/data/models/tanliboy_lambda-gemma-2-9b-dpo.json b/data/models/tanliboy_lambda-gemma-2-9b-dpo.json
index 7fb384620bce09b34b0d31ff763d2b1e971d0558..5d50cd0f56f0ac33470efc8c81f51c02a702598e 100644
--- a/data/models/tanliboy_lambda-gemma-2-9b-dpo.json
+++ b/data/models/tanliboy_lambda-gemma-2-9b-dpo.json
@@ -5,7 +5,7 @@
     "developer": "tanliboy",
     "inference_platform": "unknown",
     "additional_details": {
-      "precision": "bfloat16",
+      "precision": "float16",
       "architecture": "Gemma2ForCausalLM",
       "params_billions": "9.242"
     }
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1829
+            "score": 0.4501
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5488
+            "score": 0.5472
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0
+            "score": 0.0944
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3104
+            "score": 0.3138
           }
         },
         {
@@ -116,7 +116,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4056
+            "score": 0.4017
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3805
+            "score": 0.3792
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4501
+            "score": 0.1829
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5472
+            "score": 0.5488
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0944
+            "score": 0.0
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3138
+            "score": 0.3104
           }
         },
         {
@@ -246,7 +246,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4017
+            "score": 0.4056
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3792
+            "score": 0.3805
           }
         }
       ],
diff --git a/data/models/valiantlabs_llama3.1-8b-cobalt.json b/data/models/valiantlabs_llama3.1-8b-cobalt.json
index c47cbaf67f9d28f7ee6c973b80a6e624aec4a0cc..e1d1a85c95f8deab607165ea40b9f93f0dba9c6d 100644
--- a/data/models/valiantlabs_llama3.1-8b-cobalt.json
+++ b/data/models/valiantlabs_llama3.1-8b-cobalt.json
@@ -5,7 +5,7 @@
     "developer": "ValiantLabs",
     "inference_platform": "unknown",
     "additional_details": {
-      "precision": "float16",
+      "precision": "bfloat16",
       "architecture": "LlamaForCausalLM",
       "params_billions": "8.03"
     }
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3496
+            "score": 0.7168
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4947
+            "score": 0.4911
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1269
+            "score": 0.1533
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3037
+            "score": 0.2861
           }
         },
         {
@@ -116,7 +116,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3959
+            "score": 0.3512
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3644
+            "score": 0.3663
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7168
+            "score": 0.3496
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4911
+            "score": 0.4947
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1533
+            "score": 0.1269
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2861
+            "score": 0.3037
           }
         },
         {
@@ -246,7 +246,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3512
+            "score": 0.3959
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3663
+            "score": 0.3644
           }
         }
       ],
diff --git a/data/models/weqweasdas_hh_rlhf_rm_open_llama_3b.json b/data/models/weqweasdas_hh_rlhf_rm_open_llama_3b.json
index 564c2ceeb0768d947ec7e8507c351558f76e3907..f9d2b14f0a0f79f11e39957c0f38b89aa1e78ac9 100644
--- a/data/models/weqweasdas_hh_rlhf_rm_open_llama_3b.json
+++ b/data/models/weqweasdas_hh_rlhf_rm_open_llama_3b.json
@@ -9,10 +9,10 @@
   },
   "evaluations": [
     {
-      "evaluation_id": "reward-bench-2/weqweasdas_hh_rlhf_rm_open_llama_3b/1766412838.146816",
+      "evaluation_id": "reward-bench/weqweasdas_hh_rlhf_rm_open_llama_3b/1766412838.146816",
       "retrieved_timestamp": "1766412838.146816",
       "source_metadata": {
-        "source_name": "RewardBench 2",
+        "source_name": "RewardBench",
         "source_type": "documentation",
         "source_organization_name": "Allen Institute for AI",
         "source_organization_url": "https://allenai.org",
@@ -31,127 +31,109 @@
         {
           "evaluation_name": "Score",
           "metric_config": {
-            "evaluation_description": "Overall RewardBench 2 Score (mean of all metrics)",
-            "lower_is_better": false,
-            "score_type": "continuous",
-            "min_score": 0.0,
-            "max_score": 1.0
-          },
-          "score_details": {
-            "score": 0.2498
-          },
-          "source_data": {
-            "dataset_name": "RewardBench 2",
-            "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
-          }
-        },
-        {
-          "evaluation_name": "Factuality",
-          "metric_config": {
-            "evaluation_description": "Factuality score - measures factual accuracy",
+            "evaluation_description": "Overall RewardBench Score",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3642
+            "score": 0.5027
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Precise IF",
+          "evaluation_name": "Chat",
           "metric_config": {
-            "evaluation_description": "Precise Instruction Following score",
+            "evaluation_description": "Chat accuracy - includes easy chat subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.275
+            "score": 0.8184
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Math",
+          "evaluation_name": "Chat Hard",
           "metric_config": {
-            "evaluation_description": "Math score - measures mathematical reasoning",
+            "evaluation_description": "Chat Hard accuracy - includes hard chat subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3497
+            "score": 0.3728
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
           "evaluation_name": "Safety",
           "metric_config": {
-            "evaluation_description": "Safety score - measures safety awareness",
+            "evaluation_description": "Safety accuracy - includes safety subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.24
+            "score": 0.4149
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Focus",
+          "evaluation_name": "Reasoning",
           "metric_config": {
-            "evaluation_description": "Focus score - measures response focus",
+            "evaluation_description": "Reasoning accuracy - includes code and math subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2384
+            "score": 0.3281
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Ties",
+          "evaluation_name": "Prior Sets (0.5 weight)",
           "metric_config": {
-            "evaluation_description": "Ties score - ability to identify tie cases",
+            "evaluation_description": "Prior Sets score (weighted 0.5) - includes test sets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0315
+            "score": 0.6564
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         }
       ],
@@ -159,10 +141,10 @@
       "generation_config": null
     },
     {
-      "evaluation_id": "reward-bench/weqweasdas_hh_rlhf_rm_open_llama_3b/1766412838.146816",
+      "evaluation_id": "reward-bench-2/weqweasdas_hh_rlhf_rm_open_llama_3b/1766412838.146816",
       "retrieved_timestamp": "1766412838.146816",
       "source_metadata": {
-        "source_name": "RewardBench",
+        "source_name": "RewardBench 2",
         "source_type": "documentation",
         "source_organization_name": "Allen Institute for AI",
         "source_organization_url": "https://allenai.org",
@@ -181,109 +163,127 @@
         {
           "evaluation_name": "Score",
           "metric_config": {
-            "evaluation_description": "Overall RewardBench Score",
+            "evaluation_description": "Overall RewardBench 2 Score (mean of all metrics)",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5027
+            "score": 0.2498
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Chat",
+          "evaluation_name": "Factuality",
           "metric_config": {
-            "evaluation_description": "Chat accuracy - includes easy chat subsets",
+            "evaluation_description": "Factuality score - measures factual accuracy",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.8184
+            "score": 0.3642
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Chat Hard",
+          "evaluation_name": "Precise IF",
           "metric_config": {
-            "evaluation_description": "Chat Hard accuracy - includes hard chat subsets",
+            "evaluation_description": "Precise Instruction Following score",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3728
+            "score": 0.275
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
+          }
+        },
+        {
+          "evaluation_name": "Math",
+          "metric_config": {
+            "evaluation_description": "Math score - measures mathematical reasoning",
+            "lower_is_better": false,
+            "score_type": "continuous",
+            "min_score": 0.0,
+            "max_score": 1.0
+          },
+          "score_details": {
+            "score": 0.3497
+          },
+          "source_data": {
+            "dataset_name": "RewardBench 2",
+            "source_type": "hf_dataset",
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
           "evaluation_name": "Safety",
           "metric_config": {
-            "evaluation_description": "Safety accuracy - includes safety subsets",
+            "evaluation_description": "Safety score - measures safety awareness",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4149
+            "score": 0.24
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Reasoning",
+          "evaluation_name": "Focus",
           "metric_config": {
-            "evaluation_description": "Reasoning accuracy - includes code and math subsets",
+            "evaluation_description": "Focus score - measures response focus",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3281
+            "score": 0.2384
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Prior Sets (0.5 weight)",
+          "evaluation_name": "Ties",
           "metric_config": {
-            "evaluation_description": "Prior Sets score (weighted 0.5) - includes test sets",
+            "evaluation_description": "Ties score - ability to identify tie cases",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6564
+            "score": 0.0315
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         }
       ],
diff --git a/data/models/weqweasdas_rm-gemma-2b.json b/data/models/weqweasdas_rm-gemma-2b.json
index b1151d30882a530616e4e5f2252a198e5a25a8a2..23bdb9776ed416ae7ab56cbae8b9e5655ba27e0c 100644
--- a/data/models/weqweasdas_rm-gemma-2b.json
+++ b/data/models/weqweasdas_rm-gemma-2b.json
@@ -9,10 +9,10 @@
   },
   "evaluations": [
     {
-      "evaluation_id": "reward-bench-2/weqweasdas_RM-Gemma-2B/1766412838.146816",
+      "evaluation_id": "reward-bench/weqweasdas_RM-Gemma-2B/1766412838.146816",
       "retrieved_timestamp": "1766412838.146816",
       "source_metadata": {
-        "source_name": "RewardBench 2",
+        "source_name": "RewardBench",
         "source_type": "documentation",
         "source_organization_name": "Allen Institute for AI",
         "source_organization_url": "https://allenai.org",
@@ -31,127 +31,109 @@
         {
           "evaluation_name": "Score",
           "metric_config": {
-            "evaluation_description": "Overall RewardBench 2 Score (mean of all metrics)",
-            "lower_is_better": false,
-            "score_type": "continuous",
-            "min_score": 0.0,
-            "max_score": 1.0
-          },
-          "score_details": {
-            "score": 0.3057
-          },
-          "source_data": {
-            "dataset_name": "RewardBench 2",
-            "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
-          }
-        },
-        {
-          "evaluation_name": "Factuality",
-          "metric_config": {
-            "evaluation_description": "Factuality score - measures factual accuracy",
+            "evaluation_description": "Overall RewardBench Score",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3705
+            "score": 0.6549
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Precise IF",
+          "evaluation_name": "Chat",
           "metric_config": {
-            "evaluation_description": "Precise Instruction Following score",
+            "evaluation_description": "Chat accuracy - includes easy chat subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2812
+            "score": 0.9441
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Math",
+          "evaluation_name": "Chat Hard",
           "metric_config": {
-            "evaluation_description": "Math score - measures mathematical reasoning",
+            "evaluation_description": "Chat Hard accuracy - includes hard chat subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4317
+            "score": 0.4079
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
           "evaluation_name": "Safety",
           "metric_config": {
-            "evaluation_description": "Safety score - measures safety awareness",
+            "evaluation_description": "Safety accuracy - includes safety subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3311
+            "score": 0.4986
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Focus",
+          "evaluation_name": "Reasoning",
           "metric_config": {
-            "evaluation_description": "Focus score - measures response focus",
+            "evaluation_description": "Reasoning accuracy - includes code and math subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2343
+            "score": 0.7637
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Ties",
+          "evaluation_name": "Prior Sets (0.5 weight)",
           "metric_config": {
-            "evaluation_description": "Ties score - ability to identify tie cases",
+            "evaluation_description": "Prior Sets score (weighted 0.5) - includes test sets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1851
+            "score": 0.6652
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         }
       ],
@@ -159,10 +141,10 @@
       "generation_config": null
     },
     {
-      "evaluation_id": "reward-bench/weqweasdas_RM-Gemma-2B/1766412838.146816",
+      "evaluation_id": "reward-bench-2/weqweasdas_RM-Gemma-2B/1766412838.146816",
       "retrieved_timestamp": "1766412838.146816",
       "source_metadata": {
-        "source_name": "RewardBench",
+        "source_name": "RewardBench 2",
         "source_type": "documentation",
         "source_organization_name": "Allen Institute for AI",
         "source_organization_url": "https://allenai.org",
@@ -181,109 +163,127 @@
         {
           "evaluation_name": "Score",
           "metric_config": {
-            "evaluation_description": "Overall RewardBench Score",
+            "evaluation_description": "Overall RewardBench 2 Score (mean of all metrics)",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6549
+            "score": 0.3057
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Chat",
+          "evaluation_name": "Factuality",
           "metric_config": {
-            "evaluation_description": "Chat accuracy - includes easy chat subsets",
+            "evaluation_description": "Factuality score - measures factual accuracy",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9441
+            "score": 0.3705
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Chat Hard",
+          "evaluation_name": "Precise IF",
           "metric_config": {
-            "evaluation_description": "Chat Hard accuracy - includes hard chat subsets",
+            "evaluation_description": "Precise Instruction Following score",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4079
+            "score": 0.2812
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
+          }
+        },
+        {
+          "evaluation_name": "Math",
+          "metric_config": {
+            "evaluation_description": "Math score - measures mathematical reasoning",
+            "lower_is_better": false,
+            "score_type": "continuous",
+            "min_score": 0.0,
+            "max_score": 1.0
+          },
+          "score_details": {
+            "score": 0.4317
+          },
+          "source_data": {
+            "dataset_name": "RewardBench 2",
+            "source_type": "hf_dataset",
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
           "evaluation_name": "Safety",
           "metric_config": {
-            "evaluation_description": "Safety accuracy - includes safety subsets",
+            "evaluation_description": "Safety score - measures safety awareness",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4986
+            "score": 0.3311
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Reasoning",
+          "evaluation_name": "Focus",
           "metric_config": {
-            "evaluation_description": "Reasoning accuracy - includes code and math subsets",
+            "evaluation_description": "Focus score - measures response focus",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7637
+            "score": 0.2343
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Prior Sets (0.5 weight)",
+          "evaluation_name": "Ties",
           "metric_config": {
-            "evaluation_description": "Prior Sets score (weighted 0.5) - includes test sets",
+            "evaluation_description": "Ties score - ability to identify tie cases",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6652
+            "score": 0.1851
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         }
       ],
diff --git a/data/models/weqweasdas_rm-mistral-7b.json b/data/models/weqweasdas_rm-mistral-7b.json
index 2c0c95b4657b4530753b94c6c05b68b220f49072..014b8589e308fa2571a3ca85971364da616341ae 100644
--- a/data/models/weqweasdas_rm-mistral-7b.json
+++ b/data/models/weqweasdas_rm-mistral-7b.json
@@ -9,10 +9,10 @@
   },
   "evaluations": [
     {
-      "evaluation_id": "reward-bench-2/weqweasdas_RM-Mistral-7B/1766412838.146816",
+      "evaluation_id": "reward-bench/weqweasdas_RM-Mistral-7B/1766412838.146816",
       "retrieved_timestamp": "1766412838.146816",
       "source_metadata": {
-        "source_name": "RewardBench 2",
+        "source_name": "RewardBench",
         "source_type": "documentation",
         "source_organization_name": "Allen Institute for AI",
         "source_organization_url": "https://allenai.org",
@@ -31,127 +31,109 @@
         {
           "evaluation_name": "Score",
           "metric_config": {
-            "evaluation_description": "Overall RewardBench 2 Score (mean of all metrics)",
-            "lower_is_better": false,
-            "score_type": "continuous",
-            "min_score": 0.0,
-            "max_score": 1.0
-          },
-          "score_details": {
-            "score": 0.596
-          },
-          "source_data": {
-            "dataset_name": "RewardBench 2",
-            "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
-          }
-        },
-        {
-          "evaluation_name": "Factuality",
-          "metric_config": {
-            "evaluation_description": "Factuality score - measures factual accuracy",
+            "evaluation_description": "Overall RewardBench Score",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5937
+            "score": 0.7982
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Precise IF",
+          "evaluation_name": "Chat",
           "metric_config": {
-            "evaluation_description": "Precise Instruction Following score",
+            "evaluation_description": "Chat accuracy - includes easy chat subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3438
+            "score": 0.9665
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Math",
+          "evaluation_name": "Chat Hard",
           "metric_config": {
-            "evaluation_description": "Math score - measures mathematical reasoning",
+            "evaluation_description": "Chat Hard accuracy - includes hard chat subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5956
+            "score": 0.6053
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
           "evaluation_name": "Safety",
           "metric_config": {
-            "evaluation_description": "Safety score - measures safety awareness",
+            "evaluation_description": "Safety accuracy - includes safety subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6911
+            "score": 0.8703
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Focus",
+          "evaluation_name": "Reasoning",
           "metric_config": {
-            "evaluation_description": "Focus score - measures response focus",
+            "evaluation_description": "Reasoning accuracy - includes code and math subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7293
+            "score": 0.7736
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Ties",
+          "evaluation_name": "Prior Sets (0.5 weight)",
           "metric_config": {
-            "evaluation_description": "Ties score - ability to identify tie cases",
+            "evaluation_description": "Prior Sets score (weighted 0.5) - includes test sets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6226
+            "score": 0.753
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         }
       ],
@@ -159,10 +141,10 @@
       "generation_config": null
     },
     {
-      "evaluation_id": "reward-bench/weqweasdas_RM-Mistral-7B/1766412838.146816",
+      "evaluation_id": "reward-bench-2/weqweasdas_RM-Mistral-7B/1766412838.146816",
       "retrieved_timestamp": "1766412838.146816",
       "source_metadata": {
-        "source_name": "RewardBench",
+        "source_name": "RewardBench 2",
         "source_type": "documentation",
         "source_organization_name": "Allen Institute for AI",
         "source_organization_url": "https://allenai.org",
@@ -181,109 +163,127 @@
         {
           "evaluation_name": "Score",
           "metric_config": {
-            "evaluation_description": "Overall RewardBench Score",
+            "evaluation_description": "Overall RewardBench 2 Score (mean of all metrics)",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7982
+            "score": 0.596
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Chat",
+          "evaluation_name": "Factuality",
           "metric_config": {
-            "evaluation_description": "Chat accuracy - includes easy chat subsets",
+            "evaluation_description": "Factuality score - measures factual accuracy",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9665
+            "score": 0.5937
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Chat Hard",
+          "evaluation_name": "Precise IF",
           "metric_config": {
-            "evaluation_description": "Chat Hard accuracy - includes hard chat subsets",
+            "evaluation_description": "Precise Instruction Following score",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6053
+            "score": 0.3438
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
+          }
+        },
+        {
+          "evaluation_name": "Math",
+          "metric_config": {
+            "evaluation_description": "Math score - measures mathematical reasoning",
+            "lower_is_better": false,
+            "score_type": "continuous",
+            "min_score": 0.0,
+            "max_score": 1.0
+          },
+          "score_details": {
+            "score": 0.5956
+          },
+          "source_data": {
+            "dataset_name": "RewardBench 2",
+            "source_type": "hf_dataset",
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
           "evaluation_name": "Safety",
           "metric_config": {
-            "evaluation_description": "Safety accuracy - includes safety subsets",
+            "evaluation_description": "Safety score - measures safety awareness",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.8703
+            "score": 0.6911
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Reasoning",
+          "evaluation_name": "Focus",
           "metric_config": {
-            "evaluation_description": "Reasoning accuracy - includes code and math subsets",
+            "evaluation_description": "Focus score - measures response focus",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7736
+            "score": 0.7293
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Prior Sets (0.5 weight)",
+          "evaluation_name": "Ties",
           "metric_config": {
-            "evaluation_description": "Prior Sets score (weighted 0.5) - includes test sets",
+            "evaluation_description": "Ties score - ability to identify tie cases",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.753
+            "score": 0.6226
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         }
       ],
diff --git a/data/models/yam-peleg_hebrew-mistral-7b-200k.json b/data/models/yam-peleg_hebrew-mistral-7b-200k.json
index 1a70a6eb9b375af7d3ae622e407043222ccb78a0..baae674a05af479a549c721b22d1c0240e173193 100644
--- a/data/models/yam-peleg_hebrew-mistral-7b-200k.json
+++ b/data/models/yam-peleg_hebrew-mistral-7b-200k.json
@@ -5,7 +5,7 @@
     "developer": "yam-peleg",
     "inference_platform": "unknown",
     "additional_details": {
-      "precision": "bfloat16",
+      "precision": "float16",
       "architecture": "MistralForCausalLM",
       "params_billions": "7.504"
     }
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.177
+            "score": 0.1856
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3411
+            "score": 0.4149
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.031
+            "score": 0.0234
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2534
+            "score": 0.276
           }
         },
         {
@@ -116,7 +116,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.374
+            "score": 0.3765
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2529
+            "score": 0.2573
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1856
+            "score": 0.177
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4149
+            "score": 0.3411
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0234
+            "score": 0.031
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.276
+            "score": 0.2534
           }
         },
         {
@@ -246,7 +246,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3765
+            "score": 0.374
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2573
+            "score": 0.2529
           }
         }
       ],
diff --git a/data/models/zhipu-ai_glm-4.7.json b/data/models/zhipu-ai_glm-4.7.json
index ef6efd4fd9091259b58749fefdf86e2517723096..9ffeed9fa5797e0518c941376cc795f418b5ed1c 100644
--- a/data/models/zhipu-ai_glm-4.7.json
+++ b/data/models/zhipu-ai_glm-4.7.json
@@ -4,13 +4,13 @@
     "id": "zhipu-ai/glm-4.7",
     "developer": "Z-AI",
     "additional_details": {
-      "agent_name": "Terminus 2",
-      "agent_organization": "Terminal Bench"
+      "agent_name": "Crux",
+      "agent_organization": "Roam"
     }
   },
   "evaluations": [
     {
-      "evaluation_id": "terminal-bench-2.0/terminus-2__glm-4.7/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/crux__glm-4.7/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -34,7 +34,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2026-01-28",
+          "evaluation_timestamp": "2026-02-08",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -43,17 +43,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 33.4,
+            "score": 33.3,
             "uncertainty": {
               "standard_error": {
-                "value": 2.8
+                "value": 2.5
               },
               "num_samples": 435
             }
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"GLM 4.7\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Crux\" -m \"GLM 4.7\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -70,7 +70,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"GLM 4.7\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Crux\" -m \"GLM 4.7\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -84,7 +84,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/crux__glm-4.7/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/terminus-2__glm-4.7/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -108,7 +108,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2026-02-08",
+          "evaluation_timestamp": "2026-01-28",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -117,17 +117,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 33.3,
+            "score": 33.4,
             "uncertainty": {
               "standard_error": {
-                "value": 2.5
+                "value": 2.8
               },
               "num_samples": 435
             }
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Crux\" -m \"GLM 4.7\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"GLM 4.7\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -144,7 +144,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Crux\" -m \"GLM 4.7\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"GLM 4.7\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {