diff --git a/data/benchmarks.json b/data/benchmarks.json
index 9571727dfcd0f5a5c4445684a0e339ea8b9100b5..90e9c7c4a82eb916eea7f40ad4a052dd6581fb2c 100644
--- a/data/benchmarks.json
+++ b/data/benchmarks.json
@@ -45,7 +45,7 @@
   },
   {
     "benchmark": "hfopenllm_v2",
-    "model_count": 4493
+    "model_count": 4494
   },
   {
     "benchmark": "la_leaderboard",
@@ -57,7 +57,7 @@
   },
   {
     "benchmark": "reward-bench",
-    "model_count": 327
+    "model_count": 328
   },
   {
     "benchmark": "swe-bench",
diff --git a/data/benchmarks/appworld_test_normal.json b/data/benchmarks/appworld_test_normal.json
index df9e46daf5dd19a85e092a1af20da57930852dac..f3651490370442b9e2747ece9b07271eac5de3ad 100644
--- a/data/benchmarks/appworld_test_normal.json
+++ b/data/benchmarks/appworld_test_normal.json
@@ -13,7 +13,7 @@
       "name": "gemini-3-pro-preview",
       "developer": "Google",
       "scores": {
-        "appworld/test_normal": 0.36
+        "appworld/test_normal": 0.13
       }
     },
     {
diff --git a/data/benchmarks/browsecompplus.json b/data/benchmarks/browsecompplus.json
index 34f802eb19d92b7a54aef0531fdda5bcd88b81cf..130d44f42fc301b55e5c6bce906e1c1263721368 100644
--- a/data/benchmarks/browsecompplus.json
+++ b/data/benchmarks/browsecompplus.json
@@ -5,7 +5,7 @@
       "name": "claude-opus-4-5",
       "developer": "Anthropic",
       "scores": {
-        "browsecompplus": 0.61
+        "browsecompplus": 0.49
       }
     },
     {
@@ -21,7 +21,7 @@
       "name": "gpt-5.2-2025-12-11",
       "developer": "OpenAI",
       "scores": {
-        "browsecompplus": 0.26
+        "browsecompplus": 0.48
       }
     }
   ]
diff --git a/data/benchmarks/hfopenllm_v2.json b/data/benchmarks/hfopenllm_v2.json
index 69cfd9d7907951c5385529f14c35f4b9a0820d64..589e88495313e5113fd7851135b88baeeba06feb 100644
--- a/data/benchmarks/hfopenllm_v2.json
+++ b/data/benchmarks/hfopenllm_v2.json
@@ -1019,12 +1019,12 @@
       "name": "Qwen2.5-1.5B-continuous-learnt",
       "developer": "AtAndDev",
       "scores": {
-        "IFEval": 0.4605,
-        "BBH": 0.4258,
-        "MATH Level 5": 0.0748,
-        "GPQA": 0.2659,
-        "MUSR": 0.3636,
-        "MMLU-PRO": 0.2812
+        "IFEval": 0.4511,
+        "BBH": 0.4275,
+        "MATH Level 5": 0.1473,
+        "GPQA": 0.2701,
+        "MUSR": 0.3623,
+        "MMLU-PRO": 0.2806
       }
     },
     {
@@ -1747,12 +1747,12 @@
       "name": "NeuralDaredevil-SuperNova-Lite-7B-DARETIES-abliterated",
       "developer": "BoltMonkey",
       "scores": {
-        "IFEval": 0.7999,
-        "BBH": 0.5152,
-        "MATH Level 5": 0.1193,
-        "GPQA": 0.281,
-        "MUSR": 0.4019,
-        "MMLU-PRO": 0.3733
+        "IFEval": 0.459,
+        "BBH": 0.5185,
+        "MATH Level 5": 0.0937,
+        "GPQA": 0.2743,
+        "MUSR": 0.4083,
+        "MMLU-PRO": 0.3631
       }
     },
     {
@@ -3229,12 +3229,12 @@
       "name": "PathfinderAI",
       "developer": "Daemontatox",
       "scores": {
-        "IFEval": 0.3745,
-        "BBH": 0.6668,
-        "MATH Level 5": 0.4758,
-        "GPQA": 0.3943,
-        "MUSR": 0.4858,
-        "MMLU-PRO": 0.5593
+        "IFEval": 0.4855,
+        "BBH": 0.6627,
+        "MATH Level 5": 0.4841,
+        "GPQA": 0.3096,
+        "MUSR": 0.4256,
+        "MMLU-PRO": 0.5542
       }
     },
     {
@@ -4009,12 +4009,12 @@
       "name": "Llama-3.2-1B-SPIN-iter0",
       "developer": "DavieLion",
       "scores": {
-        "IFEval": 0.1549,
-        "BBH": 0.2937,
-        "MATH Level 5": 0.006,
-        "GPQA": 0.2576,
+        "IFEval": 0.1507,
+        "BBH": 0.293,
+        "MATH Level 5": 0.0,
+        "GPQA": 0.2534,
         "MUSR": 0.3565,
-        "MMLU-PRO": 0.1128
+        "MMLU-PRO": 0.1125
       }
     },
     {
@@ -4646,12 +4646,12 @@
       "name": "MN-12B-LilithFrame",
       "developer": "DoppelReflEx",
       "scores": {
-        "IFEval": 0.436,
-        "BBH": 0.4956,
-        "MATH Level 5": 0.0589,
-        "GPQA": 0.3205,
-        "MUSR": 0.3843,
-        "MMLU-PRO": 0.3237
+        "IFEval": 0.451,
+        "BBH": 0.4944,
+        "MATH Level 5": 0.1156,
+        "GPQA": 0.3196,
+        "MUSR": 0.3896,
+        "MMLU-PRO": 0.3256
       }
     },
     {
@@ -8728,12 +8728,12 @@
       "name": "Gemma-Ko-Merge-PEFT",
       "developer": "Gunulhona",
       "scores": {
-        "IFEval": 0.288,
-        "BBH": 0.5154,
+        "IFEval": 0.4441,
+        "BBH": 0.4863,
         "MATH Level 5": 0.0,
-        "GPQA": 0.3247,
-        "MUSR": 0.408,
-        "MMLU-PRO": 0.3817
+        "GPQA": 0.307,
+        "MUSR": 0.3986,
+        "MMLU-PRO": 0.3098
       }
     },
     {
@@ -9144,12 +9144,12 @@
       "name": "SmolLM2-135M-Instruct",
       "developer": "HuggingFaceTB",
       "scores": {
-        "IFEval": 0.2883,
-        "BBH": 0.3124,
-        "MATH Level 5": 0.003,
-        "GPQA": 0.2357,
-        "MUSR": 0.3662,
-        "MMLU-PRO": 0.1115
+        "IFEval": 0.0593,
+        "BBH": 0.3135,
+        "MATH Level 5": 0.0144,
+        "GPQA": 0.2341,
+        "MUSR": 0.3871,
+        "MMLU-PRO": 0.1092
       }
     },
     {
@@ -9378,12 +9378,12 @@
       "name": "JOSIEv4o-8b-stage1-v4",
       "developer": "Isaak-Carter",
       "scores": {
-        "IFEval": 0.2553,
-        "BBH": 0.4725,
-        "MATH Level 5": 0.0529,
-        "GPQA": 0.2919,
-        "MUSR": 0.3654,
-        "MMLU-PRO": 0.3316
+        "IFEval": 0.2477,
+        "BBH": 0.4758,
+        "MATH Level 5": 0.0453,
+        "GPQA": 0.2911,
+        "MUSR": 0.3641,
+        "MMLU-PRO": 0.3292
       }
     },
     {
@@ -13031,12 +13031,12 @@
       "name": "SpydazWeb_AI_HumanAI_012_INSTRUCT_IA",
       "developer": "LeroyDyer",
       "scores": {
-        "IFEval": 0.3066,
-        "BBH": 0.4577,
+        "IFEval": 0.3036,
+        "BBH": 0.4575,
         "MATH Level 5": 0.0446,
-        "GPQA": 0.2995,
-        "MUSR": 0.4254,
-        "MMLU-PRO": 0.2318
+        "GPQA": 0.3012,
+        "MUSR": 0.4253,
+        "MMLU-PRO": 0.2329
       }
     },
     {
@@ -18141,11 +18141,11 @@
       "developer": "PrimeIntellect",
       "scores": {
         "IFEval": 0.1757,
-        "BBH": 0.276,
+        "BBH": 0.274,
         "MATH Level 5": 0.0,
-        "GPQA": 0.2534,
-        "MUSR": 0.3339,
-        "MMLU-PRO": 0.1123
+        "GPQA": 0.25,
+        "MUSR": 0.3753,
+        "MMLU-PRO": 0.112
       }
     },
     {
@@ -18712,12 +18712,12 @@
       "name": "ODB-14B-sce",
       "developer": "Quazim0t0",
       "scores": {
-        "IFEval": 0.7016,
-        "BBH": 0.6942,
-        "MATH Level 5": 0.4116,
-        "GPQA": 0.3624,
-        "MUSR": 0.4571,
-        "MMLU-PRO": 0.5411
+        "IFEval": 0.2922,
+        "BBH": 0.6559,
+        "MATH Level 5": 0.2545,
+        "GPQA": 0.2659,
+        "MUSR": 0.3929,
+        "MMLU-PRO": 0.5207
       }
     },
     {
@@ -19726,12 +19726,12 @@
       "name": "Qwen2.5-Coder-7B-Instruct",
       "developer": "Qwen",
       "scores": {
-        "IFEval": 0.6101,
-        "BBH": 0.5008,
-        "MATH Level 5": 0.3716,
-        "GPQA": 0.2919,
-        "MUSR": 0.4073,
-        "MMLU-PRO": 0.3352
+        "IFEval": 0.6147,
+        "BBH": 0.4999,
+        "MATH Level 5": 0.031,
+        "GPQA": 0.2936,
+        "MUSR": 0.4099,
+        "MMLU-PRO": 0.3354
       }
     },
     {
@@ -25069,12 +25069,12 @@
       "name": "Llama3.1-8B-Cobalt",
       "developer": "ValiantLabs",
       "scores": {
-        "IFEval": 0.3496,
-        "BBH": 0.4947,
-        "MATH Level 5": 0.1269,
-        "GPQA": 0.3037,
-        "MUSR": 0.3959,
-        "MMLU-PRO": 0.3644
+        "IFEval": 0.7168,
+        "BBH": 0.4911,
+        "MATH Level 5": 0.1533,
+        "GPQA": 0.2861,
+        "MUSR": 0.3512,
+        "MMLU-PRO": 0.3663
       }
     },
     {
@@ -25121,12 +25121,12 @@
       "name": "Llama3.1-8B-ShiningValiant2",
       "developer": "ValiantLabs",
       "scores": {
-        "IFEval": 0.2678,
-        "BBH": 0.4429,
-        "MATH Level 5": 0.0521,
-        "GPQA": 0.302,
-        "MUSR": 0.3959,
-        "MMLU-PRO": 0.2927
+        "IFEval": 0.6496,
+        "BBH": 0.4774,
+        "MATH Level 5": 0.0566,
+        "GPQA": 0.3104,
+        "MUSR": 0.3909,
+        "MMLU-PRO": 0.3382
       }
     },
     {
@@ -26603,12 +26603,12 @@
       "name": "QAIMath-Qwen2.5-7B-TIES",
       "developer": "adriszmar",
       "scores": {
-        "IFEval": 0.1685,
-        "BBH": 0.3124,
-        "MATH Level 5": 0.0015,
-        "GPQA": 0.2492,
-        "MUSR": 0.3963,
-        "MMLU-PRO": 0.1066
+        "IFEval": 0.1746,
+        "BBH": 0.3126,
+        "MATH Level 5": 0.0,
+        "GPQA": 0.245,
+        "MUSR": 0.4096,
+        "MMLU-PRO": 0.1087
       }
     },
     {
@@ -26954,12 +26954,12 @@
       "name": "Llama-3.1-Tulu-3-8B",
       "developer": "allenai",
       "scores": {
-        "IFEval": 0.8255,
-        "BBH": 0.4061,
-        "MATH Level 5": 0.2115,
-        "GPQA": 0.297,
+        "IFEval": 0.8267,
+        "BBH": 0.405,
+        "MATH Level 5": 0.1964,
+        "GPQA": 0.2987,
         "MUSR": 0.4175,
-        "MMLU-PRO": 0.2821
+        "MMLU-PRO": 0.2827
       }
     },
     {
@@ -28449,11 +28449,11 @@
       "name": "AMD-Llama-135m",
       "developer": "amd",
       "scores": {
-        "IFEval": 0.1842,
-        "BBH": 0.2974,
-        "MATH Level 5": 0.0053,
-        "GPQA": 0.2525,
-        "MUSR": 0.378,
+        "IFEval": 0.1918,
+        "BBH": 0.2969,
+        "MATH Level 5": 0.0076,
+        "GPQA": 0.2584,
+        "MUSR": 0.3846,
         "MMLU-PRO": 0.1169
       }
     },
@@ -30360,12 +30360,12 @@
       "name": "Llama-3.2-3B-Deep-Test",
       "developer": "bunnycore",
       "scores": {
-        "IFEval": 0.4652,
-        "BBH": 0.4531,
-        "MATH Level 5": 0.1284,
-        "GPQA": 0.2643,
-        "MUSR": 0.3394,
-        "MMLU-PRO": 0.3152
+        "IFEval": 0.1775,
+        "BBH": 0.295,
+        "MATH Level 5": 0.0,
+        "GPQA": 0.2517,
+        "MUSR": 0.3647,
+        "MMLU-PRO": 0.1049
       }
     },
     {
@@ -31790,12 +31790,12 @@
       "name": "llama-43m-beta",
       "developer": "cpayne1303",
       "scores": {
-        "IFEval": 0.1949,
-        "BBH": 0.2965,
-        "MATH Level 5": 0.0045,
+        "IFEval": 0.1916,
+        "BBH": 0.2977,
+        "MATH Level 5": 0.0,
         "GPQA": 0.2685,
-        "MUSR": 0.3885,
-        "MMLU-PRO": 0.1111
+        "MUSR": 0.3872,
+        "MMLU-PRO": 0.1132
       }
     },
     {
@@ -32167,12 +32167,12 @@
       "name": "Llama-3-8B-Orpo-v0.1",
       "developer": "dfurman",
       "scores": {
-        "IFEval": 0.2835,
-        "BBH": 0.3842,
-        "MATH Level 5": 0.0521,
-        "GPQA": 0.2609,
-        "MUSR": 0.3566,
-        "MMLU-PRO": 0.2298
+        "IFEval": 0.3,
+        "BBH": 0.3853,
+        "MATH Level 5": 0.0415,
+        "GPQA": 0.2617,
+        "MUSR": 0.3579,
+        "MMLU-PRO": 0.2281
       }
     },
     {
@@ -34572,12 +34572,12 @@
       "name": "flan-t5-xl",
       "developer": "Google",
       "scores": {
-        "IFEval": 0.2207,
-        "BBH": 0.4537,
-        "MATH Level 5": 0.0008,
-        "GPQA": 0.2458,
-        "MUSR": 0.422,
-        "MMLU-PRO": 0.2142
+        "IFEval": 0.2237,
+        "BBH": 0.4531,
+        "MATH Level 5": 0.0076,
+        "GPQA": 0.2525,
+        "MUSR": 0.4181,
+        "MMLU-PRO": 0.2147
       }
     },
     {
@@ -34689,12 +34689,12 @@
       "name": "gemma-2-2b-jpn-it",
       "developer": "Google",
       "scores": {
-        "IFEval": 0.5288,
-        "BBH": 0.4178,
-        "MATH Level 5": 0.0476,
-        "GPQA": 0.2752,
-        "MUSR": 0.3728,
-        "MMLU-PRO": 0.2467
+        "IFEval": 0.5078,
+        "BBH": 0.4226,
+        "MATH Level 5": 0.0347,
+        "GPQA": 0.2852,
+        "MUSR": 0.3964,
+        "MMLU-PRO": 0.2578
       }
     },
     {
@@ -37271,6 +37271,19 @@
         "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",
@@ -42346,12 +42359,12 @@
       "name": "Mistral-v0.3-7B-ORPO",
       "developer": "llmat",
       "scores": {
-        "IFEval": 0.377,
-        "BBH": 0.3978,
-        "MATH Level 5": 0.0242,
-        "GPQA": 0.2668,
-        "MUSR": 0.3555,
-        "MMLU-PRO": 0.2278
+        "IFEval": 0.364,
+        "BBH": 0.4005,
+        "MATH Level 5": 0.0015,
+        "GPQA": 0.2693,
+        "MUSR": 0.3529,
+        "MMLU-PRO": 0.2301
       }
     },
     {
@@ -43971,12 +43984,12 @@
       "name": "Phi-3-mini-4k-instruct",
       "developer": "microsoft",
       "scores": {
-        "IFEval": 0.5613,
-        "BBH": 0.5676,
-        "MATH Level 5": 0.1163,
-        "GPQA": 0.3196,
-        "MUSR": 0.395,
-        "MMLU-PRO": 0.3866
+        "IFEval": 0.5477,
+        "BBH": 0.5491,
+        "MATH Level 5": 0.1639,
+        "GPQA": 0.3322,
+        "MUSR": 0.4284,
+        "MMLU-PRO": 0.4022
       }
     },
     {
@@ -44101,12 +44114,12 @@
       "name": "phi-4",
       "developer": "microsoft",
       "scores": {
-        "IFEval": 0.0488,
-        "BBH": 0.6703,
-        "MATH Level 5": 0.2787,
-        "GPQA": 0.401,
+        "IFEval": 0.0585,
+        "BBH": 0.6691,
+        "MATH Level 5": 0.3165,
+        "GPQA": 0.406,
         "MUSR": 0.5034,
-        "MMLU-PRO": 0.5295
+        "MMLU-PRO": 0.5287
       }
     },
     {
@@ -44465,12 +44478,12 @@
       "name": "Mixtral-8x7B-v0.1",
       "developer": "mistralai",
       "scores": {
-        "IFEval": 0.2326,
-        "BBH": 0.5098,
-        "MATH Level 5": 0.0937,
-        "GPQA": 0.3205,
-        "MUSR": 0.4413,
-        "MMLU-PRO": 0.3871
+        "IFEval": 0.2415,
+        "BBH": 0.5087,
+        "MATH Level 5": 0.102,
+        "GPQA": 0.3138,
+        "MUSR": 0.4321,
+        "MMLU-PRO": 0.385
       }
     },
     {
@@ -44725,12 +44738,12 @@
       "name": "NeuralDaredevil-8B-abliterated",
       "developer": "mlabonne",
       "scores": {
-        "IFEval": 0.4162,
-        "BBH": 0.5124,
-        "MATH Level 5": 0.0853,
-        "GPQA": 0.3029,
-        "MUSR": 0.415,
-        "MMLU-PRO": 0.3802
+        "IFEval": 0.7561,
+        "BBH": 0.5111,
+        "MATH Level 5": 0.0906,
+        "GPQA": 0.3062,
+        "MUSR": 0.4019,
+        "MMLU-PRO": 0.3841
       }
     },
     {
@@ -45063,12 +45076,12 @@
       "name": "Mistral-Nemo-Kurdish-Instruct",
       "developer": "nazimali",
       "scores": {
-        "IFEval": 0.486,
-        "BBH": 0.4721,
-        "MATH Level 5": 0.0846,
-        "GPQA": 0.2844,
-        "MUSR": 0.4006,
-        "MMLU-PRO": 0.3087
+        "IFEval": 0.4964,
+        "BBH": 0.4699,
+        "MATH Level 5": 0.0045,
+        "GPQA": 0.2827,
+        "MUSR": 0.3979,
+        "MMLU-PRO": 0.3063
       }
     },
     {
@@ -47598,12 +47611,12 @@
       "name": "wide_3b_sft_stage1.1-ss1-with_generics_intr_math_stories.no_issue",
       "developer": "ontocord",
       "scores": {
-        "IFEval": 0.1128,
-        "BBH": 0.3171,
-        "MATH Level 5": 0.0113,
-        "GPQA": 0.2685,
-        "MUSR": 0.346,
-        "MMLU-PRO": 0.1129
+        "IFEval": 0.1162,
+        "BBH": 0.3184,
+        "MATH Level 5": 0.0076,
+        "GPQA": 0.2634,
+        "MUSR": 0.3447,
+        "MMLU-PRO": 0.1124
       }
     },
     {
@@ -49431,12 +49444,12 @@
       "name": "Calcium-Opus-14B-Elite",
       "developer": "prithivMLmods",
       "scores": {
-        "IFEval": 0.6064,
-        "BBH": 0.6296,
-        "MATH Level 5": 0.3708,
-        "GPQA": 0.3733,
-        "MUSR": 0.4873,
-        "MMLU-PRO": 0.5307
+        "IFEval": 0.6052,
+        "BBH": 0.6317,
+        "MATH Level 5": 0.4789,
+        "GPQA": 0.3742,
+        "MUSR": 0.486,
+        "MMLU-PRO": 0.5302
       }
     },
     {
@@ -50848,12 +50861,12 @@
       "name": "Oracle-14B",
       "developer": "qingy2019",
       "scores": {
-        "IFEval": 0.2401,
-        "BBH": 0.4622,
-        "MATH Level 5": 0.0725,
-        "GPQA": 0.2609,
-        "MUSR": 0.3703,
-        "MMLU-PRO": 0.2379
+        "IFEval": 0.2358,
+        "BBH": 0.4612,
+        "MATH Level 5": 0.0642,
+        "GPQA": 0.2576,
+        "MUSR": 0.3717,
+        "MMLU-PRO": 0.2382
       }
     },
     {
@@ -50861,12 +50874,12 @@
       "name": "Qwen2.5-Math-14B-Instruct",
       "developer": "qingy2019",
       "scores": {
-        "IFEval": 0.6066,
-        "BBH": 0.635,
-        "MATH Level 5": 0.3716,
-        "GPQA": 0.3725,
+        "IFEval": 0.6005,
+        "BBH": 0.6356,
+        "MATH Level 5": 0.2764,
+        "GPQA": 0.3691,
         "MUSR": 0.4757,
-        "MMLU-PRO": 0.5331
+        "MMLU-PRO": 0.5339
       }
     },
     {
@@ -51589,12 +51602,12 @@
       "name": "Rombos-LLM-V2.5.1-Qwen-3b",
       "developer": "rombodawg",
       "scores": {
-        "IFEval": 0.2595,
-        "BBH": 0.3884,
-        "MATH Level 5": 0.0914,
-        "GPQA": 0.2743,
+        "IFEval": 0.2566,
+        "BBH": 0.39,
+        "MATH Level 5": 0.1208,
+        "GPQA": 0.2626,
         "MUSR": 0.3991,
-        "MMLU-PRO": 0.2719
+        "MMLU-PRO": 0.2741
       }
     },
     {
@@ -54332,12 +54345,12 @@
       "name": "lambda-gemma-2-9b-dpo",
       "developer": "tanliboy",
       "scores": {
-        "IFEval": 0.1829,
-        "BBH": 0.5488,
-        "MATH Level 5": 0.0,
-        "GPQA": 0.3104,
-        "MUSR": 0.4056,
-        "MMLU-PRO": 0.3805
+        "IFEval": 0.4501,
+        "BBH": 0.5472,
+        "MATH Level 5": 0.0944,
+        "GPQA": 0.3138,
+        "MUSR": 0.4017,
+        "MMLU-PRO": 0.3792
       }
     },
     {
@@ -56932,12 +56945,12 @@
       "name": "Hebrew-Mistral-7B-200K",
       "developer": "yam-peleg",
       "scores": {
-        "IFEval": 0.177,
-        "BBH": 0.3411,
-        "MATH Level 5": 0.031,
-        "GPQA": 0.2534,
-        "MUSR": 0.374,
-        "MMLU-PRO": 0.2529
+        "IFEval": 0.1856,
+        "BBH": 0.4149,
+        "MATH Level 5": 0.0234,
+        "GPQA": 0.276,
+        "MUSR": 0.3765,
+        "MMLU-PRO": 0.2573
       }
     },
     {
@@ -56984,12 +56997,12 @@
       "name": "BagelMIsteryTour-v2-8x7B",
       "developer": "ycros",
       "scores": {
-        "IFEval": 0.5994,
-        "BBH": 0.5159,
-        "MATH Level 5": 0.0785,
-        "GPQA": 0.3045,
-        "MUSR": 0.4203,
-        "MMLU-PRO": 0.3473
+        "IFEval": 0.6262,
+        "BBH": 0.5142,
+        "MATH Level 5": 0.0937,
+        "GPQA": 0.3079,
+        "MUSR": 0.4138,
+        "MMLU-PRO": 0.3481
       }
     },
     {
diff --git a/data/benchmarks/livecodebenchpro.json b/data/benchmarks/livecodebenchpro.json
index f8f77204727bc54bca1bbaaa204ca44d2b265f12..449e36cb0d36e98776192be2ede4fd274d74ec7e 100644
--- a/data/benchmarks/livecodebenchpro.json
+++ b/data/benchmarks/livecodebenchpro.json
@@ -255,9 +255,9 @@
       "name": "o4-mini-2025-04-16",
       "developer": "OpenAI",
       "scores": {
-        "Hard Problems": 0.0143,
-        "Medium Problems": 0.2923,
-        "Easy Problems": 0.8571
+        "Hard Problems": 0.014084507042253521,
+        "Medium Problems": 0.30985915492957744,
+        "Easy Problems": 0.8873239436619719
       }
     },
     {
diff --git a/data/benchmarks/reward-bench.json b/data/benchmarks/reward-bench.json
index 71717215bb28d07da86d76055db6b05b5dbcd648..435eb05406175ffe8530e3141464bcd0e3abcc31 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": 0.5736,
-        "Chat": 0.9749,
-        "Chat Hard": 0.5724,
-        "Safety": 0.7178,
-        "Reasoning": 0.8775,
-        "Prior Sets (0.5 weight)": 0.7029,
+        "Score": 0.8172,
         "Factuality": 0.5347,
         "Precise IF": 0.3563,
         "Math": 0.6066,
+        "Safety": 0.9014,
         "Focus": 0.5737,
-        "Ties": 0.6527
+        "Ties": 0.6527,
+        "Chat": 0.9749,
+        "Chat Hard": 0.5724,
+        "Reasoning": 0.8775,
+        "Prior Sets (0.5 weight)": 0.7029
       }
     },
     {
@@ -499,17 +499,17 @@
       "name": "Nexusflow/Starling-RM-34B",
       "developer": "Nexusflow",
       "scores": {
-        "Score": 0.8133,
+        "Score": 0.4553,
+        "Chat": 0.9693,
+        "Chat Hard": 0.5724,
+        "Safety": 0.7556,
+        "Reasoning": 0.8845,
+        "Prior Sets (0.5 weight)": 0.7137,
         "Factuality": 0.4589,
         "Precise IF": 0.3187,
         "Math": 0.6175,
-        "Safety": 0.877,
         "Focus": 0.4808,
-        "Ties": 0.1004,
-        "Chat": 0.9693,
-        "Chat Hard": 0.5724,
-        "Reasoning": 0.8845,
-        "Prior Sets (0.5 weight)": 0.7137
+        "Ties": 0.1004
       }
     },
     {
@@ -555,17 +555,17 @@
       "name": "OpenAssistant/oasst-rm-2-pythia-6.9b-epoch-1",
       "developer": "OpenAssistant",
       "scores": {
-        "Score": 0.615,
+        "Score": 0.2653,
+        "Chat": 0.9246,
+        "Chat Hard": 0.3728,
+        "Safety": 0.3289,
+        "Reasoning": 0.5855,
+        "Prior Sets (0.5 weight)": 0.6801,
         "Factuality": 0.3979,
         "Precise IF": 0.2875,
         "Math": 0.377,
-        "Safety": 0.5446,
         "Focus": 0.1535,
-        "Ties": 0.047,
-        "Chat": 0.9246,
-        "Chat Hard": 0.3728,
-        "Reasoning": 0.5855,
-        "Prior Sets (0.5 weight)": 0.6801
+        "Ties": 0.047
       }
     },
     {
@@ -573,17 +573,17 @@
       "name": "OpenAssistant/oasst-rm-2.1-pythia-1.4b-epoch-2.5",
       "developer": "OpenAssistant",
       "scores": {
-        "Score": 0.6901,
+        "Score": 0.2648,
+        "Chat": 0.8855,
+        "Chat Hard": 0.4868,
+        "Safety": 0.3244,
+        "Reasoning": 0.7752,
+        "Prior Sets (0.5 weight)": 0.6533,
         "Factuality": 0.3179,
         "Precise IF": 0.2625,
         "Math": 0.3934,
-        "Safety": 0.6311,
         "Focus": 0.2707,
-        "Ties": 0.0198,
-        "Chat": 0.8855,
-        "Chat Hard": 0.4868,
-        "Reasoning": 0.7752,
-        "Prior Sets (0.5 weight)": 0.6533
+        "Ties": 0.0198
       }
     },
     {
@@ -591,17 +591,17 @@
       "name": "OpenAssistant/reward-model-deberta-v3-large-v2",
       "developer": "OpenAssistant",
       "scores": {
-        "Score": 0.6126,
+        "Score": 0.32,
+        "Chat": 0.8939,
+        "Chat Hard": 0.4518,
+        "Safety": 0.3667,
+        "Reasoning": 0.3855,
+        "Prior Sets (0.5 weight)": 0.5836,
         "Factuality": 0.3853,
         "Precise IF": 0.2687,
         "Math": 0.5027,
-        "Safety": 0.7338,
         "Focus": 0.2768,
-        "Ties": 0.12,
-        "Chat": 0.8939,
-        "Chat Hard": 0.4518,
-        "Reasoning": 0.3855,
-        "Prior Sets (0.5 weight)": 0.5836
+        "Ties": 0.12
       }
     },
     {
@@ -627,17 +627,17 @@
       "name": "PKU-Alignment/beaver-7b-v1.0-reward",
       "developer": "PKU-Alignment",
       "scores": {
-        "Score": 0.4727,
+        "Score": 0.1606,
+        "Chat": 0.8184,
+        "Chat Hard": 0.2873,
+        "Safety": 0.1422,
+        "Reasoning": 0.346,
+        "Prior Sets (0.5 weight)": 0.5993,
         "Factuality": 0.2105,
         "Precise IF": 0.2938,
         "Math": 0.2623,
-        "Safety": 0.3757,
         "Focus": 0.0646,
-        "Ties": -0.01,
-        "Chat": 0.8184,
-        "Chat Hard": 0.2873,
-        "Reasoning": 0.346,
-        "Prior Sets (0.5 weight)": 0.5993
+        "Ties": -0.01
       }
     },
     {
@@ -938,17 +938,17 @@
       "name": "Ray2333/GRM-llama3-8B-distill",
       "developer": "Ray2333",
       "scores": {
-        "Score": 0.589,
-        "Chat": 0.9832,
-        "Chat Hard": 0.6842,
-        "Safety": 0.7222,
-        "Reasoning": 0.9133,
-        "Prior Sets (0.5 weight)": 0.7209,
+        "Score": 0.8464,
         "Factuality": 0.5874,
         "Precise IF": 0.3875,
         "Math": 0.5902,
+        "Safety": 0.8676,
         "Focus": 0.6727,
-        "Ties": 0.5743
+        "Ties": 0.5743,
+        "Chat": 0.9832,
+        "Chat Hard": 0.6842,
+        "Reasoning": 0.9133,
+        "Prior Sets (0.5 weight)": 0.7209
       }
     },
     {
@@ -956,17 +956,17 @@
       "name": "Ray2333/GRM-llama3-8B-sftreg",
       "developer": "Ray2333",
       "scores": {
-        "Score": 0.6089,
-        "Chat": 0.986,
-        "Chat Hard": 0.6776,
-        "Safety": 0.7867,
-        "Reasoning": 0.9229,
-        "Prior Sets (0.5 weight)": 0.7309,
+        "Score": 0.8542,
         "Factuality": 0.6189,
         "Precise IF": 0.3875,
         "Math": 0.5792,
+        "Safety": 0.8919,
         "Focus": 0.6828,
-        "Ties": 0.5981
+        "Ties": 0.5981,
+        "Chat": 0.986,
+        "Chat Hard": 0.6776,
+        "Reasoning": 0.9229,
+        "Prior Sets (0.5 weight)": 0.7309
       }
     },
     {
@@ -1098,16 +1098,16 @@
       "name": "ShikaiChen/LDL-Reward-Gemma-2-27B-v0.1",
       "developer": "ShikaiChen",
       "scores": {
-        "Score": 0.7249,
-        "Chat": 0.9637,
-        "Chat Hard": 0.9079,
-        "Safety": 0.9222,
-        "Reasoning": 0.9903,
+        "Score": 0.9499,
         "Factuality": 0.7558,
         "Precise IF": 0.35,
         "Math": 0.6448,
+        "Safety": 0.9378,
         "Focus": 0.9131,
-        "Ties": 0.7633
+        "Ties": 0.7633,
+        "Chat": 0.9637,
+        "Chat Hard": 0.9079,
+        "Reasoning": 0.9903
       }
     },
     {
@@ -1156,16 +1156,16 @@
       "name": "Skywork/Skywork-Reward-Gemma-2-27B-v0.2",
       "developer": "Skywork",
       "scores": {
-        "Score": 0.9426,
+        "Score": 0.7531,
+        "Chat": 0.9609,
+        "Chat Hard": 0.8991,
+        "Safety": 0.9689,
+        "Reasoning": 0.9807,
         "Factuality": 0.7674,
         "Precise IF": 0.375,
         "Math": 0.6721,
-        "Safety": 0.9297,
         "Focus": 0.9172,
-        "Ties": 0.8182,
-        "Chat": 0.9609,
-        "Chat Hard": 0.8991,
-        "Reasoning": 0.9807
+        "Ties": 0.8182
       }
     },
     {
@@ -1173,16 +1173,16 @@
       "name": "Skywork/Skywork-Reward-Llama-3.1-8B",
       "developer": "Skywork",
       "scores": {
-        "Score": 0.9252,
+        "Score": 0.7314,
+        "Chat": 0.9581,
+        "Chat Hard": 0.8728,
+        "Safety": 0.9333,
+        "Reasoning": 0.962,
         "Factuality": 0.6989,
         "Precise IF": 0.425,
         "Math": 0.6284,
-        "Safety": 0.9081,
         "Focus": 0.9616,
-        "Ties": 0.741,
-        "Chat": 0.9581,
-        "Chat Hard": 0.8728,
-        "Reasoning": 0.962
+        "Ties": 0.741
       }
     },
     {
@@ -1379,10 +1379,10 @@
       "name": "ai2/tulu-2-7b-rm-v0-nectar-binarized-3.8m-check...",
       "developer": "AI2",
       "scores": {
-        "Score": 0.6895,
+        "Score": 0.7008,
         "Chat": 0.9385,
-        "Chat Hard": 0.3706,
-        "Safety": 0.7595
+        "Chat Hard": 0.3882,
+        "Safety": 0.7757
       }
     },
     {
@@ -1423,17 +1423,17 @@
       "name": "allenai/Llama-3.1-70B-Instruct-RM-RB2",
       "developer": "allenai",
       "scores": {
-        "Score": 0.7606,
-        "Chat": 0.9665,
-        "Chat Hard": 0.8355,
-        "Safety": 0.8844,
-        "Reasoning": 0.8969,
-        "Prior Sets (0.5 weight)": 0.0,
+        "Score": 0.9021,
         "Factuality": 0.8126,
         "Precise IF": 0.4188,
         "Math": 0.6995,
+        "Safety": 0.9095,
         "Focus": 0.8646,
-        "Ties": 0.8835
+        "Ties": 0.8835,
+        "Chat": 0.9665,
+        "Chat Hard": 0.8355,
+        "Reasoning": 0.8969,
+        "Prior Sets (0.5 weight)": 0.0
       }
     },
     {
@@ -1495,17 +1495,17 @@
       "name": "allenai/Llama-3.1-Tulu-3-8B-DPO-RM-RB2",
       "developer": "allenai",
       "scores": {
-        "Score": 0.687,
-        "Chat": 0.9553,
-        "Chat Hard": 0.761,
-        "Safety": 0.86,
-        "Reasoning": 0.7898,
-        "Prior Sets (0.5 weight)": 0.0,
+        "Score": 0.8431,
         "Factuality": 0.7516,
         "Precise IF": 0.3875,
         "Math": 0.6284,
+        "Safety": 0.8662,
         "Focus": 0.8545,
-        "Ties": 0.6397
+        "Ties": 0.6397,
+        "Chat": 0.9553,
+        "Chat Hard": 0.761,
+        "Reasoning": 0.7898,
+        "Prior Sets (0.5 weight)": 0.0
       }
     },
     {
@@ -1545,17 +1545,17 @@
       "name": "allenai/Llama-3.1-Tulu-3-8B-SFT-RM-RB2",
       "developer": "allenai",
       "scores": {
-        "Score": 0.8551,
+        "Score": 0.6821,
+        "Chat": 0.9497,
+        "Chat Hard": 0.7917,
+        "Safety": 0.8978,
+        "Reasoning": 0.8005,
+        "Prior Sets (0.5 weight)": 0.0,
         "Factuality": 0.7326,
         "Precise IF": 0.3875,
         "Math": 0.5792,
-        "Safety": 0.8784,
         "Focus": 0.8889,
-        "Ties": 0.6063,
-        "Chat": 0.9497,
-        "Chat Hard": 0.7917,
-        "Reasoning": 0.8005,
-        "Prior Sets (0.5 weight)": 0.0
+        "Ties": 0.6063
       }
     },
     {
@@ -2085,6 +2085,20 @@
         "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",
@@ -3441,16 +3455,16 @@
       "name": "Claude 3.5 Sonnet 20240620",
       "developer": "Anthropic",
       "scores": {
-        "Score": 0.6466,
-        "Chat": 0.9637,
-        "Chat Hard": 0.7401,
-        "Safety": 0.8519,
-        "Reasoning": 0.8469,
+        "Score": 0.8417,
         "Factuality": 0.5284,
         "Precise IF": 0.3875,
         "Math": 0.5683,
+        "Safety": 0.8162,
         "Focus": 0.8697,
-        "Ties": 0.674
+        "Ties": 0.674,
+        "Chat": 0.9637,
+        "Chat Hard": 0.7401,
+        "Reasoning": 0.8469
       }
     },
     {
@@ -3472,17 +3486,17 @@
       "name": "Claude 3 Haiku 20240307",
       "developer": "Anthropic",
       "scores": {
-        "Score": 0.7289,
+        "Score": 0.3711,
+        "Chat": 0.9274,
+        "Chat Hard": 0.5197,
+        "Safety": 0.595,
+        "Reasoning": 0.706,
+        "Prior Sets (0.5 weight)": 0.6635,
         "Factuality": 0.4042,
         "Precise IF": 0.2812,
         "Math": 0.3552,
-        "Safety": 0.7953,
         "Focus": 0.501,
-        "Ties": 0.0899,
-        "Chat": 0.9274,
-        "Chat Hard": 0.5197,
-        "Reasoning": 0.706,
-        "Prior Sets (0.5 weight)": 0.6635
+        "Ties": 0.0899
       }
     },
     {
@@ -3490,16 +3504,16 @@
       "name": "Claude 3 Opus 20240229",
       "developer": "Anthropic",
       "scores": {
-        "Score": 0.8008,
+        "Score": 0.5744,
+        "Chat": 0.9469,
+        "Chat Hard": 0.6031,
+        "Safety": 0.8378,
+        "Reasoning": 0.7868,
         "Factuality": 0.5389,
         "Precise IF": 0.3312,
         "Math": 0.5137,
-        "Safety": 0.8662,
         "Focus": 0.6646,
-        "Ties": 0.5601,
-        "Chat": 0.9469,
-        "Chat Hard": 0.6031,
-        "Reasoning": 0.7868
+        "Ties": 0.5601
       }
     },
     {
@@ -3752,17 +3766,17 @@
       "name": "hendrydong/Mistral-RM-for-RAFT-GSHF-v0",
       "developer": "hendrydong",
       "scores": {
-        "Score": 0.5851,
-        "Chat": 0.9832,
-        "Chat Hard": 0.5789,
-        "Safety": 0.6956,
-        "Reasoning": 0.7434,
-        "Prior Sets (0.5 weight)": 0.7508,
+        "Score": 0.7847,
         "Factuality": 0.5779,
         "Precise IF": 0.3625,
         "Math": 0.6011,
+        "Safety": 0.85,
         "Focus": 0.6747,
-        "Ties": 0.5988
+        "Ties": 0.5988,
+        "Chat": 0.9832,
+        "Chat Hard": 0.5789,
+        "Reasoning": 0.7434,
+        "Prior Sets (0.5 weight)": 0.7508
       }
     },
     {
@@ -3787,16 +3801,16 @@
       "name": "internlm/internlm2-1_8b-reward",
       "developer": "internlm",
       "scores": {
-        "Score": 0.8217,
+        "Score": 0.3902,
+        "Chat": 0.9358,
+        "Chat Hard": 0.6623,
+        "Safety": 0.4711,
+        "Reasoning": 0.8724,
         "Factuality": 0.2758,
         "Precise IF": 0.3625,
         "Math": 0.4426,
-        "Safety": 0.8162,
         "Focus": 0.596,
-        "Ties": 0.1934,
-        "Chat": 0.9358,
-        "Chat Hard": 0.6623,
-        "Reasoning": 0.8724
+        "Ties": 0.1934
       }
     },
     {
@@ -3804,16 +3818,16 @@
       "name": "internlm/internlm2-20b-reward",
       "developer": "internlm",
       "scores": {
-        "Score": 0.5628,
-        "Chat": 0.9888,
-        "Chat Hard": 0.7654,
-        "Safety": 0.6111,
-        "Reasoning": 0.9576,
+        "Score": 0.9016,
         "Factuality": 0.5558,
         "Precise IF": 0.3625,
         "Math": 0.5738,
+        "Safety": 0.8946,
         "Focus": 0.7253,
-        "Ties": 0.5483
+        "Ties": 0.5483,
+        "Chat": 0.9888,
+        "Chat Hard": 0.7654,
+        "Reasoning": 0.9576
       }
     },
     {
@@ -3821,16 +3835,16 @@
       "name": "internlm/internlm2-7b-reward",
       "developer": "internlm",
       "scores": {
-        "Score": 0.8759,
+        "Score": 0.5335,
+        "Chat": 0.9916,
+        "Chat Hard": 0.6952,
+        "Safety": 0.5956,
+        "Reasoning": 0.9453,
         "Factuality": 0.4211,
         "Precise IF": 0.4,
         "Math": 0.5628,
-        "Safety": 0.8716,
         "Focus": 0.7051,
-        "Ties": 0.5164,
-        "Chat": 0.9916,
-        "Chat Hard": 0.6952,
-        "Reasoning": 0.9453
+        "Ties": 0.5164
       }
     },
     {
@@ -4041,16 +4055,16 @@
       "name": "nicolinho/QRM-Llama3.1-8B-v2",
       "developer": "nicolinho",
       "scores": {
-        "Score": 0.9314,
+        "Score": 0.7074,
+        "Chat": 0.9637,
+        "Chat Hard": 0.8684,
+        "Safety": 0.9467,
+        "Reasoning": 0.9677,
         "Factuality": 0.6653,
         "Precise IF": 0.4062,
         "Math": 0.612,
-        "Safety": 0.9257,
         "Focus": 0.8909,
-        "Ties": 0.7234,
-        "Chat": 0.9637,
-        "Chat Hard": 0.8684,
-        "Reasoning": 0.9677
+        "Ties": 0.7234
       }
     },
     {
@@ -4188,16 +4202,16 @@
       "name": "GPT-4o 2024-08-06",
       "developer": "OpenAI",
       "scores": {
-        "Score": 0.6493,
-        "Chat": 0.9609,
-        "Chat Hard": 0.761,
-        "Safety": 0.8619,
-        "Reasoning": 0.8661,
+        "Score": 0.8673,
         "Factuality": 0.5684,
         "Precise IF": 0.3312,
         "Math": 0.623,
+        "Safety": 0.8811,
         "Focus": 0.7293,
-        "Ties": 0.7819
+        "Ties": 0.7819,
+        "Chat": 0.9609,
+        "Chat Hard": 0.761,
+        "Reasoning": 0.8661
       }
     },
     {
@@ -4205,16 +4219,16 @@
       "name": "GPT-4o mini 2024-07-18",
       "developer": "OpenAI",
       "scores": {
-        "Score": 0.5796,
-        "Chat": 0.9497,
-        "Chat Hard": 0.6075,
-        "Safety": 0.7667,
-        "Reasoning": 0.8374,
+        "Score": 0.8007,
         "Factuality": 0.4105,
         "Precise IF": 0.3438,
         "Math": 0.5191,
+        "Safety": 0.8081,
         "Focus": 0.7414,
-        "Ties": 0.6962
+        "Ties": 0.6962,
+        "Chat": 0.9497,
+        "Chat Hard": 0.6075,
+        "Reasoning": 0.8374
       }
     },
     {
@@ -4235,17 +4249,17 @@
       "name": "openbmb/Eurus-RM-7b",
       "developer": "openbmb",
       "scores": {
-        "Score": 0.8159,
+        "Score": 0.5806,
+        "Chat": 0.9804,
+        "Chat Hard": 0.6557,
+        "Safety": 0.6267,
+        "Reasoning": 0.8633,
+        "Prior Sets (0.5 weight)": 0.7172,
         "Factuality": 0.6,
         "Precise IF": 0.3438,
         "Math": 0.5683,
-        "Safety": 0.8135,
         "Focus": 0.7475,
-        "Ties": 0.5972,
-        "Chat": 0.9804,
-        "Chat Hard": 0.6557,
-        "Reasoning": 0.8633,
-        "Prior Sets (0.5 weight)": 0.7172
+        "Ties": 0.5972
       }
     },
     {
@@ -4266,17 +4280,17 @@
       "name": "openbmb/UltraRM-13b",
       "developer": "openbmb",
       "scores": {
-        "Score": 0.6903,
+        "Score": 0.4683,
+        "Chat": 0.9637,
+        "Chat Hard": 0.5548,
+        "Safety": 0.5089,
+        "Reasoning": 0.6244,
+        "Prior Sets (0.5 weight)": 0.7294,
         "Factuality": 0.5063,
         "Precise IF": 0.3312,
         "Math": 0.5519,
-        "Safety": 0.5986,
         "Focus": 0.6081,
-        "Ties": 0.3036,
-        "Chat": 0.9637,
-        "Chat Hard": 0.5548,
-        "Reasoning": 0.6244,
-        "Prior Sets (0.5 weight)": 0.7294
+        "Ties": 0.3036
       }
     },
     {
@@ -4356,17 +4370,17 @@
       "name": "sfairXC/FsfairX-LLaMA3-RM-v0.1",
       "developer": "sfairXC",
       "scores": {
-        "Score": 0.6292,
-        "Chat": 0.9944,
-        "Chat Hard": 0.6513,
-        "Safety": 0.7667,
-        "Reasoning": 0.8644,
-        "Prior Sets (0.5 weight)": 0.7492,
+        "Score": 0.8338,
         "Factuality": 0.5916,
         "Precise IF": 0.4188,
         "Math": 0.6284,
+        "Safety": 0.8676,
         "Focus": 0.7051,
-        "Ties": 0.6647
+        "Ties": 0.6647,
+        "Chat": 0.9944,
+        "Chat Hard": 0.6513,
+        "Reasoning": 0.8644,
+        "Prior Sets (0.5 weight)": 0.7492
       }
     },
     {
diff --git a/data/benchmarks/swe-bench.json b/data/benchmarks/swe-bench.json
index 88b6df39554e558930cdff771fd1ab7d2dd73e3a..093176be195c26e24230b48d3e9b488139a6d6bf 100644
--- a/data/benchmarks/swe-bench.json
+++ b/data/benchmarks/swe-bench.json
@@ -5,7 +5,7 @@
       "name": "claude-opus-4-5",
       "developer": "Anthropic",
       "scores": {
-        "swe-bench": 0.6061
+        "swe-bench": 0.8072
       }
     },
     {
@@ -13,7 +13,7 @@
       "name": "gemini-3-pro-preview",
       "developer": "Google",
       "scores": {
-        "swe-bench": 0.71
+        "swe-bench": 0.7234
       }
     },
     {
@@ -21,7 +21,7 @@
       "name": "gpt-5.2-2025-12-11",
       "developer": "OpenAI",
       "scores": {
-        "swe-bench": 0.57
+        "swe-bench": 0.5455
       }
     }
   ]
diff --git a/data/benchmarks/tau-bench-2_airline.json b/data/benchmarks/tau-bench-2_airline.json
index 3829696a07bc037642c69851a891e0aeb0e5febf..203ba536a38c5fd6f5a3b4f5a7c625bb98c214a5 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": 0.72
+        "tau-bench-2/airline": 0.66
       }
     },
     {
@@ -13,7 +13,7 @@
       "name": "gemini-3-pro-preview",
       "developer": "Google",
       "scores": {
-        "tau-bench-2/airline": 0.68
+        "tau-bench-2/airline": 0.7
       }
     },
     {
@@ -21,7 +21,7 @@
       "name": "gpt-5.2-2025-12-11",
       "developer": "OpenAI",
       "scores": {
-        "tau-bench-2/airline": 0.6
+        "tau-bench-2/airline": 0.48
       }
     }
   ]
diff --git a/data/benchmarks/tau-bench-2_retail.json b/data/benchmarks/tau-bench-2_retail.json
index 220f36fbae7a50d2d3974e0cd62ceacad728d0fd..bb3c509d520d0e5ab84b4c3e44db8c84041b45fa 100644
--- a/data/benchmarks/tau-bench-2_retail.json
+++ b/data/benchmarks/tau-bench-2_retail.json
@@ -21,7 +21,7 @@
       "name": "gpt-5.2-2025-12-11",
       "developer": "OpenAI",
       "scores": {
-        "tau-bench-2/retail": 0.68
+        "tau-bench-2/retail": 0.51
       }
     }
   ]
diff --git a/data/benchmarks/tau-bench-2_telecom.json b/data/benchmarks/tau-bench-2_telecom.json
index 5e2e97c5a63c814404bfd0e936bb7f41ce63593e..0371242e1ef28be51ed37461c45171b5f6b938db 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": 0.76
+        "tau-bench-2/telecom": 0.84
       }
     },
     {
@@ -13,7 +13,7 @@
       "name": "gemini-3-pro-preview",
       "developer": "Google",
       "scores": {
-        "tau-bench-2/telecom": 0.73
+        "tau-bench-2/telecom": 0.6852
       }
     },
     {
diff --git a/data/benchmarks/terminal-bench-2.0.json b/data/benchmarks/terminal-bench-2.0.json
index eedfc30dd08733e57be031879da03991ca05bc76..a8e801f280cc4af65aa221436665986581643fe9 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": 25.4
+        "terminal-bench-2.0": 23.9
       }
     },
     {
@@ -13,7 +13,7 @@
       "name": "Claude Haiku 4.5",
       "developer": "Anthropic",
       "scores": {
-        "terminal-bench-2.0": 27.5
+        "terminal-bench-2.0": 35.5
       }
     },
     {
@@ -21,7 +21,7 @@
       "name": "Claude Opus 4.1",
       "developer": "Anthropic",
       "scores": {
-        "terminal-bench-2.0": 34.8
+        "terminal-bench-2.0": 38.0
       }
     },
     {
@@ -29,7 +29,7 @@
       "name": "Claude Opus 4.5",
       "developer": "Anthropic",
       "scores": {
-        "terminal-bench-2.0": 52.1
+        "terminal-bench-2.0": 59.1
       }
     },
     {
@@ -37,7 +37,7 @@
       "name": "Claude Opus 4.6",
       "developer": "Anthropic",
       "scores": {
-        "terminal-bench-2.0": 74.7
+        "terminal-bench-2.0": 66.9
       }
     },
     {
@@ -45,7 +45,7 @@
       "name": "Claude Sonnet 4.5",
       "developer": "Anthropic",
       "scores": {
-        "terminal-bench-2.0": 42.5
+        "terminal-bench-2.0": 40.1
       }
     },
     {
@@ -61,7 +61,7 @@
       "name": "Gemini 2.5 Flash",
       "developer": "Google",
       "scores": {
-        "terminal-bench-2.0": 16.9
+        "terminal-bench-2.0": 17.1
       }
     },
     {
@@ -69,7 +69,7 @@
       "name": "Gemini 2.5 Pro",
       "developer": "Google",
       "scores": {
-        "terminal-bench-2.0": 16.4
+        "terminal-bench-2.0": 19.6
       }
     },
     {
@@ -85,7 +85,7 @@
       "name": "Gemini 3 Pro",
       "developer": "Google",
       "scores": {
-        "terminal-bench-2.0": 56.9
+        "terminal-bench-2.0": 62.2
       }
     },
     {
@@ -149,7 +149,7 @@
       "name": "Multiple",
       "developer": "Multiple",
       "scores": {
-        "terminal-bench-2.0": 71.0
+        "terminal-bench-2.0": 58.4
       }
     },
     {
@@ -165,7 +165,7 @@
       "name": "GPT-5-Codex",
       "developer": "OpenAI",
       "scores": {
-        "terminal-bench-2.0": 43.4
+        "terminal-bench-2.0": 41.3
       }
     },
     {
@@ -173,7 +173,7 @@
       "name": "GPT-5-Mini",
       "developer": "OpenAI",
       "scores": {
-        "terminal-bench-2.0": 31.9
+        "terminal-bench-2.0": 22.2
       }
     },
     {
@@ -181,7 +181,7 @@
       "name": "GPT-5-Nano",
       "developer": "OpenAI",
       "scores": {
-        "terminal-bench-2.0": 7.0
+        "terminal-bench-2.0": 7.9
       }
     },
     {
@@ -197,7 +197,7 @@
       "name": "GPT-5.1-Codex",
       "developer": "OpenAI",
       "scores": {
-        "terminal-bench-2.0": 53.5
+        "terminal-bench-2.0": 36.9
       }
     },
     {
@@ -221,7 +221,7 @@
       "name": "GPT-5.2",
       "developer": "OpenAI",
       "scores": {
-        "terminal-bench-2.0": 60.7
+        "terminal-bench-2.0": 54.0
       }
     },
     {
@@ -237,7 +237,7 @@
       "name": "GPT-5.3-Codex",
       "developer": "OpenAI",
       "scores": {
-        "terminal-bench-2.0": 74.6
+        "terminal-bench-2.0": 77.3
       }
     },
     {
@@ -261,7 +261,7 @@
       "name": "Grok 4",
       "developer": "xAI",
       "scores": {
-        "terminal-bench-2.0": 23.1
+        "terminal-bench-2.0": 25.4
       }
     },
     {
@@ -285,7 +285,7 @@
       "name": "GLM 4.7",
       "developer": "Z-AI",
       "scores": {
-        "terminal-bench-2.0": 33.4
+        "terminal-bench-2.0": 33.3
       }
     },
     {
diff --git a/data/developers.json b/data/developers.json
index 013b8e244887bf6c63a6c680ce52cd50fedc7ed7..003e462b3fb10e7ebce2d70b3ed9418882ec3a93 100644
--- a/data/developers.json
+++ b/data/developers.json
@@ -173,7 +173,7 @@
   },
   {
     "developer": "allenai",
-    "model_count": 161
+    "model_count": 162
   },
   {
     "developer": "allknowingroger",
@@ -1097,7 +1097,7 @@
   },
   {
     "developer": "icefog72",
-    "model_count": 61
+    "model_count": 62
   },
   {
     "developer": "IDEA-CCNL",
diff --git a/data/developers/adriszmar.json b/data/developers/adriszmar.json
index acb90d745752909d8f96f323acb9caa9b19061ae..1f1d39916960942963a9c3c265196aea3657be38 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": 0.1685,
-        "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
+        "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
       }
     }
   ]
diff --git a/data/developers/ai2.json b/data/developers/ai2.json
index 498b6154facf655073d48826dd02116d29e34e45..4934c11b7806e647da8c3821dcfccba2566bb947 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": 0.6895,
+        "reward-bench/Score": 0.7008,
         "reward-bench/Chat": 0.9385,
-        "reward-bench/Chat Hard": 0.3706,
-        "reward-bench/Safety": 0.7595
+        "reward-bench/Chat Hard": 0.3882,
+        "reward-bench/Safety": 0.7757
       }
     },
     {
diff --git a/data/developers/alibaba.json b/data/developers/alibaba.json
index 8efe41024b181a324827f30ff358f0234de7b987..759f3a2b29b65da87e85bd7df67845381cdc3145 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": 25.4
+        "terminal-bench-2.0/terminal-bench-2.0": 23.9
       }
     },
     {
diff --git a/data/developers/allenai.json b/data/developers/allenai.json
index 1c85dbe2cfcc674683235ce774bcd2bc78253288..26883d607b7a5071bd9da08389772de32edfe871 100644
--- a/data/developers/allenai.json
+++ b/data/developers/allenai.json
@@ -63,17 +63,17 @@
       "developer": "allenai",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "reward-bench/Score": 0.7606,
-        "reward-bench/Chat": 0.9665,
-        "reward-bench/Chat Hard": 0.8355,
-        "reward-bench/Safety": 0.8844,
-        "reward-bench/Reasoning": 0.8969,
-        "reward-bench/Prior Sets (0.5 weight)": 0.0,
+        "reward-bench/Score": 0.9021,
         "reward-bench/Factuality": 0.8126,
         "reward-bench/Precise IF": 0.4188,
         "reward-bench/Math": 0.6995,
+        "reward-bench/Safety": 0.9095,
         "reward-bench/Focus": 0.8646,
-        "reward-bench/Ties": 0.8835
+        "reward-bench/Ties": 0.8835,
+        "reward-bench/Chat": 0.9665,
+        "reward-bench/Chat Hard": 0.8355,
+        "reward-bench/Reasoning": 0.8969,
+        "reward-bench/Prior Sets (0.5 weight)": 0.0
       }
     },
     {
@@ -181,12 +181,12 @@
       "developer": "allenai",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "hfopenllm_v2/IFEval": 0.8255,
-        "hfopenllm_v2/BBH": 0.4061,
-        "hfopenllm_v2/MATH Level 5": 0.2115,
-        "hfopenllm_v2/GPQA": 0.297,
+        "hfopenllm_v2/IFEval": 0.8267,
+        "hfopenllm_v2/BBH": 0.405,
+        "hfopenllm_v2/MATH Level 5": 0.1964,
+        "hfopenllm_v2/GPQA": 0.2987,
         "hfopenllm_v2/MUSR": 0.4175,
-        "hfopenllm_v2/MMLU-PRO": 0.2821
+        "hfopenllm_v2/MMLU-PRO": 0.2827
       }
     },
     {
@@ -209,17 +209,17 @@
       "developer": "allenai",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "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/Score": 0.8431,
         "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/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
       }
     },
     {
@@ -282,17 +282,17 @@
       "developer": "allenai",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "reward-bench/Score": 0.8551,
+        "reward-bench/Score": 0.6821,
+        "reward-bench/Chat": 0.9497,
+        "reward-bench/Chat Hard": 0.7917,
+        "reward-bench/Safety": 0.8978,
+        "reward-bench/Reasoning": 0.8005,
+        "reward-bench/Prior Sets (0.5 weight)": 0.0,
         "reward-bench/Factuality": 0.7326,
         "reward-bench/Precise IF": 0.3875,
         "reward-bench/Math": 0.5792,
-        "reward-bench/Safety": 0.8784,
         "reward-bench/Focus": 0.8889,
-        "reward-bench/Ties": 0.6063,
-        "reward-bench/Chat": 0.9497,
-        "reward-bench/Chat Hard": 0.7917,
-        "reward-bench/Reasoning": 0.8005,
-        "reward-bench/Prior Sets (0.5 weight)": 0.0
+        "reward-bench/Ties": 0.6063
       }
     },
     {
@@ -1054,6 +1054,21 @@
         "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/amd.json b/data/developers/amd.json
index ec85a4364a761e30f1999f359d0d247d8857e139..f58c5a6931b8f7bef3756ba18944919a5d99e792 100644
--- a/data/developers/amd.json
+++ b/data/developers/amd.json
@@ -7,11 +7,11 @@
       "developer": "amd",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "hfopenllm_v2/IFEval": 0.1842,
-        "hfopenllm_v2/BBH": 0.2974,
-        "hfopenllm_v2/MATH Level 5": 0.0053,
-        "hfopenllm_v2/GPQA": 0.2525,
-        "hfopenllm_v2/MUSR": 0.378,
+        "hfopenllm_v2/IFEval": 0.1918,
+        "hfopenllm_v2/BBH": 0.2969,
+        "hfopenllm_v2/MATH Level 5": 0.0076,
+        "hfopenllm_v2/GPQA": 0.2584,
+        "hfopenllm_v2/MUSR": 0.3846,
         "hfopenllm_v2/MMLU-PRO": 0.1169
       }
     }
diff --git a/data/developers/anthropic.json b/data/developers/anthropic.json
index 819a852f845410b5f7876451b1dcb93ba59f6701..c1b51c55828f681c4d430c9fc7c3821e0c017451 100644
--- a/data/developers/anthropic.json
+++ b/data/developers/anthropic.json
@@ -204,16 +204,16 @@
         "helm_mmlu/Virology": 0.602,
         "helm_mmlu/World Religions": 0.924,
         "helm_mmlu/Mean win rate": 0.17,
-        "reward-bench/Score": 0.6466,
-        "reward-bench/Chat": 0.9637,
-        "reward-bench/Chat Hard": 0.7401,
-        "reward-bench/Safety": 0.8519,
-        "reward-bench/Reasoning": 0.8469,
+        "reward-bench/Score": 0.8417,
         "reward-bench/Factuality": 0.5284,
         "reward-bench/Precise IF": 0.3875,
         "reward-bench/Math": 0.5683,
+        "reward-bench/Safety": 0.8162,
         "reward-bench/Focus": 0.8697,
-        "reward-bench/Ties": 0.674
+        "reward-bench/Ties": 0.674,
+        "reward-bench/Chat": 0.9637,
+        "reward-bench/Chat Hard": 0.7401,
+        "reward-bench/Reasoning": 0.8469
       }
     },
     {
@@ -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": 0.7289,
+        "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/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/Chat": 0.9274,
-        "reward-bench/Chat Hard": 0.5197,
-        "reward-bench/Reasoning": 0.706,
-        "reward-bench/Prior Sets (0.5 weight)": 0.6635
+        "reward-bench/Ties": 0.0899
       }
     },
     {
@@ -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": 0.8008,
+        "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/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/Chat": 0.9469,
-        "reward-bench/Chat Hard": 0.6031,
-        "reward-bench/Reasoning": 0.7868
+        "reward-bench/Ties": 0.5601
       }
     },
     {
@@ -525,7 +525,7 @@
       "developer": "Anthropic",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "terminal-bench-2.0/terminal-bench-2.0": 27.5
+        "terminal-bench-2.0/terminal-bench-2.0": 35.5
       }
     },
     {
@@ -650,12 +650,12 @@
       "developer": "Anthropic",
       "evaluator_relationship": null,
       "benchmark_scores": {
+        "browsecompplus/browsecompplus": 0.49,
         "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": 0.72,
+        "swe-bench/swe-bench": 0.8072,
+        "tau-bench-2_airline/tau-bench-2/airline": 0.66,
         "tau-bench-2_retail/tau-bench-2/retail": 0.85,
-        "tau-bench-2_telecom/tau-bench-2/telecom": 0.76
+        "tau-bench-2_telecom/tau-bench-2/telecom": 0.84
       }
     },
     {
@@ -664,7 +664,7 @@
       "developer": "Anthropic",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "terminal-bench-2.0/terminal-bench-2.0": 34.8
+        "terminal-bench-2.0/terminal-bench-2.0": 38.0
       }
     },
     {
@@ -673,7 +673,7 @@
       "developer": "Anthropic",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "terminal-bench-2.0/terminal-bench-2.0": 52.1
+        "terminal-bench-2.0/terminal-bench-2.0": 59.1
       }
     },
     {
@@ -682,7 +682,7 @@
       "developer": "Anthropic",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "terminal-bench-2.0/terminal-bench-2.0": 74.7
+        "terminal-bench-2.0/terminal-bench-2.0": 66.9
       }
     },
     {
@@ -756,7 +756,7 @@
       "developer": "Anthropic",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "terminal-bench-2.0/terminal-bench-2.0": 42.5
+        "terminal-bench-2.0/terminal-bench-2.0": 40.1
       }
     },
     {
diff --git a/data/developers/atanddev.json b/data/developers/atanddev.json
index 42530fda0188ea30162bbff58f1010442b0394c9..d269c1fbba37e9ea4df30635a880656764997806 100644
--- a/data/developers/atanddev.json
+++ b/data/developers/atanddev.json
@@ -7,12 +7,12 @@
       "developer": "AtAndDev",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "hfopenllm_v2/IFEval": 0.4605,
-        "hfopenllm_v2/BBH": 0.4258,
-        "hfopenllm_v2/MATH Level 5": 0.0748,
-        "hfopenllm_v2/GPQA": 0.2659,
-        "hfopenllm_v2/MUSR": 0.3636,
-        "hfopenllm_v2/MMLU-PRO": 0.2812
+        "hfopenllm_v2/IFEval": 0.4511,
+        "hfopenllm_v2/BBH": 0.4275,
+        "hfopenllm_v2/MATH Level 5": 0.1473,
+        "hfopenllm_v2/GPQA": 0.2701,
+        "hfopenllm_v2/MUSR": 0.3623,
+        "hfopenllm_v2/MMLU-PRO": 0.2806
       }
     }
   ]
diff --git a/data/developers/boltmonkey.json b/data/developers/boltmonkey.json
index 93a1093c0cbb01b9a84ae22cf6063fc50d8793cb..d93c347b80733b690b666d77f058a8e36708eee2 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": 0.7999,
-        "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
+        "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
       }
     },
     {
diff --git a/data/developers/bunnycore.json b/data/developers/bunnycore.json
index 069b8a9f0214975725e28f414b82b07e73072c0f..153064e2dea6c3626cb6deb17e2d3191b25ec406 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": 0.4652,
-        "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
+        "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
       }
     },
     {
diff --git a/data/developers/cir-ams.json b/data/developers/cir-ams.json
index 09d0cc390a2584b96dbfe9a5acec25171fe175fa..df9dcecb6f8fae5d901c2496b58813341797427e 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": 0.5736,
-        "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/Score": 0.8172,
         "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/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
       }
     }
   ]
diff --git a/data/developers/cpayne1303.json b/data/developers/cpayne1303.json
index 878ab50b2c306395a2d661382c84d0660b0f0d51..6d735bd94a67b9fc86d407e5a74d4ec119a21a01 100644
--- a/data/developers/cpayne1303.json
+++ b/data/developers/cpayne1303.json
@@ -35,12 +35,12 @@
       "developer": "cpayne1303",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "hfopenllm_v2/IFEval": 0.1949,
-        "hfopenllm_v2/BBH": 0.2965,
-        "hfopenllm_v2/MATH Level 5": 0.0045,
+        "hfopenllm_v2/IFEval": 0.1916,
+        "hfopenllm_v2/BBH": 0.2977,
+        "hfopenllm_v2/MATH Level 5": 0.0,
         "hfopenllm_v2/GPQA": 0.2685,
-        "hfopenllm_v2/MUSR": 0.3885,
-        "hfopenllm_v2/MMLU-PRO": 0.1111
+        "hfopenllm_v2/MUSR": 0.3872,
+        "hfopenllm_v2/MMLU-PRO": 0.1132
       }
     },
     {
diff --git a/data/developers/daemontatox.json b/data/developers/daemontatox.json
index 09a88a4f4f23ea30a1c40f4893201987d0954b30..3de1c87bc255ec29e11a7fcd9434ebc4d17ff27a 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": 0.3745,
-        "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
+        "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
       }
     },
     {
diff --git a/data/developers/davielion.json b/data/developers/davielion.json
index d2a3ca1471ea06bca721c18d505591908b22252e..5027340a9fce3c0b5162453c9d10516ec45234d2 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": 0.1549,
-        "hfopenllm_v2/BBH": 0.2937,
-        "hfopenllm_v2/MATH Level 5": 0.006,
-        "hfopenllm_v2/GPQA": 0.2576,
+        "hfopenllm_v2/IFEval": 0.1507,
+        "hfopenllm_v2/BBH": 0.293,
+        "hfopenllm_v2/MATH Level 5": 0.0,
+        "hfopenllm_v2/GPQA": 0.2534,
         "hfopenllm_v2/MUSR": 0.3565,
-        "hfopenllm_v2/MMLU-PRO": 0.1128
+        "hfopenllm_v2/MMLU-PRO": 0.1125
       }
     },
     {
diff --git a/data/developers/dfurman.json b/data/developers/dfurman.json
index 2947dc3ef503295f24886c787e729305dcebb026..7e28f4da929deb69b4028e08d70bcf7cf516d943 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": 0.2835,
-        "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
+        "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
       }
     },
     {
diff --git a/data/developers/doppelreflex.json b/data/developers/doppelreflex.json
index 0b78fc1cbec001d1df6b60b1fab265b2eab6799e..4e478be7761570eec41b8a497db82c0ab081c8b0 100644
--- a/data/developers/doppelreflex.json
+++ b/data/developers/doppelreflex.json
@@ -175,12 +175,12 @@
       "developer": "DoppelReflEx",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "hfopenllm_v2/IFEval": 0.436,
-        "hfopenllm_v2/BBH": 0.4956,
-        "hfopenllm_v2/MATH Level 5": 0.0589,
-        "hfopenllm_v2/GPQA": 0.3205,
-        "hfopenllm_v2/MUSR": 0.3843,
-        "hfopenllm_v2/MMLU-PRO": 0.3237
+        "hfopenllm_v2/IFEval": 0.451,
+        "hfopenllm_v2/BBH": 0.4944,
+        "hfopenllm_v2/MATH Level 5": 0.1156,
+        "hfopenllm_v2/GPQA": 0.3196,
+        "hfopenllm_v2/MUSR": 0.3896,
+        "hfopenllm_v2/MMLU-PRO": 0.3256
       }
     },
     {
diff --git a/data/developers/google.json b/data/developers/google.json
index d2c89d05cf05ad4bda3e0747fb0e85f41c1968c7..ae9dc7717f1b79909d67dfe1364f96967d93b736 100644
--- a/data/developers/google.json
+++ b/data/developers/google.json
@@ -76,12 +76,12 @@
       "developer": "Google",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "hfopenllm_v2/IFEval": 0.2207,
-        "hfopenllm_v2/BBH": 0.4537,
-        "hfopenllm_v2/MATH Level 5": 0.0008,
-        "hfopenllm_v2/GPQA": 0.2458,
-        "hfopenllm_v2/MUSR": 0.422,
-        "hfopenllm_v2/MMLU-PRO": 0.2142
+        "hfopenllm_v2/IFEval": 0.2237,
+        "hfopenllm_v2/BBH": 0.4531,
+        "hfopenllm_v2/MATH Level 5": 0.0076,
+        "hfopenllm_v2/GPQA": 0.2525,
+        "hfopenllm_v2/MUSR": 0.4181,
+        "hfopenllm_v2/MMLU-PRO": 0.2147
       }
     },
     {
@@ -139,7 +139,6 @@
       "developer": "Google",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "ace/Gaming Score": 0.415,
         "apex-agents/Overall Pass@1": 0.24,
         "apex-agents/Overall Pass@8": 0.367,
         "apex-agents/Overall Mean Score": 0.395,
@@ -147,6 +146,7 @@
         "apex-agents/Management Consulting Pass@1": 0.193,
         "apex-agents/Corporate Law Pass@1": 0.259,
         "apex-agents/Corporate Lawyer Mean Score": 0.524,
+        "ace/Gaming Score": 0.415,
         "apex-v1/Overall Score": 0.64,
         "apex-v1/Consulting Score": 0.64
       }
@@ -723,7 +723,7 @@
         "reward-bench/Safety": 0.909,
         "reward-bench/Focus": 0.841,
         "reward-bench/Ties": 0.809,
-        "terminal-bench-2.0/terminal-bench-2.0": 16.9
+        "terminal-bench-2.0/terminal-bench-2.0": 17.1
       }
     },
     {
@@ -823,7 +823,7 @@
         "reward-bench/Safety": 0.881,
         "reward-bench/Focus": 0.805,
         "reward-bench/Ties": 0.811,
-        "terminal-bench-2.0/terminal-bench-2.0": 16.4
+        "terminal-bench-2.0/terminal-bench-2.0": 19.6
       }
     },
     {
@@ -870,7 +870,7 @@
       "developer": "Google",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "terminal-bench-2.0/terminal-bench-2.0": 56.9
+        "terminal-bench-2.0/terminal-bench-2.0": 62.2
       }
     },
     {
@@ -879,7 +879,7 @@
       "developer": "Google",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "appworld_test_normal/appworld/test_normal": 0.36,
+        "appworld_test_normal/appworld/test_normal": 0.13,
         "browsecompplus/browsecompplus": 0.48,
         "global-mmlu-lite/Global MMLU Lite": 0.9453,
         "global-mmlu-lite/Culturally Sensitive": 0.9397,
@@ -900,10 +900,10 @@
         "global-mmlu-lite/Yoruba": 0.9425,
         "global-mmlu-lite/Chinese": 0.9475,
         "global-mmlu-lite/Burmese": 0.9425,
-        "swe-bench/swe-bench": 0.71,
-        "tau-bench-2_airline/tau-bench-2/airline": 0.68,
+        "swe-bench/swe-bench": 0.7234,
+        "tau-bench-2_airline/tau-bench-2/airline": 0.7,
         "tau-bench-2_retail/tau-bench-2/retail": 0.7805,
-        "tau-bench-2_telecom/tau-bench-2/telecom": 0.73
+        "tau-bench-2_telecom/tau-bench-2/telecom": 0.6852
       }
     },
     {
@@ -1056,12 +1056,12 @@
       "developer": "Google",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "hfopenllm_v2/IFEval": 0.5288,
-        "hfopenllm_v2/BBH": 0.4178,
-        "hfopenllm_v2/MATH Level 5": 0.0476,
-        "hfopenllm_v2/GPQA": 0.2752,
-        "hfopenllm_v2/MUSR": 0.3728,
-        "hfopenllm_v2/MMLU-PRO": 0.2467
+        "hfopenllm_v2/IFEval": 0.5078,
+        "hfopenllm_v2/BBH": 0.4226,
+        "hfopenllm_v2/MATH Level 5": 0.0347,
+        "hfopenllm_v2/GPQA": 0.2852,
+        "hfopenllm_v2/MUSR": 0.3964,
+        "hfopenllm_v2/MMLU-PRO": 0.2578
       }
     },
     {
diff --git a/data/developers/gunulhona.json b/data/developers/gunulhona.json
index 3d63c85d80df83c6632e31f815d8dc78510d19a0..1eba4dc6aed35ea93d90c3c8c2e1a2676805ffa0 100644
--- a/data/developers/gunulhona.json
+++ b/data/developers/gunulhona.json
@@ -21,12 +21,12 @@
       "developer": "Gunulhona",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "hfopenllm_v2/IFEval": 0.288,
-        "hfopenllm_v2/BBH": 0.5154,
+        "hfopenllm_v2/IFEval": 0.4441,
+        "hfopenllm_v2/BBH": 0.4863,
         "hfopenllm_v2/MATH Level 5": 0.0,
-        "hfopenllm_v2/GPQA": 0.3247,
-        "hfopenllm_v2/MUSR": 0.408,
-        "hfopenllm_v2/MMLU-PRO": 0.3817
+        "hfopenllm_v2/GPQA": 0.307,
+        "hfopenllm_v2/MUSR": 0.3986,
+        "hfopenllm_v2/MMLU-PRO": 0.3098
       }
     }
   ]
diff --git a/data/developers/hendrydong.json b/data/developers/hendrydong.json
index 66d1cb6cae0c438dba7144b9a92c7891857c219e..56e05071d3b06a1289763aa84d052b49b755b3aa 100644
--- a/data/developers/hendrydong.json
+++ b/data/developers/hendrydong.json
@@ -7,17 +7,17 @@
       "developer": "hendrydong",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "reward-bench/Score": 0.5851,
-        "reward-bench/Chat": 0.9832,
-        "reward-bench/Chat Hard": 0.5789,
-        "reward-bench/Safety": 0.6956,
-        "reward-bench/Reasoning": 0.7434,
-        "reward-bench/Prior Sets (0.5 weight)": 0.7508,
+        "reward-bench/Score": 0.7847,
         "reward-bench/Factuality": 0.5779,
         "reward-bench/Precise IF": 0.3625,
         "reward-bench/Math": 0.6011,
+        "reward-bench/Safety": 0.85,
         "reward-bench/Focus": 0.6747,
-        "reward-bench/Ties": 0.5988
+        "reward-bench/Ties": 0.5988,
+        "reward-bench/Chat": 0.9832,
+        "reward-bench/Chat Hard": 0.5789,
+        "reward-bench/Reasoning": 0.7434,
+        "reward-bench/Prior Sets (0.5 weight)": 0.7508
       }
     }
   ]
diff --git a/data/developers/huggingfacetb.json b/data/developers/huggingfacetb.json
index 912c5d4a2004a890736a0d6051d6fabe190615d4..60e6e856fd10ebf29a5d127dd18301cd9edf10dd 100644
--- a/data/developers/huggingfacetb.json
+++ b/data/developers/huggingfacetb.json
@@ -133,12 +133,12 @@
       "developer": "HuggingFaceTB",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "hfopenllm_v2/IFEval": 0.2883,
-        "hfopenllm_v2/BBH": 0.3124,
-        "hfopenllm_v2/MATH Level 5": 0.003,
-        "hfopenllm_v2/GPQA": 0.2357,
-        "hfopenllm_v2/MUSR": 0.3662,
-        "hfopenllm_v2/MMLU-PRO": 0.1115
+        "hfopenllm_v2/IFEval": 0.0593,
+        "hfopenllm_v2/BBH": 0.3135,
+        "hfopenllm_v2/MATH Level 5": 0.0144,
+        "hfopenllm_v2/GPQA": 0.2341,
+        "hfopenllm_v2/MUSR": 0.3871,
+        "hfopenllm_v2/MMLU-PRO": 0.1092
       }
     },
     {
diff --git a/data/developers/icefog72.json b/data/developers/icefog72.json
index 7e3fc1f7a7c9a270611dd8a76e50d06bd5496253..0ea5ae912613ba6349dc7eed95da5f8d3afd5dbe 100644
--- a/data/developers/icefog72.json
+++ b/data/developers/icefog72.json
@@ -813,6 +813,20 @@
         "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/internlm.json b/data/developers/internlm.json
index 3995d91bd1934deb8a0118739d074676cf30299b..ba5efe87a4d9e153aadeeeaadd0b465b5955bdd6 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": 0.8217,
+        "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/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/Chat": 0.9358,
-        "reward-bench/Chat Hard": 0.6623,
-        "reward-bench/Reasoning": 0.8724
+        "reward-bench/Ties": 0.1934
       }
     },
     {
@@ -39,16 +39,16 @@
       "developer": "internlm",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "reward-bench/Score": 0.5628,
-        "reward-bench/Chat": 0.9888,
-        "reward-bench/Chat Hard": 0.7654,
-        "reward-bench/Safety": 0.6111,
-        "reward-bench/Reasoning": 0.9576,
+        "reward-bench/Score": 0.9016,
         "reward-bench/Factuality": 0.5558,
         "reward-bench/Precise IF": 0.3625,
         "reward-bench/Math": 0.5738,
+        "reward-bench/Safety": 0.8946,
         "reward-bench/Focus": 0.7253,
-        "reward-bench/Ties": 0.5483
+        "reward-bench/Ties": 0.5483,
+        "reward-bench/Chat": 0.9888,
+        "reward-bench/Chat Hard": 0.7654,
+        "reward-bench/Reasoning": 0.9576
       }
     },
     {
@@ -71,16 +71,16 @@
       "developer": "internlm",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "reward-bench/Score": 0.8759,
+        "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/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/Chat": 0.9916,
-        "reward-bench/Chat Hard": 0.6952,
-        "reward-bench/Reasoning": 0.9453
+        "reward-bench/Ties": 0.5164
       }
     },
     {
diff --git a/data/developers/isaak-carter.json b/data/developers/isaak-carter.json
index 5e4243cedab9b62fa1fd1f8e9be8ea7f6c708259..690871bc9bb32834a871ee3cfe82d0488b7c6bad 100644
--- a/data/developers/isaak-carter.json
+++ b/data/developers/isaak-carter.json
@@ -35,12 +35,12 @@
       "developer": "Isaak-Carter",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "hfopenllm_v2/IFEval": 0.2553,
-        "hfopenllm_v2/BBH": 0.4725,
-        "hfopenllm_v2/MATH Level 5": 0.0529,
-        "hfopenllm_v2/GPQA": 0.2919,
-        "hfopenllm_v2/MUSR": 0.3654,
-        "hfopenllm_v2/MMLU-PRO": 0.3316
+        "hfopenllm_v2/IFEval": 0.2477,
+        "hfopenllm_v2/BBH": 0.4758,
+        "hfopenllm_v2/MATH Level 5": 0.0453,
+        "hfopenllm_v2/GPQA": 0.2911,
+        "hfopenllm_v2/MUSR": 0.3641,
+        "hfopenllm_v2/MMLU-PRO": 0.3292
       }
     }
   ]
diff --git a/data/developers/leroydyer.json b/data/developers/leroydyer.json
index 7fdecb6a1e65adfe5948ae6f60f4bc236a803ac7..e1aa95462e1fed8d4e011735c7846112031a21a1 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": 0.3066,
-        "hfopenllm_v2/BBH": 0.4577,
+        "hfopenllm_v2/IFEval": 0.3036,
+        "hfopenllm_v2/BBH": 0.4575,
         "hfopenllm_v2/MATH Level 5": 0.0446,
-        "hfopenllm_v2/GPQA": 0.2995,
-        "hfopenllm_v2/MUSR": 0.4254,
-        "hfopenllm_v2/MMLU-PRO": 0.2318
+        "hfopenllm_v2/GPQA": 0.3012,
+        "hfopenllm_v2/MUSR": 0.4253,
+        "hfopenllm_v2/MMLU-PRO": 0.2329
       }
     },
     {
diff --git a/data/developers/llmat.json b/data/developers/llmat.json
index d073eb81547c22e04e5363702192b3a9654d7362..95633d3199310803501c256677a0fb788d0a08f7 100644
--- a/data/developers/llmat.json
+++ b/data/developers/llmat.json
@@ -7,12 +7,12 @@
       "developer": "llmat",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "hfopenllm_v2/IFEval": 0.377,
-        "hfopenllm_v2/BBH": 0.3978,
-        "hfopenllm_v2/MATH Level 5": 0.0242,
-        "hfopenllm_v2/GPQA": 0.2668,
-        "hfopenllm_v2/MUSR": 0.3555,
-        "hfopenllm_v2/MMLU-PRO": 0.2278
+        "hfopenllm_v2/IFEval": 0.364,
+        "hfopenllm_v2/BBH": 0.4005,
+        "hfopenllm_v2/MATH Level 5": 0.0015,
+        "hfopenllm_v2/GPQA": 0.2693,
+        "hfopenllm_v2/MUSR": 0.3529,
+        "hfopenllm_v2/MMLU-PRO": 0.2301
       }
     }
   ]
diff --git a/data/developers/microsoft.json b/data/developers/microsoft.json
index ac7ddab4c9378bc179c9df1d82dca24687067465..5b22c3abc624b7d65a825afffb8ded406b5eb203 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": 0.5613,
-        "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
+        "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
       }
     },
     {
@@ -341,12 +341,12 @@
       "developer": "microsoft",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "hfopenllm_v2/IFEval": 0.0488,
-        "hfopenllm_v2/BBH": 0.6703,
-        "hfopenllm_v2/MATH Level 5": 0.2787,
-        "hfopenllm_v2/GPQA": 0.401,
+        "hfopenllm_v2/IFEval": 0.0585,
+        "hfopenllm_v2/BBH": 0.6691,
+        "hfopenllm_v2/MATH Level 5": 0.3165,
+        "hfopenllm_v2/GPQA": 0.406,
         "hfopenllm_v2/MUSR": 0.5034,
-        "hfopenllm_v2/MMLU-PRO": 0.5295
+        "hfopenllm_v2/MMLU-PRO": 0.5287
       }
     },
     {
diff --git a/data/developers/mistralai.json b/data/developers/mistralai.json
index 14d2f60be9e807210d185f950d2f81080246d7d7..57d196d824fe3b2d3e0a8303970991b9f16872ee 100644
--- a/data/developers/mistralai.json
+++ b/data/developers/mistralai.json
@@ -718,12 +718,12 @@
       "developer": "mistralai",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "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
+        "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
       }
     },
     {
diff --git a/data/developers/mlabonne.json b/data/developers/mlabonne.json
index be86bd7fe732025f133b06dc7c412aa5e56b7119..2620a8c4e8931697abdcd44e4a4aae7c1e430da5 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": 0.4162,
-        "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
+        "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
       }
     },
     {
diff --git a/data/developers/multiple.json b/data/developers/multiple.json
index e235ffc0287578be5fd9fdf3ba4e4e1b232b5df8..3ca416f37a8a2d37629452327cce332c02e2b948 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": 71.0
+        "terminal-bench-2.0/terminal-bench-2.0": 58.4
       }
     }
   ]
diff --git a/data/developers/nazimali.json b/data/developers/nazimali.json
index 34d47c9647d462b17a0fe6015c5c4f9fc00264e7..07c42beb48b2fc9e0ad1a1059178a9ce4071a591 100644
--- a/data/developers/nazimali.json
+++ b/data/developers/nazimali.json
@@ -21,12 +21,12 @@
       "developer": "nazimali",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "hfopenllm_v2/IFEval": 0.486,
-        "hfopenllm_v2/BBH": 0.4721,
-        "hfopenllm_v2/MATH Level 5": 0.0846,
-        "hfopenllm_v2/GPQA": 0.2844,
-        "hfopenllm_v2/MUSR": 0.4006,
-        "hfopenllm_v2/MMLU-PRO": 0.3087
+        "hfopenllm_v2/IFEval": 0.4964,
+        "hfopenllm_v2/BBH": 0.4699,
+        "hfopenllm_v2/MATH Level 5": 0.0045,
+        "hfopenllm_v2/GPQA": 0.2827,
+        "hfopenllm_v2/MUSR": 0.3979,
+        "hfopenllm_v2/MMLU-PRO": 0.3063
       }
     }
   ]
diff --git a/data/developers/nexusflow.json b/data/developers/nexusflow.json
index 2f78cab8780e463261ce35ef251c295eb3f3fd0f..49fe739e7104f59b148ecb24e067de8a0cb500b5 100644
--- a/data/developers/nexusflow.json
+++ b/data/developers/nexusflow.json
@@ -21,17 +21,17 @@
       "developer": "Nexusflow",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "reward-bench/Score": 0.8133,
+        "reward-bench/Score": 0.4553,
+        "reward-bench/Chat": 0.9693,
+        "reward-bench/Chat Hard": 0.5724,
+        "reward-bench/Safety": 0.7556,
+        "reward-bench/Reasoning": 0.8845,
+        "reward-bench/Prior Sets (0.5 weight)": 0.7137,
         "reward-bench/Factuality": 0.4589,
         "reward-bench/Precise IF": 0.3187,
         "reward-bench/Math": 0.6175,
-        "reward-bench/Safety": 0.877,
         "reward-bench/Focus": 0.4808,
-        "reward-bench/Ties": 0.1004,
-        "reward-bench/Chat": 0.9693,
-        "reward-bench/Chat Hard": 0.5724,
-        "reward-bench/Reasoning": 0.8845,
-        "reward-bench/Prior Sets (0.5 weight)": 0.7137
+        "reward-bench/Ties": 0.1004
       }
     }
   ]
diff --git a/data/developers/nicolinho.json b/data/developers/nicolinho.json
index 551d4a5de698babd0e830b509f51bb11f4dd2ac7..bf9706fe4ed328188b0945860efeebf7183abc65 100644
--- a/data/developers/nicolinho.json
+++ b/data/developers/nicolinho.json
@@ -51,16 +51,16 @@
       "developer": "nicolinho",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "reward-bench/Score": 0.9314,
+        "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/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/Chat": 0.9637,
-        "reward-bench/Chat Hard": 0.8684,
-        "reward-bench/Reasoning": 0.9677
+        "reward-bench/Ties": 0.7234
       }
     }
   ]
diff --git a/data/developers/ontocord.json b/data/developers/ontocord.json
index c16f4cbacdda3485b721f459b079923a6793a670..add41dbe183800ebed90c916e0b704c974dd50e7 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": 0.1128,
-        "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
+        "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
       }
     },
     {
diff --git a/data/developers/openai.json b/data/developers/openai.json
index 1d144bd538c9cee7f94220b8970cc16ed56fa6ae..ede5404bc51db07d8e63c7bbcb6be1b005184ac0 100644
--- a/data/developers/openai.json
+++ b/data/developers/openai.json
@@ -163,16 +163,16 @@
       "developer": "OpenAI",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "ace/Overall Score": 0.515,
-        "ace/Food Score": 0.65,
-        "ace/Gaming Score": 0.578,
         "apex-agents/Overall Pass@1": 0.23,
         "apex-agents/Overall Pass@8": 0.4,
         "apex-agents/Overall Mean Score": 0.387,
         "apex-agents/Investment Banking Pass@1": 0.273,
         "apex-agents/Management Consulting Pass@1": 0.227,
         "apex-agents/Corporate Law Pass@1": 0.189,
-        "apex-agents/Corporate Lawyer Mean Score": 0.443
+        "apex-agents/Corporate Lawyer Mean Score": 0.443,
+        "ace/Overall Score": 0.515,
+        "ace/Food Score": 0.65,
+        "ace/Gaming Score": 0.578
       }
     },
     {
@@ -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": 0.6493,
-        "reward-bench/Chat": 0.9609,
-        "reward-bench/Chat Hard": 0.761,
-        "reward-bench/Safety": 0.8619,
-        "reward-bench/Reasoning": 0.8661,
+        "reward-bench/Score": 0.8673,
         "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/Ties": 0.7819,
+        "reward-bench/Chat": 0.9609,
+        "reward-bench/Chat Hard": 0.761,
+        "reward-bench/Reasoning": 0.8661
       }
     },
     {
@@ -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": 0.5796,
-        "reward-bench/Chat": 0.9497,
-        "reward-bench/Chat Hard": 0.6075,
-        "reward-bench/Safety": 0.7667,
-        "reward-bench/Reasoning": 0.8374,
+        "reward-bench/Score": 0.8007,
         "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/Ties": 0.6962,
+        "reward-bench/Chat": 0.9497,
+        "reward-bench/Chat Hard": 0.6075,
+        "reward-bench/Reasoning": 0.8374
       }
     },
     {
@@ -922,7 +922,7 @@
       "developer": "OpenAI",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "terminal-bench-2.0/terminal-bench-2.0": 43.4
+        "terminal-bench-2.0/terminal-bench-2.0": 41.3
       }
     },
     {
@@ -931,7 +931,7 @@
       "developer": "OpenAI",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "terminal-bench-2.0/terminal-bench-2.0": 31.9
+        "terminal-bench-2.0/terminal-bench-2.0": 22.2
       }
     },
     {
@@ -954,7 +954,7 @@
       "developer": "OpenAI",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "terminal-bench-2.0/terminal-bench-2.0": 7.0
+        "terminal-bench-2.0/terminal-bench-2.0": 7.9
       }
     },
     {
@@ -986,7 +986,7 @@
       "developer": "OpenAI",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "terminal-bench-2.0/terminal-bench-2.0": 53.5
+        "terminal-bench-2.0/terminal-bench-2.0": 36.9
       }
     },
     {
@@ -1013,7 +1013,7 @@
       "developer": "OpenAI",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "terminal-bench-2.0/terminal-bench-2.0": 60.7
+        "terminal-bench-2.0/terminal-bench-2.0": 54.0
       }
     },
     {
@@ -1023,13 +1023,13 @@
       "evaluator_relationship": null,
       "benchmark_scores": {
         "appworld_test_normal/appworld/test_normal": 0.0,
-        "browsecompplus/browsecompplus": 0.26,
+        "browsecompplus/browsecompplus": 0.48,
         "livecodebenchpro/Hard Problems": 0.1594,
         "livecodebenchpro/Medium Problems": 0.5211,
         "livecodebenchpro/Easy Problems": 0.9014,
-        "swe-bench/swe-bench": 0.57,
-        "tau-bench-2_airline/tau-bench-2/airline": 0.6,
-        "tau-bench-2_retail/tau-bench-2/retail": 0.68,
+        "swe-bench/swe-bench": 0.5455,
+        "tau-bench-2_airline/tau-bench-2/airline": 0.48,
+        "tau-bench-2_retail/tau-bench-2/retail": 0.51,
         "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": 74.6
+        "terminal-bench-2.0/terminal-bench-2.0": 77.3
       }
     },
     {
@@ -1233,9 +1233,9 @@
         "helm_capabilities/IFEval": 0.929,
         "helm_capabilities/WildBench": 0.854,
         "helm_capabilities/Omni-MATH": 0.72,
-        "livecodebenchpro/Hard Problems": 0.0143,
-        "livecodebenchpro/Medium Problems": 0.2923,
-        "livecodebenchpro/Easy Problems": 0.8571
+        "livecodebenchpro/Hard Problems": 0.014084507042253521,
+        "livecodebenchpro/Medium Problems": 0.30985915492957744,
+        "livecodebenchpro/Easy Problems": 0.8873239436619719
       }
     },
     {
diff --git a/data/developers/openassistant.json b/data/developers/openassistant.json
index 0d3e3f32693fa46354d7063e0615e0d45e8641c5..95e3fbf7702e838e1924ccdd51ef3a7ea27c9d5c 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": 0.615,
+        "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/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/Chat": 0.9246,
-        "reward-bench/Chat Hard": 0.3728,
-        "reward-bench/Reasoning": 0.5855,
-        "reward-bench/Prior Sets (0.5 weight)": 0.6801
+        "reward-bench/Ties": 0.047
       }
     },
     {
@@ -26,17 +26,17 @@
       "developer": "OpenAssistant",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "reward-bench/Score": 0.6901,
+        "reward-bench/Score": 0.2648,
+        "reward-bench/Chat": 0.8855,
+        "reward-bench/Chat Hard": 0.4868,
+        "reward-bench/Safety": 0.3244,
+        "reward-bench/Reasoning": 0.7752,
+        "reward-bench/Prior Sets (0.5 weight)": 0.6533,
         "reward-bench/Factuality": 0.3179,
         "reward-bench/Precise IF": 0.2625,
         "reward-bench/Math": 0.3934,
-        "reward-bench/Safety": 0.6311,
         "reward-bench/Focus": 0.2707,
-        "reward-bench/Ties": 0.0198,
-        "reward-bench/Chat": 0.8855,
-        "reward-bench/Chat Hard": 0.4868,
-        "reward-bench/Reasoning": 0.7752,
-        "reward-bench/Prior Sets (0.5 weight)": 0.6533
+        "reward-bench/Ties": 0.0198
       }
     },
     {
@@ -59,17 +59,17 @@
       "developer": "OpenAssistant",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "reward-bench/Score": 0.6126,
+        "reward-bench/Score": 0.32,
+        "reward-bench/Chat": 0.8939,
+        "reward-bench/Chat Hard": 0.4518,
+        "reward-bench/Safety": 0.3667,
+        "reward-bench/Reasoning": 0.3855,
+        "reward-bench/Prior Sets (0.5 weight)": 0.5836,
         "reward-bench/Factuality": 0.3853,
         "reward-bench/Precise IF": 0.2687,
         "reward-bench/Math": 0.5027,
-        "reward-bench/Safety": 0.7338,
         "reward-bench/Focus": 0.2768,
-        "reward-bench/Ties": 0.12,
-        "reward-bench/Chat": 0.8939,
-        "reward-bench/Chat Hard": 0.4518,
-        "reward-bench/Reasoning": 0.3855,
-        "reward-bench/Prior Sets (0.5 weight)": 0.5836
+        "reward-bench/Ties": 0.12
       }
     }
   ]
diff --git a/data/developers/openbmb.json b/data/developers/openbmb.json
index d6a398c44a61b95d325c54de1768af4a13c46f1f..b9795ed819d46987af7a443e489394fa08308cdd 100644
--- a/data/developers/openbmb.json
+++ b/data/developers/openbmb.json
@@ -21,17 +21,17 @@
       "developer": "openbmb",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "reward-bench/Score": 0.8159,
+        "reward-bench/Score": 0.5806,
+        "reward-bench/Chat": 0.9804,
+        "reward-bench/Chat Hard": 0.6557,
+        "reward-bench/Safety": 0.6267,
+        "reward-bench/Reasoning": 0.8633,
+        "reward-bench/Prior Sets (0.5 weight)": 0.7172,
         "reward-bench/Factuality": 0.6,
         "reward-bench/Precise IF": 0.3438,
         "reward-bench/Math": 0.5683,
-        "reward-bench/Safety": 0.8135,
         "reward-bench/Focus": 0.7475,
-        "reward-bench/Ties": 0.5972,
-        "reward-bench/Chat": 0.9804,
-        "reward-bench/Chat Hard": 0.6557,
-        "reward-bench/Reasoning": 0.8633,
-        "reward-bench/Prior Sets (0.5 weight)": 0.7172
+        "reward-bench/Ties": 0.5972
       }
     },
     {
@@ -68,17 +68,17 @@
       "developer": "openbmb",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "reward-bench/Score": 0.6903,
+        "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/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/Chat": 0.9637,
-        "reward-bench/Chat Hard": 0.5548,
-        "reward-bench/Reasoning": 0.6244,
-        "reward-bench/Prior Sets (0.5 weight)": 0.7294
+        "reward-bench/Ties": 0.3036
       }
     }
   ]
diff --git a/data/developers/pku-alignment.json b/data/developers/pku-alignment.json
index 0ae80803f93980ecd8558a983e84a1646a1bd7d6..4cebe3d4c55c06b2bbbd44b7bb6fe487a030b922 100644
--- a/data/developers/pku-alignment.json
+++ b/data/developers/pku-alignment.json
@@ -26,17 +26,17 @@
       "developer": "PKU-Alignment",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "reward-bench/Score": 0.4727,
+        "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/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/Chat": 0.8184,
-        "reward-bench/Chat Hard": 0.2873,
-        "reward-bench/Reasoning": 0.346,
-        "reward-bench/Prior Sets (0.5 weight)": 0.5993
+        "reward-bench/Ties": -0.01
       }
     },
     {
diff --git a/data/developers/primeintellect.json b/data/developers/primeintellect.json
index 674a0e3b141480d7e0d33d0a2fe9b205b710216f..160722785b06f80d9b220dee435fad1245d45495 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": 0.276,
+        "hfopenllm_v2/BBH": 0.274,
         "hfopenllm_v2/MATH Level 5": 0.0,
-        "hfopenllm_v2/GPQA": 0.2534,
-        "hfopenllm_v2/MUSR": 0.3339,
-        "hfopenllm_v2/MMLU-PRO": 0.1123
+        "hfopenllm_v2/GPQA": 0.25,
+        "hfopenllm_v2/MUSR": 0.3753,
+        "hfopenllm_v2/MMLU-PRO": 0.112
       }
     },
     {
diff --git a/data/developers/prithivmlmods.json b/data/developers/prithivmlmods.json
index f14f3864a910968b11c756eb8300bd4bd3eea36e..88e743a4279f310dec935aed3968189a78be084e 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": 0.6064,
-        "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
+        "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
       }
     },
     {
diff --git a/data/developers/qingy2019.json b/data/developers/qingy2019.json
index f93967ea7ea0a389f1379b7b85428b832b816fb9..b11a9d79a541432fdd0c8e33c56cfaa201540388 100644
--- a/data/developers/qingy2019.json
+++ b/data/developers/qingy2019.json
@@ -35,12 +35,12 @@
       "developer": "qingy2019",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "hfopenllm_v2/IFEval": 0.2401,
-        "hfopenllm_v2/BBH": 0.4622,
-        "hfopenllm_v2/MATH Level 5": 0.0725,
-        "hfopenllm_v2/GPQA": 0.2609,
-        "hfopenllm_v2/MUSR": 0.3703,
-        "hfopenllm_v2/MMLU-PRO": 0.2379
+        "hfopenllm_v2/IFEval": 0.2358,
+        "hfopenllm_v2/BBH": 0.4612,
+        "hfopenllm_v2/MATH Level 5": 0.0642,
+        "hfopenllm_v2/GPQA": 0.2576,
+        "hfopenllm_v2/MUSR": 0.3717,
+        "hfopenllm_v2/MMLU-PRO": 0.2382
       }
     },
     {
@@ -49,12 +49,12 @@
       "developer": "qingy2019",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "hfopenllm_v2/IFEval": 0.6066,
-        "hfopenllm_v2/BBH": 0.635,
-        "hfopenllm_v2/MATH Level 5": 0.3716,
-        "hfopenllm_v2/GPQA": 0.3725,
+        "hfopenllm_v2/IFEval": 0.6005,
+        "hfopenllm_v2/BBH": 0.6356,
+        "hfopenllm_v2/MATH Level 5": 0.2764,
+        "hfopenllm_v2/GPQA": 0.3691,
         "hfopenllm_v2/MUSR": 0.4757,
-        "hfopenllm_v2/MMLU-PRO": 0.5331
+        "hfopenllm_v2/MMLU-PRO": 0.5339
       }
     },
     {
diff --git a/data/developers/quazim0t0.json b/data/developers/quazim0t0.json
index 135f1135e53ac7da23b4b9457344787d94d6e680..e5588b4aeabec7b69b53d4145ba5bbe548d82ff9 100644
--- a/data/developers/quazim0t0.json
+++ b/data/developers/quazim0t0.json
@@ -637,12 +637,12 @@
       "developer": "Quazim0t0",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "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
+        "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
       }
     },
     {
diff --git a/data/developers/qwen.json b/data/developers/qwen.json
index 727516da8d72881c91634dd8fcd12326550fd1bf..3433447d4af65af4b79f785b8a7b43fc273f9d86 100644
--- a/data/developers/qwen.json
+++ b/data/developers/qwen.json
@@ -1177,12 +1177,12 @@
       "developer": "Qwen",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "hfopenllm_v2/IFEval": 0.6101,
-        "hfopenllm_v2/BBH": 0.5008,
-        "hfopenllm_v2/MATH Level 5": 0.3716,
-        "hfopenllm_v2/GPQA": 0.2919,
-        "hfopenllm_v2/MUSR": 0.4073,
-        "hfopenllm_v2/MMLU-PRO": 0.3352
+        "hfopenllm_v2/IFEval": 0.6147,
+        "hfopenllm_v2/BBH": 0.4999,
+        "hfopenllm_v2/MATH Level 5": 0.031,
+        "hfopenllm_v2/GPQA": 0.2936,
+        "hfopenllm_v2/MUSR": 0.4099,
+        "hfopenllm_v2/MMLU-PRO": 0.3354
       }
     },
     {
diff --git a/data/developers/ray2333.json b/data/developers/ray2333.json
index 535b872cfc093237ac0d0dc85564191f8ac0a72c..51f9b51d9ebb192a98a4a9a46633e05cf73f77b6 100644
--- a/data/developers/ray2333.json
+++ b/data/developers/ray2333.json
@@ -79,17 +79,17 @@
       "developer": "Ray2333",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "reward-bench/Score": 0.589,
-        "reward-bench/Chat": 0.9832,
-        "reward-bench/Chat Hard": 0.6842,
-        "reward-bench/Safety": 0.7222,
-        "reward-bench/Reasoning": 0.9133,
-        "reward-bench/Prior Sets (0.5 weight)": 0.7209,
+        "reward-bench/Score": 0.8464,
         "reward-bench/Factuality": 0.5874,
         "reward-bench/Precise IF": 0.3875,
         "reward-bench/Math": 0.5902,
+        "reward-bench/Safety": 0.8676,
         "reward-bench/Focus": 0.6727,
-        "reward-bench/Ties": 0.5743
+        "reward-bench/Ties": 0.5743,
+        "reward-bench/Chat": 0.9832,
+        "reward-bench/Chat Hard": 0.6842,
+        "reward-bench/Reasoning": 0.9133,
+        "reward-bench/Prior Sets (0.5 weight)": 0.7209
       }
     },
     {
@@ -116,17 +116,17 @@
       "developer": "Ray2333",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "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/Score": 0.8542,
         "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/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
       }
     },
     {
diff --git a/data/developers/rombodawg.json b/data/developers/rombodawg.json
index a241fbd73dcecc7fc768ef47719ff98c1bcb64ab..e7b347a91d5be7f4c52661e255a50c99caa3a3fd 100644
--- a/data/developers/rombodawg.json
+++ b/data/developers/rombodawg.json
@@ -133,12 +133,12 @@
       "developer": "rombodawg",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "hfopenllm_v2/IFEval": 0.2595,
-        "hfopenllm_v2/BBH": 0.3884,
-        "hfopenllm_v2/MATH Level 5": 0.0914,
-        "hfopenllm_v2/GPQA": 0.2743,
+        "hfopenllm_v2/IFEval": 0.2566,
+        "hfopenllm_v2/BBH": 0.39,
+        "hfopenllm_v2/MATH Level 5": 0.1208,
+        "hfopenllm_v2/GPQA": 0.2626,
         "hfopenllm_v2/MUSR": 0.3991,
-        "hfopenllm_v2/MMLU-PRO": 0.2719
+        "hfopenllm_v2/MMLU-PRO": 0.2741
       }
     },
     {
diff --git a/data/developers/sfairxc.json b/data/developers/sfairxc.json
index f511504fa472f754b653d8fff6432038f2fa5642..0f83a5aa819fcf69906563e63fd5c5a7cc1f8ce0 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": 0.6292,
-        "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/Score": 0.8338,
         "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/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
       }
     }
   ]
diff --git a/data/developers/shikaichen.json b/data/developers/shikaichen.json
index 6502ef5b0e02cc85862537458f25816eb0826b7d..6162cba6dec7eaed27af88272ffb98342af2522b 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": 0.7249,
-        "reward-bench/Chat": 0.9637,
-        "reward-bench/Chat Hard": 0.9079,
-        "reward-bench/Safety": 0.9222,
-        "reward-bench/Reasoning": 0.9903,
+        "reward-bench/Score": 0.9499,
         "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/Ties": 0.7633,
+        "reward-bench/Chat": 0.9637,
+        "reward-bench/Chat Hard": 0.9079,
+        "reward-bench/Reasoning": 0.9903
       }
     }
   ]
diff --git a/data/developers/skywork.json b/data/developers/skywork.json
index 15f843864c8bce10620ff0dcdbde98d85af98ac4..a1886dbde5ab2f08ceeb175a3c92e5b11655f24d 100644
--- a/data/developers/skywork.json
+++ b/data/developers/skywork.json
@@ -71,16 +71,16 @@
         "hfopenllm_v2/GPQA": 0.344,
         "hfopenllm_v2/MUSR": 0.4231,
         "hfopenllm_v2/MMLU-PRO": 0.4103,
-        "reward-bench/Score": 0.9426,
+        "reward-bench/Score": 0.7531,
+        "reward-bench/Chat": 0.9609,
+        "reward-bench/Chat Hard": 0.8991,
+        "reward-bench/Safety": 0.9689,
+        "reward-bench/Reasoning": 0.9807,
         "reward-bench/Factuality": 0.7674,
         "reward-bench/Precise IF": 0.375,
         "reward-bench/Math": 0.6721,
-        "reward-bench/Safety": 0.9297,
         "reward-bench/Focus": 0.9172,
-        "reward-bench/Ties": 0.8182,
-        "reward-bench/Chat": 0.9609,
-        "reward-bench/Chat Hard": 0.8991,
-        "reward-bench/Reasoning": 0.9807
+        "reward-bench/Ties": 0.8182
       }
     },
     {
@@ -89,16 +89,16 @@
       "developer": "Skywork",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "reward-bench/Score": 0.9252,
+        "reward-bench/Score": 0.7314,
+        "reward-bench/Chat": 0.9581,
+        "reward-bench/Chat Hard": 0.8728,
+        "reward-bench/Safety": 0.9333,
+        "reward-bench/Reasoning": 0.962,
         "reward-bench/Factuality": 0.6989,
         "reward-bench/Precise IF": 0.425,
         "reward-bench/Math": 0.6284,
-        "reward-bench/Safety": 0.9081,
         "reward-bench/Focus": 0.9616,
-        "reward-bench/Ties": 0.741,
-        "reward-bench/Chat": 0.9581,
-        "reward-bench/Chat Hard": 0.8728,
-        "reward-bench/Reasoning": 0.962
+        "reward-bench/Ties": 0.741
       }
     },
     {
diff --git a/data/developers/tanliboy.json b/data/developers/tanliboy.json
index 7b17e651b33310ae087a6456408950e1456ff623..daa17945601d8528cbfc7c883e4dc4315ea363fc 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": 0.1829,
-        "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
+        "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
       }
     },
     {
diff --git a/data/developers/valiantlabs.json b/data/developers/valiantlabs.json
index b0b3adff2288383cd6923301f5751d53ee8ba504..fea79922ada6f8587a14d0c683f2c0090d2ca061 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": 0.3496,
-        "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
+        "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
       }
     },
     {
@@ -105,12 +105,12 @@
       "developer": "ValiantLabs",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "hfopenllm_v2/IFEval": 0.2678,
-        "hfopenllm_v2/BBH": 0.4429,
-        "hfopenllm_v2/MATH Level 5": 0.0521,
-        "hfopenllm_v2/GPQA": 0.302,
-        "hfopenllm_v2/MUSR": 0.3959,
-        "hfopenllm_v2/MMLU-PRO": 0.2927
+        "hfopenllm_v2/IFEval": 0.6496,
+        "hfopenllm_v2/BBH": 0.4774,
+        "hfopenllm_v2/MATH Level 5": 0.0566,
+        "hfopenllm_v2/GPQA": 0.3104,
+        "hfopenllm_v2/MUSR": 0.3909,
+        "hfopenllm_v2/MMLU-PRO": 0.3382
       }
     },
     {
diff --git a/data/developers/xai.json b/data/developers/xai.json
index 5bf50e8754b14e71e2153e4564b26c11231d3d27..d0ba30a6d3c372a4bdb6c48d3c0cb90677ed30d5 100644
--- a/data/developers/xai.json
+++ b/data/developers/xai.json
@@ -78,7 +78,7 @@
       "developer": "xAI",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "terminal-bench-2.0/terminal-bench-2.0": 23.1
+        "terminal-bench-2.0/terminal-bench-2.0": 25.4
       }
     },
     {
diff --git a/data/developers/yam-peleg.json b/data/developers/yam-peleg.json
index f415128b8e93253c12ae15436b68cf36d5f248bf..3161f95274f1998cddb90c53a59dce4097dbe0fd 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": 0.177,
-        "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
+        "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
       }
     }
   ]
diff --git a/data/developers/ycros.json b/data/developers/ycros.json
index 9b83f7f872f197f98fd71538cda202af618f5659..e95400442aba80bbdb2ffa85224e7399ce946b0d 100644
--- a/data/developers/ycros.json
+++ b/data/developers/ycros.json
@@ -7,12 +7,12 @@
       "developer": "ycros",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "hfopenllm_v2/IFEval": 0.5994,
-        "hfopenllm_v2/BBH": 0.5159,
-        "hfopenllm_v2/MATH Level 5": 0.0785,
-        "hfopenllm_v2/GPQA": 0.3045,
-        "hfopenllm_v2/MUSR": 0.4203,
-        "hfopenllm_v2/MMLU-PRO": 0.3473
+        "hfopenllm_v2/IFEval": 0.6262,
+        "hfopenllm_v2/BBH": 0.5142,
+        "hfopenllm_v2/MATH Level 5": 0.0937,
+        "hfopenllm_v2/GPQA": 0.3079,
+        "hfopenllm_v2/MUSR": 0.4138,
+        "hfopenllm_v2/MMLU-PRO": 0.3481
       }
     }
   ]
diff --git a/data/developers/z-ai.json b/data/developers/z-ai.json
index 25c72391d11bee4c4ccdbee1d0c2cdded93b09ab..d4ada9599b117d1b4893fef821933bb44c4fb1d9 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": 33.4
+        "terminal-bench-2.0/terminal-bench-2.0": 33.3
       }
     },
     {
diff --git a/data/models.json b/data/models.json
index a4ab0a1994ca0a7faae8835c098ea436fc0ab99c..b08337869e0315ca25ad74e1e682be0126b52503 100644
--- a/data/models.json
+++ b/data/models.json
@@ -1005,12 +1005,12 @@
     "developer": "adriszmar",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "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
+      "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
     }
   },
   {
@@ -1391,10 +1391,10 @@
     "developer": "AI2",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "reward-bench/Score": 0.6895,
+      "reward-bench/Score": 0.7008,
       "reward-bench/Chat": 0.9385,
-      "reward-bench/Chat Hard": 0.3706,
-      "reward-bench/Safety": 0.7595
+      "reward-bench/Chat Hard": 0.3882,
+      "reward-bench/Safety": 0.7757
     }
   },
   {
@@ -2243,7 +2243,7 @@
     "developer": "Alibaba",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "terminal-bench-2.0/terminal-bench-2.0": 25.4
+      "terminal-bench-2.0/terminal-bench-2.0": 23.9
     }
   },
   {
@@ -2390,17 +2390,17 @@
     "developer": "allenai",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "reward-bench/Score": 0.7606,
-      "reward-bench/Chat": 0.9665,
-      "reward-bench/Chat Hard": 0.8355,
-      "reward-bench/Safety": 0.8844,
-      "reward-bench/Reasoning": 0.8969,
-      "reward-bench/Prior Sets (0.5 weight)": 0.0,
+      "reward-bench/Score": 0.9021,
       "reward-bench/Factuality": 0.8126,
       "reward-bench/Precise IF": 0.4188,
       "reward-bench/Math": 0.6995,
+      "reward-bench/Safety": 0.9095,
       "reward-bench/Focus": 0.8646,
-      "reward-bench/Ties": 0.8835
+      "reward-bench/Ties": 0.8835,
+      "reward-bench/Chat": 0.9665,
+      "reward-bench/Chat Hard": 0.8355,
+      "reward-bench/Reasoning": 0.8969,
+      "reward-bench/Prior Sets (0.5 weight)": 0.0
     }
   },
   {
@@ -2508,12 +2508,12 @@
     "developer": "allenai",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "hfopenllm_v2/IFEval": 0.8255,
-      "hfopenllm_v2/BBH": 0.4061,
-      "hfopenllm_v2/MATH Level 5": 0.2115,
-      "hfopenllm_v2/GPQA": 0.297,
+      "hfopenllm_v2/IFEval": 0.8267,
+      "hfopenllm_v2/BBH": 0.405,
+      "hfopenllm_v2/MATH Level 5": 0.1964,
+      "hfopenllm_v2/GPQA": 0.2987,
       "hfopenllm_v2/MUSR": 0.4175,
-      "hfopenllm_v2/MMLU-PRO": 0.2821
+      "hfopenllm_v2/MMLU-PRO": 0.2827
     }
   },
   {
@@ -2536,17 +2536,17 @@
     "developer": "allenai",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "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/Score": 0.8431,
       "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/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
     }
   },
   {
@@ -2609,17 +2609,17 @@
     "developer": "allenai",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "reward-bench/Score": 0.8551,
+      "reward-bench/Score": 0.6821,
+      "reward-bench/Chat": 0.9497,
+      "reward-bench/Chat Hard": 0.7917,
+      "reward-bench/Safety": 0.8978,
+      "reward-bench/Reasoning": 0.8005,
+      "reward-bench/Prior Sets (0.5 weight)": 0.0,
       "reward-bench/Factuality": 0.7326,
       "reward-bench/Precise IF": 0.3875,
       "reward-bench/Math": 0.5792,
-      "reward-bench/Safety": 0.8784,
       "reward-bench/Focus": 0.8889,
-      "reward-bench/Ties": 0.6063,
-      "reward-bench/Chat": 0.9497,
-      "reward-bench/Chat Hard": 0.7917,
-      "reward-bench/Reasoning": 0.8005,
-      "reward-bench/Prior Sets (0.5 weight)": 0.0
+      "reward-bench/Ties": 0.6063
     }
   },
   {
@@ -3381,6 +3381,21 @@
       "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",
@@ -6541,11 +6556,11 @@
     "developer": "amd",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "hfopenllm_v2/IFEval": 0.1842,
-      "hfopenllm_v2/BBH": 0.2974,
-      "hfopenllm_v2/MATH Level 5": 0.0053,
-      "hfopenllm_v2/GPQA": 0.2525,
-      "hfopenllm_v2/MUSR": 0.378,
+      "hfopenllm_v2/IFEval": 0.1918,
+      "hfopenllm_v2/BBH": 0.2969,
+      "hfopenllm_v2/MATH Level 5": 0.0076,
+      "hfopenllm_v2/GPQA": 0.2584,
+      "hfopenllm_v2/MUSR": 0.3846,
       "hfopenllm_v2/MMLU-PRO": 0.1169
     }
   },
@@ -6985,16 +7000,16 @@
       "helm_mmlu/Virology": 0.602,
       "helm_mmlu/World Religions": 0.924,
       "helm_mmlu/Mean win rate": 0.17,
-      "reward-bench/Score": 0.6466,
-      "reward-bench/Chat": 0.9637,
-      "reward-bench/Chat Hard": 0.7401,
-      "reward-bench/Safety": 0.8519,
-      "reward-bench/Reasoning": 0.8469,
+      "reward-bench/Score": 0.8417,
       "reward-bench/Factuality": 0.5284,
       "reward-bench/Precise IF": 0.3875,
       "reward-bench/Math": 0.5683,
+      "reward-bench/Safety": 0.8162,
       "reward-bench/Focus": 0.8697,
-      "reward-bench/Ties": 0.674
+      "reward-bench/Ties": 0.674,
+      "reward-bench/Chat": 0.9637,
+      "reward-bench/Chat Hard": 0.7401,
+      "reward-bench/Reasoning": 0.8469
     }
   },
   {
@@ -7152,17 +7167,17 @@
       "helm_mmlu/Virology": 0.542,
       "helm_mmlu/World Religions": 0.871,
       "helm_mmlu/Mean win rate": 0.28,
-      "reward-bench/Score": 0.7289,
+      "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/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/Chat": 0.9274,
-      "reward-bench/Chat Hard": 0.5197,
-      "reward-bench/Reasoning": 0.706,
-      "reward-bench/Prior Sets (0.5 weight)": 0.6635
+      "reward-bench/Ties": 0.0899
     }
   },
   {
@@ -7217,16 +7232,16 @@
       "helm_mmlu/Virology": 0.578,
       "helm_mmlu/World Religions": 0.901,
       "helm_mmlu/Mean win rate": 0.014,
-      "reward-bench/Score": 0.8008,
+      "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/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/Chat": 0.9469,
-      "reward-bench/Chat Hard": 0.6031,
-      "reward-bench/Reasoning": 0.7868
+      "reward-bench/Ties": 0.5601
     }
   },
   {
@@ -7306,7 +7321,7 @@
     "developer": "Anthropic",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "terminal-bench-2.0/terminal-bench-2.0": 27.5
+      "terminal-bench-2.0/terminal-bench-2.0": 35.5
     }
   },
   {
@@ -7431,12 +7446,12 @@
     "developer": "Anthropic",
     "evaluator_relationship": null,
     "benchmark_scores": {
+      "browsecompplus/browsecompplus": 0.49,
       "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": 0.72,
+      "swe-bench/swe-bench": 0.8072,
+      "tau-bench-2_airline/tau-bench-2/airline": 0.66,
       "tau-bench-2_retail/tau-bench-2/retail": 0.85,
-      "tau-bench-2_telecom/tau-bench-2/telecom": 0.76
+      "tau-bench-2_telecom/tau-bench-2/telecom": 0.84
     }
   },
   {
@@ -7445,7 +7460,7 @@
     "developer": "Anthropic",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "terminal-bench-2.0/terminal-bench-2.0": 34.8
+      "terminal-bench-2.0/terminal-bench-2.0": 38.0
     }
   },
   {
@@ -7454,7 +7469,7 @@
     "developer": "Anthropic",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "terminal-bench-2.0/terminal-bench-2.0": 52.1
+      "terminal-bench-2.0/terminal-bench-2.0": 59.1
     }
   },
   {
@@ -7463,7 +7478,7 @@
     "developer": "Anthropic",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "terminal-bench-2.0/terminal-bench-2.0": 74.7
+      "terminal-bench-2.0/terminal-bench-2.0": 66.9
     }
   },
   {
@@ -7537,7 +7552,7 @@
     "developer": "Anthropic",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "terminal-bench-2.0/terminal-bench-2.0": 42.5
+      "terminal-bench-2.0/terminal-bench-2.0": 40.1
     }
   },
   {
@@ -8076,12 +8091,12 @@
     "developer": "AtAndDev",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "hfopenllm_v2/IFEval": 0.4605,
-      "hfopenllm_v2/BBH": 0.4258,
-      "hfopenllm_v2/MATH Level 5": 0.0748,
-      "hfopenllm_v2/GPQA": 0.2659,
-      "hfopenllm_v2/MUSR": 0.3636,
-      "hfopenllm_v2/MMLU-PRO": 0.2812
+      "hfopenllm_v2/IFEval": 0.4511,
+      "hfopenllm_v2/BBH": 0.4275,
+      "hfopenllm_v2/MATH Level 5": 0.1473,
+      "hfopenllm_v2/GPQA": 0.2701,
+      "hfopenllm_v2/MUSR": 0.3623,
+      "hfopenllm_v2/MMLU-PRO": 0.2806
     }
   },
   {
@@ -9828,12 +9843,12 @@
     "developer": "BoltMonkey",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "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
+      "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
     }
   },
   {
@@ -10584,12 +10599,12 @@
     "developer": "bunnycore",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "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
+      "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
     }
   },
   {
@@ -11813,17 +11828,17 @@
     "developer": "CIR-AMS",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "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/Score": 0.8172,
       "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/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
     }
   },
   {
@@ -13385,12 +13400,12 @@
     "developer": "cpayne1303",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "hfopenllm_v2/IFEval": 0.1949,
-      "hfopenllm_v2/BBH": 0.2965,
-      "hfopenllm_v2/MATH Level 5": 0.0045,
+      "hfopenllm_v2/IFEval": 0.1916,
+      "hfopenllm_v2/BBH": 0.2977,
+      "hfopenllm_v2/MATH Level 5": 0.0,
       "hfopenllm_v2/GPQA": 0.2685,
-      "hfopenllm_v2/MUSR": 0.3885,
-      "hfopenllm_v2/MMLU-PRO": 0.1111
+      "hfopenllm_v2/MUSR": 0.3872,
+      "hfopenllm_v2/MMLU-PRO": 0.1132
     }
   },
   {
@@ -14323,12 +14338,12 @@
     "developer": "Daemontatox",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "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
+      "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
     }
   },
   {
@@ -15378,12 +15393,12 @@
     "developer": "DavieLion",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "hfopenllm_v2/IFEval": 0.1549,
-      "hfopenllm_v2/BBH": 0.2937,
-      "hfopenllm_v2/MATH Level 5": 0.006,
-      "hfopenllm_v2/GPQA": 0.2576,
+      "hfopenllm_v2/IFEval": 0.1507,
+      "hfopenllm_v2/BBH": 0.293,
+      "hfopenllm_v2/MATH Level 5": 0.0,
+      "hfopenllm_v2/GPQA": 0.2534,
       "hfopenllm_v2/MUSR": 0.3565,
-      "hfopenllm_v2/MMLU-PRO": 0.1128
+      "hfopenllm_v2/MMLU-PRO": 0.1125
     }
   },
   {
@@ -16361,12 +16376,12 @@
     "developer": "dfurman",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "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
+      "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
     }
   },
   {
@@ -17005,12 +17020,12 @@
     "developer": "DoppelReflEx",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "hfopenllm_v2/IFEval": 0.436,
-      "hfopenllm_v2/BBH": 0.4956,
-      "hfopenllm_v2/MATH Level 5": 0.0589,
-      "hfopenllm_v2/GPQA": 0.3205,
-      "hfopenllm_v2/MUSR": 0.3843,
-      "hfopenllm_v2/MMLU-PRO": 0.3237
+      "hfopenllm_v2/IFEval": 0.451,
+      "hfopenllm_v2/BBH": 0.4944,
+      "hfopenllm_v2/MATH Level 5": 0.1156,
+      "hfopenllm_v2/GPQA": 0.3196,
+      "hfopenllm_v2/MUSR": 0.3896,
+      "hfopenllm_v2/MMLU-PRO": 0.3256
     }
   },
   {
@@ -23441,12 +23456,12 @@
     "developer": "Google",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "hfopenllm_v2/IFEval": 0.2207,
-      "hfopenllm_v2/BBH": 0.4537,
-      "hfopenllm_v2/MATH Level 5": 0.0008,
-      "hfopenllm_v2/GPQA": 0.2458,
-      "hfopenllm_v2/MUSR": 0.422,
-      "hfopenllm_v2/MMLU-PRO": 0.2142
+      "hfopenllm_v2/IFEval": 0.2237,
+      "hfopenllm_v2/BBH": 0.4531,
+      "hfopenllm_v2/MATH Level 5": 0.0076,
+      "hfopenllm_v2/GPQA": 0.2525,
+      "hfopenllm_v2/MUSR": 0.4181,
+      "hfopenllm_v2/MMLU-PRO": 0.2147
     }
   },
   {
@@ -23504,7 +23519,6 @@
     "developer": "Google",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "ace/Gaming Score": 0.415,
       "apex-agents/Overall Pass@1": 0.24,
       "apex-agents/Overall Pass@8": 0.367,
       "apex-agents/Overall Mean Score": 0.395,
@@ -23512,6 +23526,7 @@
       "apex-agents/Management Consulting Pass@1": 0.193,
       "apex-agents/Corporate Law Pass@1": 0.259,
       "apex-agents/Corporate Lawyer Mean Score": 0.524,
+      "ace/Gaming Score": 0.415,
       "apex-v1/Overall Score": 0.64,
       "apex-v1/Consulting Score": 0.64
     }
@@ -24088,7 +24103,7 @@
       "reward-bench/Safety": 0.909,
       "reward-bench/Focus": 0.841,
       "reward-bench/Ties": 0.809,
-      "terminal-bench-2.0/terminal-bench-2.0": 16.9
+      "terminal-bench-2.0/terminal-bench-2.0": 17.1
     }
   },
   {
@@ -24188,7 +24203,7 @@
       "reward-bench/Safety": 0.881,
       "reward-bench/Focus": 0.805,
       "reward-bench/Ties": 0.811,
-      "terminal-bench-2.0/terminal-bench-2.0": 16.4
+      "terminal-bench-2.0/terminal-bench-2.0": 19.6
     }
   },
   {
@@ -24235,7 +24250,7 @@
     "developer": "Google",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "terminal-bench-2.0/terminal-bench-2.0": 56.9
+      "terminal-bench-2.0/terminal-bench-2.0": 62.2
     }
   },
   {
@@ -24244,7 +24259,7 @@
     "developer": "Google",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "appworld_test_normal/appworld/test_normal": 0.36,
+      "appworld_test_normal/appworld/test_normal": 0.13,
       "browsecompplus/browsecompplus": 0.48,
       "global-mmlu-lite/Global MMLU Lite": 0.9453,
       "global-mmlu-lite/Culturally Sensitive": 0.9397,
@@ -24265,10 +24280,10 @@
       "global-mmlu-lite/Yoruba": 0.9425,
       "global-mmlu-lite/Chinese": 0.9475,
       "global-mmlu-lite/Burmese": 0.9425,
-      "swe-bench/swe-bench": 0.71,
-      "tau-bench-2_airline/tau-bench-2/airline": 0.68,
+      "swe-bench/swe-bench": 0.7234,
+      "tau-bench-2_airline/tau-bench-2/airline": 0.7,
       "tau-bench-2_retail/tau-bench-2/retail": 0.7805,
-      "tau-bench-2_telecom/tau-bench-2/telecom": 0.73
+      "tau-bench-2_telecom/tau-bench-2/telecom": 0.6852
     }
   },
   {
@@ -24421,12 +24436,12 @@
     "developer": "Google",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "hfopenllm_v2/IFEval": 0.5288,
-      "hfopenllm_v2/BBH": 0.4178,
-      "hfopenllm_v2/MATH Level 5": 0.0476,
-      "hfopenllm_v2/GPQA": 0.2752,
-      "hfopenllm_v2/MUSR": 0.3728,
-      "hfopenllm_v2/MMLU-PRO": 0.2467
+      "hfopenllm_v2/IFEval": 0.5078,
+      "hfopenllm_v2/BBH": 0.4226,
+      "hfopenllm_v2/MATH Level 5": 0.0347,
+      "hfopenllm_v2/GPQA": 0.2852,
+      "hfopenllm_v2/MUSR": 0.3964,
+      "hfopenllm_v2/MMLU-PRO": 0.2578
     }
   },
   {
@@ -25543,12 +25558,12 @@
     "developer": "Gunulhona",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "hfopenllm_v2/IFEval": 0.288,
-      "hfopenllm_v2/BBH": 0.5154,
+      "hfopenllm_v2/IFEval": 0.4441,
+      "hfopenllm_v2/BBH": 0.4863,
       "hfopenllm_v2/MATH Level 5": 0.0,
-      "hfopenllm_v2/GPQA": 0.3247,
-      "hfopenllm_v2/MUSR": 0.408,
-      "hfopenllm_v2/MMLU-PRO": 0.3817
+      "hfopenllm_v2/GPQA": 0.307,
+      "hfopenllm_v2/MUSR": 0.3986,
+      "hfopenllm_v2/MMLU-PRO": 0.3098
     }
   },
   {
@@ -25879,17 +25894,17 @@
     "developer": "hendrydong",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "reward-bench/Score": 0.5851,
-      "reward-bench/Chat": 0.9832,
-      "reward-bench/Chat Hard": 0.5789,
-      "reward-bench/Safety": 0.6956,
-      "reward-bench/Reasoning": 0.7434,
-      "reward-bench/Prior Sets (0.5 weight)": 0.7508,
+      "reward-bench/Score": 0.7847,
       "reward-bench/Factuality": 0.5779,
       "reward-bench/Precise IF": 0.3625,
       "reward-bench/Math": 0.6011,
+      "reward-bench/Safety": 0.85,
       "reward-bench/Focus": 0.6747,
-      "reward-bench/Ties": 0.5988
+      "reward-bench/Ties": 0.5988,
+      "reward-bench/Chat": 0.9832,
+      "reward-bench/Chat Hard": 0.5789,
+      "reward-bench/Reasoning": 0.7434,
+      "reward-bench/Prior Sets (0.5 weight)": 0.7508
     }
   },
   {
@@ -26771,12 +26786,12 @@
     "developer": "HuggingFaceTB",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "hfopenllm_v2/IFEval": 0.2883,
-      "hfopenllm_v2/BBH": 0.3124,
-      "hfopenllm_v2/MATH Level 5": 0.003,
-      "hfopenllm_v2/GPQA": 0.2357,
-      "hfopenllm_v2/MUSR": 0.3662,
-      "hfopenllm_v2/MMLU-PRO": 0.1115
+      "hfopenllm_v2/IFEval": 0.0593,
+      "hfopenllm_v2/BBH": 0.3135,
+      "hfopenllm_v2/MATH Level 5": 0.0144,
+      "hfopenllm_v2/GPQA": 0.2341,
+      "hfopenllm_v2/MUSR": 0.3871,
+      "hfopenllm_v2/MMLU-PRO": 0.1092
     }
   },
   {
@@ -28206,6 +28221,20 @@
       "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",
@@ -28622,16 +28651,16 @@
     "developer": "internlm",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "reward-bench/Score": 0.8217,
+      "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/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/Chat": 0.9358,
-      "reward-bench/Chat Hard": 0.6623,
-      "reward-bench/Reasoning": 0.8724
+      "reward-bench/Ties": 0.1934
     }
   },
   {
@@ -28640,16 +28669,16 @@
     "developer": "internlm",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "reward-bench/Score": 0.5628,
-      "reward-bench/Chat": 0.9888,
-      "reward-bench/Chat Hard": 0.7654,
-      "reward-bench/Safety": 0.6111,
-      "reward-bench/Reasoning": 0.9576,
+      "reward-bench/Score": 0.9016,
       "reward-bench/Factuality": 0.5558,
       "reward-bench/Precise IF": 0.3625,
       "reward-bench/Math": 0.5738,
+      "reward-bench/Safety": 0.8946,
       "reward-bench/Focus": 0.7253,
-      "reward-bench/Ties": 0.5483
+      "reward-bench/Ties": 0.5483,
+      "reward-bench/Chat": 0.9888,
+      "reward-bench/Chat Hard": 0.7654,
+      "reward-bench/Reasoning": 0.9576
     }
   },
   {
@@ -28672,16 +28701,16 @@
     "developer": "internlm",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "reward-bench/Score": 0.8759,
+      "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/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/Chat": 0.9916,
-      "reward-bench/Chat Hard": 0.6952,
-      "reward-bench/Reasoning": 0.9453
+      "reward-bench/Ties": 0.5164
     }
   },
   {
@@ -28956,12 +28985,12 @@
     "developer": "Isaak-Carter",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "hfopenllm_v2/IFEval": 0.2553,
-      "hfopenllm_v2/BBH": 0.4725,
-      "hfopenllm_v2/MATH Level 5": 0.0529,
-      "hfopenllm_v2/GPQA": 0.2919,
-      "hfopenllm_v2/MUSR": 0.3654,
-      "hfopenllm_v2/MMLU-PRO": 0.3316
+      "hfopenllm_v2/IFEval": 0.2477,
+      "hfopenllm_v2/BBH": 0.4758,
+      "hfopenllm_v2/MATH Level 5": 0.0453,
+      "hfopenllm_v2/GPQA": 0.2911,
+      "hfopenllm_v2/MUSR": 0.3641,
+      "hfopenllm_v2/MMLU-PRO": 0.3292
     }
   },
   {
@@ -37955,12 +37984,12 @@
     "developer": "LeroyDyer",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "hfopenllm_v2/IFEval": 0.3066,
-      "hfopenllm_v2/BBH": 0.4577,
+      "hfopenllm_v2/IFEval": 0.3036,
+      "hfopenllm_v2/BBH": 0.4575,
       "hfopenllm_v2/MATH Level 5": 0.0446,
-      "hfopenllm_v2/GPQA": 0.2995,
-      "hfopenllm_v2/MUSR": 0.4254,
-      "hfopenllm_v2/MMLU-PRO": 0.2318
+      "hfopenllm_v2/GPQA": 0.3012,
+      "hfopenllm_v2/MUSR": 0.4253,
+      "hfopenllm_v2/MMLU-PRO": 0.2329
     }
   },
   {
@@ -38907,12 +38936,12 @@
     "developer": "llmat",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "hfopenllm_v2/IFEval": 0.377,
-      "hfopenllm_v2/BBH": 0.3978,
-      "hfopenllm_v2/MATH Level 5": 0.0242,
-      "hfopenllm_v2/GPQA": 0.2668,
-      "hfopenllm_v2/MUSR": 0.3555,
-      "hfopenllm_v2/MMLU-PRO": 0.2278
+      "hfopenllm_v2/IFEval": 0.364,
+      "hfopenllm_v2/BBH": 0.4005,
+      "hfopenllm_v2/MATH Level 5": 0.0015,
+      "hfopenllm_v2/GPQA": 0.2693,
+      "hfopenllm_v2/MUSR": 0.3529,
+      "hfopenllm_v2/MMLU-PRO": 0.2301
     }
   },
   {
@@ -43206,12 +43235,12 @@
     "developer": "microsoft",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "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
+      "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
     }
   },
   {
@@ -43322,12 +43351,12 @@
     "developer": "microsoft",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "hfopenllm_v2/IFEval": 0.0488,
-      "hfopenllm_v2/BBH": 0.6703,
-      "hfopenllm_v2/MATH Level 5": 0.2787,
-      "hfopenllm_v2/GPQA": 0.401,
+      "hfopenllm_v2/IFEval": 0.0585,
+      "hfopenllm_v2/BBH": 0.6691,
+      "hfopenllm_v2/MATH Level 5": 0.3165,
+      "hfopenllm_v2/GPQA": 0.406,
       "hfopenllm_v2/MUSR": 0.5034,
-      "hfopenllm_v2/MMLU-PRO": 0.5295
+      "hfopenllm_v2/MMLU-PRO": 0.5287
     }
   },
   {
@@ -44423,12 +44452,12 @@
     "developer": "mistralai",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "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
+      "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
     }
   },
   {
@@ -44729,12 +44758,12 @@
     "developer": "mlabonne",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "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
+      "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
     }
   },
   {
@@ -45288,7 +45317,7 @@
     "developer": "Multiple",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "terminal-bench-2.0/terminal-bench-2.0": 71.0
+      "terminal-bench-2.0/terminal-bench-2.0": 58.4
     }
   },
   {
@@ -45604,12 +45633,12 @@
     "developer": "nazimali",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "hfopenllm_v2/IFEval": 0.486,
-      "hfopenllm_v2/BBH": 0.4721,
-      "hfopenllm_v2/MATH Level 5": 0.0846,
-      "hfopenllm_v2/GPQA": 0.2844,
-      "hfopenllm_v2/MUSR": 0.4006,
-      "hfopenllm_v2/MMLU-PRO": 0.3087
+      "hfopenllm_v2/IFEval": 0.4964,
+      "hfopenllm_v2/BBH": 0.4699,
+      "hfopenllm_v2/MATH Level 5": 0.0045,
+      "hfopenllm_v2/GPQA": 0.2827,
+      "hfopenllm_v2/MUSR": 0.3979,
+      "hfopenllm_v2/MMLU-PRO": 0.3063
     }
   },
   {
@@ -48113,17 +48142,17 @@
     "developer": "Nexusflow",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "reward-bench/Score": 0.8133,
+      "reward-bench/Score": 0.4553,
+      "reward-bench/Chat": 0.9693,
+      "reward-bench/Chat Hard": 0.5724,
+      "reward-bench/Safety": 0.7556,
+      "reward-bench/Reasoning": 0.8845,
+      "reward-bench/Prior Sets (0.5 weight)": 0.7137,
       "reward-bench/Factuality": 0.4589,
       "reward-bench/Precise IF": 0.3187,
       "reward-bench/Math": 0.6175,
-      "reward-bench/Safety": 0.877,
       "reward-bench/Focus": 0.4808,
-      "reward-bench/Ties": 0.1004,
-      "reward-bench/Chat": 0.9693,
-      "reward-bench/Chat Hard": 0.5724,
-      "reward-bench/Reasoning": 0.8845,
-      "reward-bench/Prior Sets (0.5 weight)": 0.7137
+      "reward-bench/Ties": 0.1004
     }
   },
   {
@@ -48288,16 +48317,16 @@
     "developer": "nicolinho",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "reward-bench/Score": 0.9314,
+      "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/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/Chat": 0.9637,
-      "reward-bench/Chat Hard": 0.8684,
-      "reward-bench/Reasoning": 0.9677
+      "reward-bench/Ties": 0.7234
     }
   },
   {
@@ -50364,12 +50393,12 @@
     "developer": "ontocord",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "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
+      "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
     }
   },
   {
@@ -50982,16 +51011,16 @@
     "developer": "OpenAI",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "ace/Overall Score": 0.515,
-      "ace/Food Score": 0.65,
-      "ace/Gaming Score": 0.578,
       "apex-agents/Overall Pass@1": 0.23,
       "apex-agents/Overall Pass@8": 0.4,
       "apex-agents/Overall Mean Score": 0.387,
       "apex-agents/Investment Banking Pass@1": 0.273,
       "apex-agents/Management Consulting Pass@1": 0.227,
       "apex-agents/Corporate Law Pass@1": 0.189,
-      "apex-agents/Corporate Lawyer Mean Score": 0.443
+      "apex-agents/Corporate Lawyer Mean Score": 0.443,
+      "ace/Overall Score": 0.515,
+      "ace/Food Score": 0.65,
+      "ace/Gaming Score": 0.578
     }
   },
   {
@@ -51591,16 +51620,16 @@
       "helm_mmlu/Virology": 0.578,
       "helm_mmlu/World Religions": 0.883,
       "helm_mmlu/Mean win rate": 0.52,
-      "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/Score": 0.8673,
       "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/Ties": 0.7819,
+      "reward-bench/Chat": 0.9609,
+      "reward-bench/Chat Hard": 0.761,
+      "reward-bench/Reasoning": 0.8661
     }
   },
   {
@@ -51678,16 +51707,16 @@
       "helm_mmlu/Virology": 0.536,
       "helm_mmlu/World Religions": 0.86,
       "helm_mmlu/Mean win rate": 0.774,
-      "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/Score": 0.8007,
       "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/Ties": 0.6962,
+      "reward-bench/Chat": 0.9497,
+      "reward-bench/Chat Hard": 0.6075,
+      "reward-bench/Reasoning": 0.8374
     }
   },
   {
@@ -51741,7 +51770,7 @@
     "developer": "OpenAI",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "terminal-bench-2.0/terminal-bench-2.0": 43.4
+      "terminal-bench-2.0/terminal-bench-2.0": 41.3
     }
   },
   {
@@ -51750,7 +51779,7 @@
     "developer": "OpenAI",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "terminal-bench-2.0/terminal-bench-2.0": 31.9
+      "terminal-bench-2.0/terminal-bench-2.0": 22.2
     }
   },
   {
@@ -51773,7 +51802,7 @@
     "developer": "OpenAI",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "terminal-bench-2.0/terminal-bench-2.0": 7.0
+      "terminal-bench-2.0/terminal-bench-2.0": 7.9
     }
   },
   {
@@ -51805,7 +51834,7 @@
     "developer": "OpenAI",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "terminal-bench-2.0/terminal-bench-2.0": 53.5
+      "terminal-bench-2.0/terminal-bench-2.0": 36.9
     }
   },
   {
@@ -51832,7 +51861,7 @@
     "developer": "OpenAI",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "terminal-bench-2.0/terminal-bench-2.0": 60.7
+      "terminal-bench-2.0/terminal-bench-2.0": 54.0
     }
   },
   {
@@ -51842,13 +51871,13 @@
     "evaluator_relationship": null,
     "benchmark_scores": {
       "appworld_test_normal/appworld/test_normal": 0.0,
-      "browsecompplus/browsecompplus": 0.26,
+      "browsecompplus/browsecompplus": 0.48,
       "livecodebenchpro/Hard Problems": 0.1594,
       "livecodebenchpro/Medium Problems": 0.5211,
       "livecodebenchpro/Easy Problems": 0.9014,
-      "swe-bench/swe-bench": 0.57,
-      "tau-bench-2_airline/tau-bench-2/airline": 0.6,
-      "tau-bench-2_retail/tau-bench-2/retail": 0.68,
+      "swe-bench/swe-bench": 0.5455,
+      "tau-bench-2_airline/tau-bench-2/airline": 0.48,
+      "tau-bench-2_retail/tau-bench-2/retail": 0.51,
       "tau-bench-2_telecom/tau-bench-2/telecom": 0.5354
     }
   },
@@ -51867,7 +51896,7 @@
     "developer": "OpenAI",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "terminal-bench-2.0/terminal-bench-2.0": 74.6
+      "terminal-bench-2.0/terminal-bench-2.0": 77.3
     }
   },
   {
@@ -52052,9 +52081,9 @@
       "helm_capabilities/IFEval": 0.929,
       "helm_capabilities/WildBench": 0.854,
       "helm_capabilities/Omni-MATH": 0.72,
-      "livecodebenchpro/Hard Problems": 0.0143,
-      "livecodebenchpro/Medium Problems": 0.2923,
-      "livecodebenchpro/Easy Problems": 0.8571
+      "livecodebenchpro/Hard Problems": 0.014084507042253521,
+      "livecodebenchpro/Medium Problems": 0.30985915492957744,
+      "livecodebenchpro/Easy Problems": 0.8873239436619719
     }
   },
   {
@@ -52198,17 +52227,17 @@
     "developer": "OpenAssistant",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "reward-bench/Score": 0.615,
+      "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/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/Chat": 0.9246,
-      "reward-bench/Chat Hard": 0.3728,
-      "reward-bench/Reasoning": 0.5855,
-      "reward-bench/Prior Sets (0.5 weight)": 0.6801
+      "reward-bench/Ties": 0.047
     }
   },
   {
@@ -52217,17 +52246,17 @@
     "developer": "OpenAssistant",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "reward-bench/Score": 0.6901,
+      "reward-bench/Score": 0.2648,
+      "reward-bench/Chat": 0.8855,
+      "reward-bench/Chat Hard": 0.4868,
+      "reward-bench/Safety": 0.3244,
+      "reward-bench/Reasoning": 0.7752,
+      "reward-bench/Prior Sets (0.5 weight)": 0.6533,
       "reward-bench/Factuality": 0.3179,
       "reward-bench/Precise IF": 0.2625,
       "reward-bench/Math": 0.3934,
-      "reward-bench/Safety": 0.6311,
       "reward-bench/Focus": 0.2707,
-      "reward-bench/Ties": 0.0198,
-      "reward-bench/Chat": 0.8855,
-      "reward-bench/Chat Hard": 0.4868,
-      "reward-bench/Reasoning": 0.7752,
-      "reward-bench/Prior Sets (0.5 weight)": 0.6533
+      "reward-bench/Ties": 0.0198
     }
   },
   {
@@ -52250,17 +52279,17 @@
     "developer": "OpenAssistant",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "reward-bench/Score": 0.6126,
+      "reward-bench/Score": 0.32,
+      "reward-bench/Chat": 0.8939,
+      "reward-bench/Chat Hard": 0.4518,
+      "reward-bench/Safety": 0.3667,
+      "reward-bench/Reasoning": 0.3855,
+      "reward-bench/Prior Sets (0.5 weight)": 0.5836,
       "reward-bench/Factuality": 0.3853,
       "reward-bench/Precise IF": 0.2687,
       "reward-bench/Math": 0.5027,
-      "reward-bench/Safety": 0.7338,
       "reward-bench/Focus": 0.2768,
-      "reward-bench/Ties": 0.12,
-      "reward-bench/Chat": 0.8939,
-      "reward-bench/Chat Hard": 0.4518,
-      "reward-bench/Reasoning": 0.3855,
-      "reward-bench/Prior Sets (0.5 weight)": 0.5836
+      "reward-bench/Ties": 0.12
     }
   },
   {
@@ -52283,17 +52312,17 @@
     "developer": "openbmb",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "reward-bench/Score": 0.8159,
+      "reward-bench/Score": 0.5806,
+      "reward-bench/Chat": 0.9804,
+      "reward-bench/Chat Hard": 0.6557,
+      "reward-bench/Safety": 0.6267,
+      "reward-bench/Reasoning": 0.8633,
+      "reward-bench/Prior Sets (0.5 weight)": 0.7172,
       "reward-bench/Factuality": 0.6,
       "reward-bench/Precise IF": 0.3438,
       "reward-bench/Math": 0.5683,
-      "reward-bench/Safety": 0.8135,
       "reward-bench/Focus": 0.7475,
-      "reward-bench/Ties": 0.5972,
-      "reward-bench/Chat": 0.9804,
-      "reward-bench/Chat Hard": 0.6557,
-      "reward-bench/Reasoning": 0.8633,
-      "reward-bench/Prior Sets (0.5 weight)": 0.7172
+      "reward-bench/Ties": 0.5972
     }
   },
   {
@@ -52330,17 +52359,17 @@
     "developer": "openbmb",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "reward-bench/Score": 0.6903,
+      "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/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/Chat": 0.9637,
-      "reward-bench/Chat Hard": 0.5548,
-      "reward-bench/Reasoning": 0.6244,
-      "reward-bench/Prior Sets (0.5 weight)": 0.7294
+      "reward-bench/Ties": 0.3036
     }
   },
   {
@@ -53820,17 +53849,17 @@
     "developer": "PKU-Alignment",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "reward-bench/Score": 0.4727,
+      "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/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/Chat": 0.8184,
-      "reward-bench/Chat Hard": 0.2873,
-      "reward-bench/Reasoning": 0.346,
-      "reward-bench/Prior Sets (0.5 weight)": 0.5993
+      "reward-bench/Ties": -0.01
     }
   },
   {
@@ -54143,11 +54172,11 @@
     "evaluator_relationship": null,
     "benchmark_scores": {
       "hfopenllm_v2/IFEval": 0.1757,
-      "hfopenllm_v2/BBH": 0.276,
+      "hfopenllm_v2/BBH": 0.274,
       "hfopenllm_v2/MATH Level 5": 0.0,
-      "hfopenllm_v2/GPQA": 0.2534,
-      "hfopenllm_v2/MUSR": 0.3339,
-      "hfopenllm_v2/MMLU-PRO": 0.1123
+      "hfopenllm_v2/GPQA": 0.25,
+      "hfopenllm_v2/MUSR": 0.3753,
+      "hfopenllm_v2/MMLU-PRO": 0.112
     }
   },
   {
@@ -54954,12 +54983,12 @@
     "developer": "prithivMLmods",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "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
+      "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
     }
   },
   {
@@ -56562,12 +56591,12 @@
     "developer": "qingy2019",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "hfopenllm_v2/IFEval": 0.2401,
-      "hfopenllm_v2/BBH": 0.4622,
-      "hfopenllm_v2/MATH Level 5": 0.0725,
-      "hfopenllm_v2/GPQA": 0.2609,
-      "hfopenllm_v2/MUSR": 0.3703,
-      "hfopenllm_v2/MMLU-PRO": 0.2379
+      "hfopenllm_v2/IFEval": 0.2358,
+      "hfopenllm_v2/BBH": 0.4612,
+      "hfopenllm_v2/MATH Level 5": 0.0642,
+      "hfopenllm_v2/GPQA": 0.2576,
+      "hfopenllm_v2/MUSR": 0.3717,
+      "hfopenllm_v2/MMLU-PRO": 0.2382
     }
   },
   {
@@ -56576,12 +56605,12 @@
     "developer": "qingy2019",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "hfopenllm_v2/IFEval": 0.6066,
-      "hfopenllm_v2/BBH": 0.635,
-      "hfopenllm_v2/MATH Level 5": 0.3716,
-      "hfopenllm_v2/GPQA": 0.3725,
+      "hfopenllm_v2/IFEval": 0.6005,
+      "hfopenllm_v2/BBH": 0.6356,
+      "hfopenllm_v2/MATH Level 5": 0.2764,
+      "hfopenllm_v2/GPQA": 0.3691,
       "hfopenllm_v2/MUSR": 0.4757,
-      "hfopenllm_v2/MMLU-PRO": 0.5331
+      "hfopenllm_v2/MMLU-PRO": 0.5339
     }
   },
   {
@@ -57514,12 +57543,12 @@
     "developer": "Quazim0t0",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "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
+      "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
     }
   },
   {
@@ -59020,12 +59049,12 @@
     "developer": "Qwen",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "hfopenllm_v2/IFEval": 0.6101,
-      "hfopenllm_v2/BBH": 0.5008,
-      "hfopenllm_v2/MATH Level 5": 0.3716,
-      "hfopenllm_v2/GPQA": 0.2919,
-      "hfopenllm_v2/MUSR": 0.4073,
-      "hfopenllm_v2/MMLU-PRO": 0.3352
+      "hfopenllm_v2/IFEval": 0.6147,
+      "hfopenllm_v2/BBH": 0.4999,
+      "hfopenllm_v2/MATH Level 5": 0.031,
+      "hfopenllm_v2/GPQA": 0.2936,
+      "hfopenllm_v2/MUSR": 0.4099,
+      "hfopenllm_v2/MMLU-PRO": 0.3354
     }
   },
   {
@@ -59371,17 +59400,17 @@
     "developer": "Ray2333",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "reward-bench/Score": 0.589,
-      "reward-bench/Chat": 0.9832,
-      "reward-bench/Chat Hard": 0.6842,
-      "reward-bench/Safety": 0.7222,
-      "reward-bench/Reasoning": 0.9133,
-      "reward-bench/Prior Sets (0.5 weight)": 0.7209,
+      "reward-bench/Score": 0.8464,
       "reward-bench/Factuality": 0.5874,
       "reward-bench/Precise IF": 0.3875,
       "reward-bench/Math": 0.5902,
+      "reward-bench/Safety": 0.8676,
       "reward-bench/Focus": 0.6727,
-      "reward-bench/Ties": 0.5743
+      "reward-bench/Ties": 0.5743,
+      "reward-bench/Chat": 0.9832,
+      "reward-bench/Chat Hard": 0.6842,
+      "reward-bench/Reasoning": 0.9133,
+      "reward-bench/Prior Sets (0.5 weight)": 0.7209
     }
   },
   {
@@ -59408,17 +59437,17 @@
     "developer": "Ray2333",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "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/Score": 0.8542,
       "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/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
     }
   },
   {
@@ -60129,12 +60158,12 @@
     "developer": "rombodawg",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "hfopenllm_v2/IFEval": 0.2595,
-      "hfopenllm_v2/BBH": 0.3884,
-      "hfopenllm_v2/MATH Level 5": 0.0914,
-      "hfopenllm_v2/GPQA": 0.2743,
+      "hfopenllm_v2/IFEval": 0.2566,
+      "hfopenllm_v2/BBH": 0.39,
+      "hfopenllm_v2/MATH Level 5": 0.1208,
+      "hfopenllm_v2/GPQA": 0.2626,
       "hfopenllm_v2/MUSR": 0.3991,
-      "hfopenllm_v2/MMLU-PRO": 0.2719
+      "hfopenllm_v2/MMLU-PRO": 0.2741
     }
   },
   {
@@ -62463,17 +62492,17 @@
     "developer": "sfairXC",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "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/Score": 0.8338,
       "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/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
     }
   },
   {
@@ -62552,16 +62581,16 @@
     "developer": "ShikaiChen",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "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/Score": 0.9499,
       "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/Ties": 0.7633,
+      "reward-bench/Chat": 0.9637,
+      "reward-bench/Chat Hard": 0.9079,
+      "reward-bench/Reasoning": 0.9903
     }
   },
   {
@@ -63278,16 +63307,16 @@
       "hfopenllm_v2/GPQA": 0.344,
       "hfopenllm_v2/MUSR": 0.4231,
       "hfopenllm_v2/MMLU-PRO": 0.4103,
-      "reward-bench/Score": 0.9426,
+      "reward-bench/Score": 0.7531,
+      "reward-bench/Chat": 0.9609,
+      "reward-bench/Chat Hard": 0.8991,
+      "reward-bench/Safety": 0.9689,
+      "reward-bench/Reasoning": 0.9807,
       "reward-bench/Factuality": 0.7674,
       "reward-bench/Precise IF": 0.375,
       "reward-bench/Math": 0.6721,
-      "reward-bench/Safety": 0.9297,
       "reward-bench/Focus": 0.9172,
-      "reward-bench/Ties": 0.8182,
-      "reward-bench/Chat": 0.9609,
-      "reward-bench/Chat Hard": 0.8991,
-      "reward-bench/Reasoning": 0.9807
+      "reward-bench/Ties": 0.8182
     }
   },
   {
@@ -63296,16 +63325,16 @@
     "developer": "Skywork",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "reward-bench/Score": 0.9252,
+      "reward-bench/Score": 0.7314,
+      "reward-bench/Chat": 0.9581,
+      "reward-bench/Chat Hard": 0.8728,
+      "reward-bench/Safety": 0.9333,
+      "reward-bench/Reasoning": 0.962,
       "reward-bench/Factuality": 0.6989,
       "reward-bench/Precise IF": 0.425,
       "reward-bench/Math": 0.6284,
-      "reward-bench/Safety": 0.9081,
       "reward-bench/Focus": 0.9616,
-      "reward-bench/Ties": 0.741,
-      "reward-bench/Chat": 0.9581,
-      "reward-bench/Chat Hard": 0.8728,
-      "reward-bench/Reasoning": 0.962
+      "reward-bench/Ties": 0.741
     }
   },
   {
@@ -66755,12 +66784,12 @@
     "developer": "tanliboy",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "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
+      "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
     }
   },
   {
@@ -70971,12 +71000,12 @@
     "developer": "ValiantLabs",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "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
+      "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
     }
   },
   {
@@ -71027,12 +71056,12 @@
     "developer": "ValiantLabs",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "hfopenllm_v2/IFEval": 0.2678,
-      "hfopenllm_v2/BBH": 0.4429,
-      "hfopenllm_v2/MATH Level 5": 0.0521,
-      "hfopenllm_v2/GPQA": 0.302,
-      "hfopenllm_v2/MUSR": 0.3959,
-      "hfopenllm_v2/MMLU-PRO": 0.2927
+      "hfopenllm_v2/IFEval": 0.6496,
+      "hfopenllm_v2/BBH": 0.4774,
+      "hfopenllm_v2/MATH Level 5": 0.0566,
+      "hfopenllm_v2/GPQA": 0.3104,
+      "hfopenllm_v2/MUSR": 0.3909,
+      "hfopenllm_v2/MMLU-PRO": 0.3382
     }
   },
   {
@@ -72365,7 +72394,7 @@
     "developer": "xAI",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "terminal-bench-2.0/terminal-bench-2.0": 23.1
+      "terminal-bench-2.0/terminal-bench-2.0": 25.4
     }
   },
   {
@@ -73018,12 +73047,12 @@
     "developer": "yam-peleg",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "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
+      "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
     }
   },
   {
@@ -73111,12 +73140,12 @@
     "developer": "ycros",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "hfopenllm_v2/IFEval": 0.5994,
-      "hfopenllm_v2/BBH": 0.5159,
-      "hfopenllm_v2/MATH Level 5": 0.0785,
-      "hfopenllm_v2/GPQA": 0.3045,
-      "hfopenllm_v2/MUSR": 0.4203,
-      "hfopenllm_v2/MMLU-PRO": 0.3473
+      "hfopenllm_v2/IFEval": 0.6262,
+      "hfopenllm_v2/BBH": 0.5142,
+      "hfopenllm_v2/MATH Level 5": 0.0937,
+      "hfopenllm_v2/GPQA": 0.3079,
+      "hfopenllm_v2/MUSR": 0.4138,
+      "hfopenllm_v2/MMLU-PRO": 0.3481
     }
   },
   {
@@ -75520,7 +75549,7 @@
     "developer": "Z-AI",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "terminal-bench-2.0/terminal-bench-2.0": 33.4
+      "terminal-bench-2.0/terminal-bench-2.0": 33.3
     }
   },
   {
diff --git a/data/models/adriszmar_qaimath-qwen2.5-7b-ties.json b/data/models/adriszmar_qaimath-qwen2.5-7b-ties.json
index a8a69697e53329e56da6b7741229b84b4f2eeb85..776a7c662b5afb276bf059bb90896cee5cd968ec 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": "float16",
+      "precision": "bfloat16",
       "architecture": "Qwen2ForCausalLM",
       "params_billions": "7.616"
     }
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1746
+            "score": 0.1685
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3126
+            "score": 0.3124
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0
+            "score": 0.0015
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.245
+            "score": 0.2492
           }
         },
         {
@@ -116,7 +116,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4096
+            "score": 0.3963
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1087
+            "score": 0.1066
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1685
+            "score": 0.1746
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3124
+            "score": 0.3126
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0015
+            "score": 0.0
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2492
+            "score": 0.245
           }
         },
         {
@@ -246,7 +246,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3963
+            "score": 0.4096
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1066
+            "score": 0.1087
           }
         }
       ],
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 036d2144a17c2773cc45b3fcdc429ec4c85d29b1..e1ac41e4bb97f41e9784803c588108ddfee89905 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
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6905
+            "score": 0.6895
           },
           "source_data": {
             "dataset_name": "RewardBench",
@@ -152,7 +152,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9441
+            "score": 0.9385
           },
           "source_data": {
             "dataset_name": "RewardBench",
@@ -170,7 +170,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3596
+            "score": 0.3706
           },
           "source_data": {
             "dataset_name": "RewardBench",
@@ -188,7 +188,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7676
+            "score": 0.7595
           },
           "source_data": {
             "dataset_name": "RewardBench",
@@ -230,7 +230,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7004
+            "score": 0.7019
           },
           "source_data": {
             "dataset_name": "RewardBench",
@@ -248,7 +248,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9413
+            "score": 0.9497
           },
           "source_data": {
             "dataset_name": "RewardBench",
@@ -266,7 +266,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3882
+            "score": 0.375
           },
           "source_data": {
             "dataset_name": "RewardBench",
@@ -284,7 +284,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7716
+            "score": 0.7811
           },
           "source_data": {
             "dataset_name": "RewardBench",
@@ -326,7 +326,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6945
+            "score": 0.6905
           },
           "source_data": {
             "dataset_name": "RewardBench",
@@ -344,7 +344,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9385
+            "score": 0.9441
           },
           "source_data": {
             "dataset_name": "RewardBench",
@@ -362,7 +362,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3706
+            "score": 0.3596
           },
           "source_data": {
             "dataset_name": "RewardBench",
@@ -380,7 +380,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7743
+            "score": 0.7676
           },
           "source_data": {
             "dataset_name": "RewardBench",
@@ -518,7 +518,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7008
+            "score": 0.6924
           },
           "source_data": {
             "dataset_name": "RewardBench",
@@ -536,7 +536,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9385
+            "score": 0.9441
           },
           "source_data": {
             "dataset_name": "RewardBench",
@@ -554,7 +554,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3882
+            "score": 0.3575
           },
           "source_data": {
             "dataset_name": "RewardBench",
@@ -614,7 +614,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7019
+            "score": 0.6945
           },
           "source_data": {
             "dataset_name": "RewardBench",
@@ -632,7 +632,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9497
+            "score": 0.9385
           },
           "source_data": {
             "dataset_name": "RewardBench",
@@ -650,7 +650,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.375
+            "score": 0.3706
           },
           "source_data": {
             "dataset_name": "RewardBench",
@@ -668,7 +668,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7811
+            "score": 0.7743
           },
           "source_data": {
             "dataset_name": "RewardBench",
@@ -710,7 +710,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6924
+            "score": 0.7004
           },
           "source_data": {
             "dataset_name": "RewardBench",
@@ -728,7 +728,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9441
+            "score": 0.9413
           },
           "source_data": {
             "dataset_name": "RewardBench",
@@ -746,7 +746,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3575
+            "score": 0.3882
           },
           "source_data": {
             "dataset_name": "RewardBench",
@@ -764,7 +764,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7757
+            "score": 0.7716
           },
           "source_data": {
             "dataset_name": "RewardBench",
@@ -806,7 +806,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6895
+            "score": 0.7008
           },
           "source_data": {
             "dataset_name": "RewardBench",
@@ -842,7 +842,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3706
+            "score": 0.3882
           },
           "source_data": {
             "dataset_name": "RewardBench",
@@ -860,7 +860,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7595
+            "score": 0.7757
           },
           "source_data": {
             "dataset_name": "RewardBench",
diff --git a/data/models/alibaba_qwen-3-coder-480b.json b/data/models/alibaba_qwen-3-coder-480b.json
index 5529ecfec8fec832ba0fc670045bbad34374bc66..f598d15a400b5ed438e43880c6cab3a3248e3641 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": "Dakou Agent",
-      "agent_organization": "iflow"
+      "agent_name": "OpenHands",
+      "agent_organization": "OpenHands"
     }
   },
   "evaluations": [
     {
-      "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",
@@ -34,7 +34,7 @@
               "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,
@@ -43,7 +43,7 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 27.2,
+            "score": 25.4,
             "uncertainty": {
               "standard_error": {
                 "value": 2.6
@@ -53,7 +53,7 @@
           },
           "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": [
                   {
@@ -70,7 +70,7 @@
       "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": [
               {
@@ -84,7 +84,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/terminus-2__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",
@@ -108,7 +108,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-11-01",
+          "evaluation_timestamp": "2025-12-28",
           "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": 23.9,
+            "score": 27.2,
             "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 \"Terminus 2\" -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": [
                   {
@@ -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 \"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/openhands__qwen-3-coder-480b/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/terminus-2__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": "2025-11-02",
+          "evaluation_timestamp": "2025-11-01",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -191,17 +191,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 25.4,
+            "score": 23.9,
             "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 \"OpenHands\" -m \"Qwen 3 Coder 480B\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -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 \"OpenHands\" -m \"Qwen 3 Coder 480B\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"Qwen 3 Coder 480B\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
diff --git a/data/models/allenai_llama-3.1-70b-instruct-rm-rb2.json b/data/models/allenai_llama-3.1-70b-instruct-rm-rb2.json
index 3edb4e861c9c885f1d8b857f90568f09968d9fbc..6b82bed55df1bdb62067f41e1f2f588c7fd5e772 100644
--- a/data/models/allenai_llama-3.1-70b-instruct-rm-rb2.json
+++ b/data/models/allenai_llama-3.1-70b-instruct-rm-rb2.json
@@ -9,10 +9,10 @@
   },
   "evaluations": [
     {
-      "evaluation_id": "reward-bench/allenai_Llama-3.1-70B-Instruct-RM-RB2/1766412838.146816",
+      "evaluation_id": "reward-bench-2/allenai_Llama-3.1-70B-Instruct-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": 0.9021
+            "score": 0.7606
           },
           "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": 0.8126
           },
           "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": 0.8355
+            "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": 0.6995
+          },
+          "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": 0.9095
+            "score": 0.8844
           },
           "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": 0.8969
+            "score": 0.8646
           },
           "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": 0.8835
           },
           "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-3.1-70B-Instruct-RM-RB2/1766412838.146816",
+      "evaluation_id": "reward-bench/allenai_Llama-3.1-70B-Instruct-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": 0.7606
-          },
-          "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": 0.8126
+            "score": 0.9021
           },
           "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": 0.9665
           },
           "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": 0.6995
+            "score": 0.8355
           },
           "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": 0.8844
+            "score": 0.9095
           },
           "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": 0.8646
+            "score": 0.8969
           },
           "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": 0.8835
+            "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-3-8b-dpo-rm-rb2.json b/data/models/allenai_llama-3.1-tulu-3-8b-dpo-rm-rb2.json
index 408cdcea425aaae910c976c1f57587d29fcf9c63..52eed39924ec31b815aba5be343333e3d61411ae 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/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",
@@ -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": 0.8431
+            "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"
           }
         }
       ],
@@ -141,10 +159,10 @@
       "generation_config": null
     },
     {
-      "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",
@@ -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": 0.687
-          },
-          "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"
           }
         }
       ],
diff --git a/data/models/allenai_llama-3.1-tulu-3-8b-sft-rm-rb2.json b/data/models/allenai_llama-3.1-tulu-3-8b-sft-rm-rb2.json
index 84c4146c17907f25ce74864c179dc0e7dcd19fbd..e5b15dac5cb2f4285962219bbf6cd6008c5fe41a 100644
--- a/data/models/allenai_llama-3.1-tulu-3-8b-sft-rm-rb2.json
+++ b/data/models/allenai_llama-3.1-tulu-3-8b-sft-rm-rb2.json
@@ -9,10 +9,10 @@
   },
   "evaluations": [
     {
-      "evaluation_id": "reward-bench-2/allenai_Llama-3.1-Tulu-3-8B-SFT-RM-RB2/1766412838.146816",
+      "evaluation_id": "reward-bench/allenai_Llama-3.1-Tulu-3-8B-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": 0.6821
-          },
-          "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": 0.7326
+            "score": 0.8551
           },
           "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": 0.9497
           },
           "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": "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": 0.7917
           },
           "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": 0.8978
+            "score": 0.8784
           },
           "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": 0.8889
+            "score": 0.8005
           },
           "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": 0.6063
+            "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-SFT-RM-RB2/1766412838.146816",
+      "evaluation_id": "reward-bench-2/allenai_Llama-3.1-Tulu-3-8B-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": 0.8551
+            "score": 0.6821
           },
           "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": 0.9497
+            "score": 0.7326
           },
           "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": 0.7917
+            "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": 0.8784
+            "score": 0.8978
           },
           "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": 0.8005
+            "score": 0.8889
           },
           "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": 0.6063
           },
           "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"
           }
         }
       ],
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 7de1c9431728784c04f1c32781631febc2ed7e32..53350f20b1f74556a0af6a9aa87ed77d181deaec 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": "bfloat16",
+      "precision": "float16",
       "architecture": "LlamaForCausalLM",
       "params_billions": "8.03"
     }
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.8267
+            "score": 0.8255
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.405
+            "score": 0.4061
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1964
+            "score": 0.2115
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2987
+            "score": 0.297
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2827
+            "score": 0.2821
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.8255
+            "score": 0.8267
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4061
+            "score": 0.405
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2115
+            "score": 0.1964
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.297
+            "score": 0.2987
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2821
+            "score": 0.2827
           }
         }
       ],
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
new file mode 100644
index 0000000000000000000000000000000000000000..cedfd398cf32e477ed09f75303d207e32a02614e
--- /dev/null
+++ b/data/models/allenai_open_instruct_dev-rm_1e-6_2_30pctflipped__1__1743325094.json
@@ -0,0 +1,162 @@
+{
+  "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/amd_amd-llama-135m.json b/data/models/amd_amd-llama-135m.json
index dfdcf8e7a431ddc8bdf51b6aa797b81cf0f89c9e..a445333e3dd0495a4c3e2fddf3e92a96b288f85c 100644
--- a/data/models/amd_amd-llama-135m.json
+++ b/data/models/amd_amd-llama-135m.json
@@ -5,9 +5,9 @@
     "developer": "amd",
     "inference_platform": "unknown",
     "additional_details": {
-      "precision": "bfloat16",
+      "precision": "float16",
       "architecture": "LlamaForCausalLM",
-      "params_billions": "0.134"
+      "params_billions": "0.135"
     }
   },
   "evaluations": [
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1918
+            "score": 0.1842
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2969
+            "score": 0.2974
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0076
+            "score": 0.0053
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2584
+            "score": 0.2525
           }
         },
         {
@@ -116,7 +116,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3846
+            "score": 0.378
           }
         },
         {
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1842
+            "score": 0.1918
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2974
+            "score": 0.2969
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0053
+            "score": 0.0076
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2525
+            "score": 0.2584
           }
         },
         {
@@ -246,7 +246,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.378
+            "score": 0.3846
           }
         },
         {
diff --git a/data/models/anthropic_claude-3-5-haiku-20241022.json b/data/models/anthropic_claude-3-5-haiku-20241022.json
index 9edb0c7484cd3b1eab61fa90716227281f955253..97ab32cadbb5e110dfa409cbea1ee9b8c38d6850 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-20241022/1773936583.743359",
-      "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",
@@ -525,8 +525,8 @@
       "generation_config": null
     },
     {
-      "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",
diff --git a/data/models/anthropic_claude-3-5-sonnet-20240620.json b/data/models/anthropic_claude-3-5-sonnet-20240620.json
index db73167f2ee9a0684ae3211521c8476cfd4cde1f..3864d6fb81d70dd8f8c2977e067122577576cb3c 100644
--- a/data/models/anthropic_claude-3-5-sonnet-20240620.json
+++ b/data/models/anthropic_claude-3-5-sonnet-20240620.json
@@ -1903,10 +1903,10 @@
       }
     },
     {
-      "evaluation_id": "reward-bench/Anthropic_claude-3-5-sonnet-20240620/1766412838.146816",
+      "evaluation_id": "reward-bench-2/anthropic_claude-3-5-sonnet-20240620/1766412838.146816",
       "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": 0.8417
+            "score": 0.6466
           },
           "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": 0.5284
           },
           "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": 0.7401
+            "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": "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": 0.5683
           },
           "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": 0.8469
+            "score": 0.8519
           },
           "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-3-5-sonnet-20240620/1766412838.146816",
-      "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": 0.6466
+            "score": 0.8697
           },
           "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": 0.5284
+            "score": 0.674
           },
           "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-3-5-sonnet-20240620/1766412838.146816",
+      "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": 0.3875
+            "score": 0.8417
           },
           "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": 0.5683
+            "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": 0.8519
+            "score": 0.7401
           },
           "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": 0.8697
+            "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": 0.674
+            "score": 0.8469
           },
           "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-haiku-20240307.json b/data/models/anthropic_claude-3-haiku-20240307.json
index 4a2b563f634d87e24d77a5003bd4befff9181e63..52bb9959dd5613be4f3fe143bd6f01f97e2632c2 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-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",
@@ -1925,127 +1925,109 @@
         {
           "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"
           }
         }
       ],
@@ -2053,10 +2035,10 @@
       "generation_config": null
     },
     {
-      "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",
@@ -2075,109 +2057,127 @@
         {
           "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"
           }
         }
       ],
diff --git a/data/models/anthropic_claude-3-opus-20240229.json b/data/models/anthropic_claude-3-opus-20240229.json
index 150503f1a5f91571d10a33f8965d4bd84f3ccf46..8f8b70dd804fcbb225ceb8111209d93e20e8bd0b 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-2/anthropic_claude-3-opus-20240229/1766412838.146816",
+      "evaluation_id": "reward-bench/Anthropic_claude-3-opus-20240229/1766412838.146816",
       "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",
@@ -1925,104 +1925,128 @@
         {
           "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": 0.5744
+            "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": "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": 0.5389
+            "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": "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": 0.6031
           },
           "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": "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": 0.5137
+            "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": "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": 0.8378
+            "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"
           }
-        },
+        }
+      ],
+      "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": "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": 0.6646
+            "score": 0.5744
           },
           "source_data": {
             "dataset_name": "RewardBench 2",
@@ -2031,135 +2055,111 @@
           }
         },
         {
-          "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": 0.5601
+            "score": 0.5389
           },
           "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": "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": 0.8008
+            "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": 0.9469
+            "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": "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": 0.6031
+            "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"
           }
         },
         {
-          "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": 0.8662
+            "score": 0.6646
           },
           "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": 0.7868
+            "score": 0.5601
           },
           "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/anthropic_claude-haiku-4.5.json b/data/models/anthropic_claude-haiku-4.5.json
index a44b80f840579ff8c5f06292af8a76c394e19084..0030689870b1d61c70e99ee0cdff0afc1d0e9bf2 100644
--- a/data/models/anthropic_claude-haiku-4.5.json
+++ b/data/models/anthropic_claude-haiku-4.5.json
@@ -4,13 +4,13 @@
     "id": "anthropic/claude-haiku-4.5",
     "developer": "Anthropic",
     "additional_details": {
-      "agent_name": "Mini-SWE-Agent",
-      "agent_organization": "Princeton"
+      "agent_name": "Terminus 2",
+      "agent_organization": "Terminal Bench"
     }
   },
   "evaluations": [
     {
-      "evaluation_id": "terminal-bench-2.0/mini-swe-agent__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",
@@ -34,7 +34,7 @@
               "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,
@@ -43,17 +43,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 29.8,
+            "score": 28.3,
             "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 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": [
                   {
@@ -70,7 +70,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Mini-SWE-Agent\" -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": [
               {
@@ -84,7 +84,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/goose__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",
@@ -108,7 +108,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-12-11",
+          "evaluation_timestamp": "2025-11-04",
           "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": 35.5,
+            "score": 27.5,
             "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 \"Goose\" -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": [
                   {
@@ -144,7 +144,7 @@
       "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 \"Claude Code\" -m \"Claude Haiku 4.5\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -158,7 +158,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/openhands__claude-haiku-4.5/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/mini-swe-agent__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": "2025-11-02",
+          "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": 13.9,
+            "score": 29.8,
             "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 \"Claude Haiku 4.5\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Mini-SWE-Agent\" -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 \"OpenHands\" -m \"Claude Haiku 4.5\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Mini-SWE-Agent\" -m \"Claude Haiku 4.5\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -232,7 +232,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/terminus-2__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",
@@ -256,7 +256,7 @@
               "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,
@@ -265,17 +265,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 28.3,
+            "score": 13.9,
             "uncertainty": {
               "standard_error": {
-                "value": 2.9
+                "value": 2.7
               },
               "num_samples": 435
             }
           },
           "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 \"OpenHands\" -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 \"Terminus 2\" -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": [
               {
@@ -306,7 +306,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/claude-code__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",
@@ -330,7 +330,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-11-04",
+          "evaluation_timestamp": "2025-12-11",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -339,17 +339,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 27.5,
+            "score": 35.5,
             "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 \"Claude Code\" -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": [
                   {
@@ -366,7 +366,7 @@
       "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 \"Goose\" -m \"Claude Haiku 4.5\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
diff --git a/data/models/anthropic_claude-opus-4-1-20250805.json b/data/models/anthropic_claude-opus-4-1-20250805.json
index d8d76da387da094a25675bc9e4c49b25e5dc839b..97af67f7a9590f836aeb06cb6e8ac5e127131091 100644
--- a/data/models/anthropic_claude-opus-4-1-20250805.json
+++ b/data/models/anthropic_claude-opus-4-1-20250805.json
@@ -10,8 +10,8 @@
   },
   "evaluations": [
     {
-      "evaluation_id": "global-mmlu-lite/anthropic_claude-opus-4-1-20250805/1773936583.743359",
-      "retrieved_timestamp": "1773936583.743359",
+      "evaluation_id": "global-mmlu-lite/anthropic_claude-opus-4-1-20250805/1773936496.366405",
+      "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/anthropic_claude-opus-4-1-20250805/1773936496.366405",
-      "retrieved_timestamp": "1773936496.366405",
+      "evaluation_id": "global-mmlu-lite/anthropic_claude-opus-4-1-20250805/1773936583.743359",
+      "retrieved_timestamp": "1773936583.743359",
       "source_metadata": {
         "source_name": "Global MMLU Lite Leaderboard",
         "source_type": "documentation",
diff --git a/data/models/anthropic_claude-opus-4-5.json b/data/models/anthropic_claude-opus-4-5.json
index e58ae243e6675ffbe5718b2cd53dbb80e8f1ba8b..0cd69b8f1e682224797162bd821dc65c4792b021 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": "OpenAI Solo",
-      "agent_framework": "openai_solo"
+      "agent_name": "LiteLLM Tool Calling with Shortlisting",
+      "agent_framework": "tool_calling_with_shortlisting"
     }
   },
   "evaluations": [
     {
-      "evaluation_id": "appworld/test_normal/openai-solo__anthropic_claude-opus-4-5/1774263615.0201504",
+      "evaluation_id": "browsecompplus/litellm-tool-calling-with-shortlisting__anthropic_claude-opus-4-5/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -23,42 +23,42 @@
         "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": 0.68,
+            "score": 0.49,
             "uncertainty": {
               "num_samples": 100
             },
             "details": {
-              "average_agent_cost": "22.76",
-              "total_run_cost": "2276.48",
-              "average_steps": "47.65",
-              "percent_finished": "0.77"
+              "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": "OpenAI Solo",
-                  "agent_framework": "openai_solo"
+                  "agent_name": "LiteLLM Tool Calling with Shortlisting",
+                  "agent_framework": "tool_calling_with_shortlisting"
                 }
               }
             }
@@ -70,15 +70,15 @@
         "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": "appworld/test_normal/claude-code-cli__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",
@@ -110,23 +110,23 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.66,
+            "score": 0.61,
             "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": "11.32",
+              "total_run_cost": "1132.47",
+              "average_steps": "21.99",
+              "percent_finished": "0.83"
             }
           },
           "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__anthropic_claude-opus-4-5/1774263615.0201504",
+      "evaluation_id": "browsecompplus/claude-code-cli__anthropic_claude-opus-4-5/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -159,42 +159,42 @@
         "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": 0.61,
+            "score": 0.5294,
             "uncertainty": {
-              "num_samples": 100
+              "num_samples": 51
             },
             "details": {
-              "average_agent_cost": "11.32",
-              "total_run_cost": "1132.47",
-              "average_steps": "21.99",
-              "percent_finished": "0.83"
+              "average_agent_cost": "11.66",
+              "total_run_cost": "594.68",
+              "average_steps": "31.04",
+              "percent_finished": "0.8431"
             }
           },
           "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"
                 }
               }
             }
@@ -206,8 +206,8 @@
         "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"
             }
           }
         }
@@ -282,7 +282,7 @@
       }
     },
     {
-      "evaluation_id": "appworld/test_normal/smolagents-code__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",
@@ -314,23 +314,23 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7,
+            "score": 0.66,
             "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": "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": "SmolAgents Code",
-                  "agent_framework": "smolagents_code"
+                  "agent_name": "Claude Code CLI",
+                  "agent_framework": "claude_code"
                 }
               }
             }
@@ -342,15 +342,15 @@
         "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": "appworld/test_normal/litellm-tool-calling-with-shortlisting__anthropic_claude-opus-4-5/1774263615.0201504",
+      "evaluation_id": "appworld/test_normal/openai-solo__anthropic_claude-opus-4-5/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -382,23 +382,23 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.64,
+            "score": 0.68,
             "uncertainty": {
               "num_samples": 100
             },
             "details": {
-              "average_agent_cost": "3.43",
-              "total_run_cost": "343.32",
-              "average_steps": "20.06",
-              "percent_finished": "0.82"
+              "average_agent_cost": "22.76",
+              "total_run_cost": "2276.48",
+              "average_steps": "47.65",
+              "percent_finished": "0.77"
             }
           },
           "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"
                 }
               }
             }
@@ -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": "OpenAI Solo",
+              "agent_framework": "openai_solo"
             }
           }
         }
       }
     },
     {
-      "evaluation_id": "browsecompplus/claude-code-cli__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",
@@ -450,23 +450,23 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5294,
+            "score": 0.61,
             "uncertainty": {
-              "num_samples": 51
+              "num_samples": 100
             },
             "details": {
-              "average_agent_cost": "11.66",
-              "total_run_cost": "594.68",
-              "average_steps": "31.04",
-              "percent_finished": "0.8431"
+              "average_agent_cost": "7.59",
+              "total_run_cost": "759.44",
+              "average_steps": "27.18",
+              "percent_finished": "1.0"
             }
           },
           "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"
                 }
               }
             }
@@ -478,15 +478,15 @@
         "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": "browsecompplus/litellm-tool-calling__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",
@@ -499,42 +499,42 @@
         "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": 0.49,
+            "score": 0.7,
             "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": "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": "LiteLLM Tool Calling",
-                  "agent_framework": "tool_calling"
+                  "agent_name": "SmolAgents Code",
+                  "agent_framework": "smolagents_code"
                 }
               }
             }
@@ -546,15 +546,15 @@
         "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": "browsecompplus/litellm-tool-calling-with-shortlisting__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",
@@ -601,8 +601,8 @@
             "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"
                 }
               }
             }
@@ -614,15 +614,15 @@
         "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": "browsecompplus/openai-solo__anthropic_claude-opus-4-5/1774263615.0201504",
+      "evaluation_id": "appworld/test_normal/litellm-tool-calling-with-shortlisting__anthropic_claude-opus-4-5/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -635,42 +635,42 @@
         "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": 0.64,
             "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": "3.43",
+              "total_run_cost": "343.32",
+              "average_steps": "20.06",
+              "percent_finished": "0.82"
             }
           },
           "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"
                 }
               }
             }
@@ -682,15 +682,15 @@
         "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": "swe-bench/smolagents-code__anthropic_claude-opus-4-5/1774263615.0201504",
+      "evaluation_id": "swe-bench/litellm-tool-calling-with-shortlisting__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": 0.65,
+            "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"
             }
           },
@@ -737,8 +737,8 @@
             "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"
                 }
               }
             }
@@ -750,15 +750,15 @@
         "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": "swe-bench/openai-solo__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",
@@ -790,14 +790,14 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.8072,
+            "score": 0.65,
             "uncertainty": {
-              "num_samples": 83
+              "num_samples": 100
             },
             "details": {
-              "average_agent_cost": "2.96",
-              "total_run_cost": "245.78",
-              "average_steps": "34.1",
+              "average_agent_cost": "4.85",
+              "total_run_cost": "485.22",
+              "average_steps": "39.13",
               "percent_finished": "1.0"
             }
           },
@@ -805,8 +805,8 @@
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "OpenAI Solo",
-                  "agent_framework": "openai_solo"
+                  "agent_name": "SmolAgents Code",
+                  "agent_framework": "smolagents_code"
                 }
               }
             }
@@ -818,15 +818,15 @@
         "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/claude-code-cli__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",
@@ -858,14 +858,14 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7423,
+            "score": 0.6061,
             "uncertainty": {
-              "num_samples": 97
+              "num_samples": 99
             },
             "details": {
-              "average_agent_cost": "5.6",
-              "total_run_cost": "543.62",
-              "average_steps": "31.76",
+              "average_agent_cost": "3.97",
+              "total_run_cost": "393.16",
+              "average_steps": "43.44",
               "percent_finished": "1.0"
             }
           },
@@ -873,8 +873,8 @@
             "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"
                 }
               }
             }
@@ -886,15 +886,15 @@
         "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__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",
@@ -926,14 +926,14 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6061,
+            "score": 0.7423,
             "uncertainty": {
-              "num_samples": 99
+              "num_samples": 97
             },
             "details": {
-              "average_agent_cost": "3.97",
-              "total_run_cost": "393.16",
-              "average_steps": "43.44",
+              "average_agent_cost": "5.6",
+              "total_run_cost": "543.62",
+              "average_steps": "31.76",
               "percent_finished": "1.0"
             }
           },
@@ -941,8 +941,8 @@
             "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"
                 }
               }
             }
@@ -954,15 +954,15 @@
         "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": "swe-bench/litellm-tool-calling-with-shortlisting__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",
@@ -975,33 +975,33 @@
         "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": 0.6061,
+            "score": 0.74,
             "uncertainty": {
-              "num_samples": 99
+              "num_samples": 50
             },
             "details": {
-              "average_agent_cost": "3.97",
-              "total_run_cost": "393.16",
-              "average_steps": "43.44",
+              "average_agent_cost": "0.72",
+              "total_run_cost": "36.55",
+              "average_steps": "12.22",
               "percent_finished": "1.0"
             }
           },
@@ -1009,8 +1009,8 @@
             "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"
                 }
               }
             }
@@ -1022,15 +1022,15 @@
         "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__anthropic_claude-opus-4-5/1774263615.0201504",
+      "evaluation_id": "tau-bench-2/airline/claude-code-cli__anthropic_claude-opus-4-5/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -1067,9 +1067,9 @@
               "num_samples": 50
             },
             "details": {
-              "average_agent_cost": "0.47",
-              "total_run_cost": "24.23",
-              "average_steps": "10.0",
+              "average_agent_cost": "1.3",
+              "total_run_cost": "65.66",
+              "average_steps": "11.5",
               "percent_finished": "1.0"
             }
           },
@@ -1077,8 +1077,8 @@
             "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"
                 }
               }
             }
@@ -1090,15 +1090,15 @@
         "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/claude-code-cli__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",
@@ -1135,9 +1135,9 @@
               "num_samples": 50
             },
             "details": {
-              "average_agent_cost": "1.3",
-              "total_run_cost": "65.66",
-              "average_steps": "11.5",
+              "average_agent_cost": "0.47",
+              "total_run_cost": "24.23",
+              "average_steps": "10.0",
               "percent_finished": "1.0"
             }
           },
@@ -1145,8 +1145,8 @@
             "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"
                 }
               }
             }
@@ -1158,15 +1158,15 @@
         "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__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",
@@ -1198,14 +1198,14 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.74,
+            "score": 0.72,
             "uncertainty": {
               "num_samples": 50
             },
             "details": {
-              "average_agent_cost": "0.72",
-              "total_run_cost": "36.55",
-              "average_steps": "12.22",
+              "average_agent_cost": "0.78",
+              "total_run_cost": "39.67",
+              "average_steps": "11.88",
               "percent_finished": "1.0"
             }
           },
@@ -1213,8 +1213,8 @@
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "OpenAI Solo",
-                  "agent_framework": "openai_solo"
+                  "agent_name": "SmolAgents Code",
+                  "agent_framework": "smolagents_code"
                 }
               }
             }
@@ -1226,15 +1226,15 @@
         "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": "tau-bench-2/airline/litellm-tool-calling-with-shortlisting__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",
@@ -1247,33 +1247,33 @@
         "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": 0.66,
+            "score": 0.8072,
             "uncertainty": {
-              "num_samples": 50
+              "num_samples": 83
             },
             "details": {
-              "average_agent_cost": "0.47",
-              "total_run_cost": "24.23",
-              "average_steps": "10.0",
+              "average_agent_cost": "2.96",
+              "total_run_cost": "245.78",
+              "average_steps": "34.1",
               "percent_finished": "1.0"
             }
           },
@@ -1281,8 +1281,8 @@
             "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"
                 }
               }
             }
@@ -1294,15 +1294,15 @@
         "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/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",
@@ -1334,14 +1334,14 @@
             "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"
             }
           },
@@ -1349,8 +1349,8 @@
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "SmolAgents Code",
-                  "agent_framework": "smolagents_code"
+                  "agent_name": "LiteLLM Tool Calling",
+                  "agent_framework": "tool_calling"
                 }
               }
             }
@@ -1362,8 +1362,8 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "SmolAgents Code",
-              "agent_framework": "smolagents_code"
+              "agent_name": "LiteLLM Tool Calling",
+              "agent_framework": "tool_calling"
             }
           }
         }
@@ -1438,7 +1438,7 @@
       }
     },
     {
-      "evaluation_id": "tau-bench-2/retail/claude-code-cli__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",
@@ -1470,14 +1470,14 @@
             "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": "0.47",
+              "total_run_cost": "48.01",
+              "average_steps": "11.33",
               "percent_finished": "1.0"
             }
           },
@@ -1485,8 +1485,8 @@
             "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"
                 }
               }
             }
@@ -1498,15 +1498,15 @@
         "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/retail/litellm-tool-calling-with-shortlisting__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",
@@ -1538,14 +1538,14 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.78,
+            "score": 0.83,
             "uncertainty": {
               "num_samples": 100
             },
             "details": {
-              "average_agent_cost": "0.47",
-              "total_run_cost": "48.01",
-              "average_steps": "11.33",
+              "average_agent_cost": "1.6",
+              "total_run_cost": "161.14",
+              "average_steps": "12.54",
               "percent_finished": "1.0"
             }
           },
@@ -1553,8 +1553,8 @@
             "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"
                 }
               }
             }
@@ -1566,15 +1566,15 @@
         "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": "tau-bench-2/retail/litellm-tool-calling__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",
@@ -1621,8 +1621,8 @@
             "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"
                 }
               }
             }
@@ -1634,8 +1634,8 @@
         "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"
             }
           }
         }
@@ -1710,7 +1710,7 @@
       }
     },
     {
-      "evaluation_id": "tau-bench-2/telecom/smolagents-code__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",
@@ -1742,14 +1742,14 @@
             "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": "0.92",
+              "total_run_cost": "102.01",
+              "average_steps": "17.22",
               "percent_finished": "1.0"
             }
           },
@@ -1757,8 +1757,8 @@
             "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"
                 }
               }
             }
@@ -1770,15 +1770,15 @@
         "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/telecom/claude-code-cli__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",
@@ -1810,14 +1810,14 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.76,
+            "score": 0.58,
             "uncertainty": {
               "num_samples": 100
             },
             "details": {
-              "average_agent_cost": "2.45",
-              "total_run_cost": "255.97",
-              "average_steps": "18.71",
+              "average_agent_cost": "1.06",
+              "total_run_cost": "114.62",
+              "average_steps": "13.77",
               "percent_finished": "1.0"
             }
           },
@@ -1825,8 +1825,8 @@
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "Claude Code CLI",
-                  "agent_framework": "claude_code"
+                  "agent_name": "SmolAgents Code",
+                  "agent_framework": "smolagents_code"
                 }
               }
             }
@@ -1838,15 +1838,15 @@
         "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__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",
@@ -1883,9 +1883,9 @@
               "num_samples": 100
             },
             "details": {
-              "average_agent_cost": "0.92",
-              "total_run_cost": "102.01",
-              "average_steps": "17.22",
+              "average_agent_cost": "2.45",
+              "total_run_cost": "255.97",
+              "average_steps": "18.71",
               "percent_finished": "1.0"
             }
           },
@@ -1893,8 +1893,8 @@
             "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"
                 }
               }
             }
@@ -1906,15 +1906,15 @@
         "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": "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",
@@ -1946,14 +1946,14 @@
             "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"
             }
           },
@@ -1961,8 +1961,8 @@
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "OpenAI Solo",
-                  "agent_framework": "openai_solo"
+                  "agent_name": "LiteLLM Tool Calling",
+                  "agent_framework": "tool_calling"
                 }
               }
             }
@@ -1974,15 +1974,15 @@
         "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/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",
@@ -2014,14 +2014,14 @@
             "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"
             }
           },
@@ -2029,8 +2029,8 @@
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "LiteLLM Tool Calling",
-                  "agent_framework": "tool_calling"
+                  "agent_name": "OpenAI Solo",
+                  "agent_framework": "openai_solo"
                 }
               }
             }
@@ -2042,8 +2042,8 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "LiteLLM Tool Calling",
-              "agent_framework": "tool_calling"
+              "agent_name": "OpenAI Solo",
+              "agent_framework": "openai_solo"
             }
           }
         }
diff --git a/data/models/anthropic_claude-opus-4.1.json b/data/models/anthropic_claude-opus-4.1.json
index 59416d90b1dbdb120915f9f1b242f981bce8e890..66d9a9691d54a3cae59a5a4b0972ad6110b06a9b 100644
--- a/data/models/anthropic_claude-opus-4.1.json
+++ b/data/models/anthropic_claude-opus-4.1.json
@@ -4,13 +4,13 @@
     "id": "anthropic/claude-opus-4.1",
     "developer": "Anthropic",
     "additional_details": {
-      "agent_name": "OpenHands",
-      "agent_organization": "OpenHands"
+      "agent_name": "Mini-SWE-Agent",
+      "agent_organization": "Princeton"
     }
   },
   "evaluations": [
     {
-      "evaluation_id": "terminal-bench-2.0/openhands__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",
@@ -34,7 +34,7 @@
               "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,
@@ -43,17 +43,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 36.9,
+            "score": 35.1,
             "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 \"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": [
                   {
@@ -70,7 +70,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"OpenHands\" -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": [
               {
@@ -84,7 +84,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/terminus-2__claude-opus-4.1/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/openhands__claude-opus-4.1/1773776901.772108",
       "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": "2025-10-31",
+          "evaluation_timestamp": "2025-11-02",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -117,17 +117,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 38.0,
+            "score": 36.9,
             "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 \"Terminus 2\" -m \"Claude Opus 4.1\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"OpenHands\" -m \"Claude Opus 4.1\" -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 \"Terminus 2\" -m \"Claude Opus 4.1\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"OpenHands\" -m \"Claude Opus 4.1\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -158,7 +158,7 @@
       }
     },
     {
-      "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",
@@ -182,7 +182,7 @@
               "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,
@@ -191,17 +191,17 @@
             "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": [
                   {
@@ -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 \"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": [
               {
@@ -232,7 +232,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/claude-code__claude-opus-4.1/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/terminus-2__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": "2025-11-04",
+          "evaluation_timestamp": "2025-10-31",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -265,17 +265,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 34.8,
+            "score": 38.0,
             "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 \"Claude Code\" -m \"Claude Opus 4.1\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -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 \"Claude Code\" -m \"Claude Opus 4.1\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -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 007d3ac2c88dec5dff72fba0205d56eeaed42464..08f15dd6e988a559ca38856b6df4c4e4d53b00a1 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": "Terminus 2",
-      "agent_organization": "Terminal Bench"
+      "agent_name": "OpenCode",
+      "agent_organization": "Anomaly Innovations"
     }
   },
   "evaluations": [
     {
-      "evaluation_id": "terminal-bench-2.0/terminus-2__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",
@@ -34,7 +34,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-11-22",
+          "evaluation_timestamp": "2026-01-12",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -43,17 +43,11 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 57.8,
-            "uncertainty": {
-              "standard_error": {
-                "value": 2.5
-              },
-              "num_samples": 435
-            }
+            "score": 51.7
           },
           "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 \"OpenCode\" -m \"Claude Opus 4.5\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -70,7 +64,7 @@
       "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 \"OpenCode\" -m \"Claude Opus 4.5\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -152,7 +146,7 @@
       }
     },
     {
-      "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",
@@ -176,7 +170,7 @@
               "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,
@@ -185,11 +179,17 @@
             "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": [
                   {
@@ -206,7 +206,7 @@
       "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": [
               {
@@ -220,7 +220,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/goose__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",
@@ -244,7 +244,7 @@
               "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,
@@ -253,17 +253,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 54.3,
+            "score": 51.9,
             "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 \"Goose\" -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": [
                   {
@@ -280,7 +280,7 @@
       "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 \"OpenHands\" -m \"Claude Opus 4.5\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -294,7 +294,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/letta-code__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",
@@ -318,7 +318,7 @@
               "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,
@@ -327,17 +327,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 59.1,
+            "score": 54.3,
             "uncertainty": {
               "standard_error": {
-                "value": 2.4
+                "value": 2.6
               },
               "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 \"Goose\" -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 \"Letta Code\" -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": [
               {
@@ -368,7 +368,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/openhands__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",
@@ -392,7 +392,7 @@
               "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,
@@ -401,17 +401,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 51.9,
+            "score": 63.1,
             "uncertainty": {
               "standard_error": {
-                "value": 2.9
+                "value": 2.7
               },
               "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 \"Droid\" -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 \"OpenHands\" -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": [
               {
@@ -442,7 +442,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/droid__claude-opus-4.5/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/claude-code__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": "2025-12-11",
+          "evaluation_timestamp": "2025-12-18",
           "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": 63.1,
+            "score": 52.1,
             "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 \"Droid\" -m \"Claude Opus 4.5\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Claude Code\" -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 \"Droid\" -m \"Claude Opus 4.5\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Claude Code\" -m \"Claude Opus 4.5\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -516,7 +516,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/claude-code__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",
@@ -540,7 +540,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-12-18",
+          "evaluation_timestamp": "2025-12-17",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -549,17 +549,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 52.1,
+            "score": 59.1,
             "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 \"Claude Code\" -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": [
                   {
@@ -576,7 +576,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Claude Code\" -m \"Claude Opus 4.5\" -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": [
               {
diff --git a/data/models/anthropic_claude-opus-4.6.json b/data/models/anthropic_claude-opus-4.6.json
index 6de13fc0f3140d257d348a852063485bd1007995..1ae6eba958aa9144fbbc47e84b576827e9ba8012 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": "Claude Code",
-      "agent_organization": "Anthropic"
+      "agent_name": "TongAgents",
+      "agent_organization": "Bigai"
     }
   },
   "evaluations": [
     {
-      "evaluation_id": "terminal-bench-2.0/claude-code__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",
@@ -34,7 +34,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2026-02-07",
+          "evaluation_timestamp": "2026-02-22",
           "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": 58.0,
+            "score": 71.9,
             "uncertainty": {
               "standard_error": {
-                "value": 2.9
+                "value": 2.7
               },
               "num_samples": 435
             }
           },
           "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 \"TongAgents\" -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 \"Claude Code\" -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": [
               {
@@ -84,7 +84,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/mux__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",
@@ -108,7 +108,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2026-02-13",
+          "evaluation_timestamp": "2026-02-05",
           "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": 66.5,
+            "score": 69.9,
             "uncertainty": {
               "standard_error": {
                 "value": 2.5
@@ -127,7 +127,7 @@
           },
           "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 \"Droid\" -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 \"Mux\" -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": [
               {
@@ -158,7 +158,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/tongagents__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",
@@ -191,17 +191,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 71.9,
+            "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 \"TongAgents\" -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": [
                   {
@@ -218,7 +218,7 @@
       "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 \"Terminus-KIRA\" -m \"Claude Opus 4.6\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -306,7 +306,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/crux__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",
@@ -330,7 +330,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2026-02-23",
+          "evaluation_timestamp": "2026-02-13",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -339,11 +339,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 66.9
+            "score": 66.5,
+            "uncertainty": {
+              "standard_error": {
+                "value": 2.5
+              },
+              "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 \"Mux\" -m \"Claude Opus 4.6\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -360,7 +366,7 @@
       "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 \"Mux\" -m \"Claude Opus 4.6\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -374,7 +380,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/droid__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",
@@ -398,7 +404,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2026-02-05",
+          "evaluation_timestamp": "2026-02-07",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -407,17 +413,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 69.9,
+            "score": 58.0,
             "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 \"Droid\" -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": [
                   {
@@ -434,7 +440,7 @@
       "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 \"Claude Code\" -m \"Claude Opus 4.6\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -448,7 +454,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/terminus-kira__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",
@@ -472,7 +478,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2026-02-22",
+          "evaluation_timestamp": "2026-02-23",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -481,17 +487,11 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 74.7,
-            "uncertainty": {
-              "standard_error": {
-                "value": 2.6
-              },
-              "num_samples": 435
-            }
+            "score": 66.9
           },
           "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 \"Crux\" -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-KIRA\" -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": [
               {
diff --git a/data/models/anthropic_claude-sonnet-4-20250514.json b/data/models/anthropic_claude-sonnet-4-20250514.json
index a43572d10d77d034b8cc0b4e9e80cb595c19f907..17485295f0940239338e7d9ae5edbc1db77fa9eb 100644
--- a/data/models/anthropic_claude-sonnet-4-20250514.json
+++ b/data/models/anthropic_claude-sonnet-4-20250514.json
@@ -10,8 +10,8 @@
   },
   "evaluations": [
     {
-      "evaluation_id": "global-mmlu-lite/anthropic_claude-sonnet-4-20250514/1773936496.366405",
-      "retrieved_timestamp": "1773936496.366405",
+      "evaluation_id": "global-mmlu-lite/anthropic_claude-sonnet-4-20250514/1773936583.743359",
+      "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-sonnet-4-20250514/1773936583.743359",
-      "retrieved_timestamp": "1773936583.743359",
+      "evaluation_id": "global-mmlu-lite/anthropic_claude-sonnet-4-20250514/1773936496.366405",
+      "retrieved_timestamp": "1773936496.366405",
       "source_metadata": {
         "source_name": "Global MMLU Lite Leaderboard",
         "source_type": "documentation",
diff --git a/data/models/anthropic_claude-sonnet-4.5.json b/data/models/anthropic_claude-sonnet-4.5.json
index 66356dbecae8af8177ad511141877805ad8752da..c0439a05bb694a022b80d498957deb384990a100 100644
--- a/data/models/anthropic_claude-sonnet-4.5.json
+++ b/data/models/anthropic_claude-sonnet-4.5.json
@@ -84,7 +84,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/terminus-2__claude-sonnet-4.5/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/camel-ai__claude-sonnet-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": "2025-12-24",
           "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": 42.8,
+            "score": 46.5,
             "uncertainty": {
               "standard_error": {
-                "value": 2.8
+                "value": 2.4
               },
               "num_samples": 435
             }
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"Claude Sonnet 4.5\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"CAMEL-AI\" -m \"Claude Sonnet 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 Sonnet 4.5\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"CAMEL-AI\" -m \"Claude Sonnet 4.5\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -158,7 +158,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/maya__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",
@@ -182,7 +182,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2026-01-04",
+          "evaluation_timestamp": "2025-11-03",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -191,11 +191,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 42.7
+            "score": 42.5,
+            "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 \"Mini-SWE-Agent\" -m \"Claude Sonnet 4.5\" -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 \"MAYA\" -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": [
               {
@@ -226,7 +232,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/openhands__claude-sonnet-4.5/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/terminus-2__claude-sonnet-4.5/1773776901.772108",
       "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": "2025-11-02",
+          "evaluation_timestamp": "2025-10-31",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -259,7 +265,7 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 42.6,
+            "score": 42.8,
             "uncertainty": {
               "standard_error": {
                 "value": 2.8
@@ -269,7 +275,7 @@
           },
           "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 \"Terminus 2\" -m \"Claude Sonnet 4.5\" -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 \"OpenHands\" -m \"Claude Sonnet 4.5\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"Claude Sonnet 4.5\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -300,7 +306,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/claude-code__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",
@@ -324,7 +330,7 @@
               "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,
@@ -333,17 +339,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 40.1,
+            "score": 42.6,
             "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 \"Claude Code\" -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": [
                   {
@@ -360,7 +366,7 @@
       "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 \"OpenHands\" -m \"Claude Sonnet 4.5\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -374,7 +380,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/camel-ai__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",
@@ -398,7 +404,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-12-24",
+          "evaluation_timestamp": "2026-01-04",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -407,17 +413,11 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 46.5,
-            "uncertainty": {
-              "standard_error": {
-                "value": 2.4
-              },
-              "num_samples": 435
-            }
+            "score": 42.7
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"CAMEL-AI\" -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": [
                   {
@@ -434,7 +434,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"CAMEL-AI\" -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": [
               {
@@ -448,7 +448,7 @@
       }
     },
     {
-      "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",
@@ -472,7 +472,7 @@
               "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,
@@ -481,17 +481,17 @@
             "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": [
                   {
@@ -508,7 +508,7 @@
       "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": [
               {
diff --git a/data/models/atanddev_qwen2.5-1.5b-continuous-learnt.json b/data/models/atanddev_qwen2.5-1.5b-continuous-learnt.json
index d9c4a63a2048d58930bc10ecb5695a3676976b8f..c02cc4e6043653215ef5039a1e40518d83ff39e0 100644
--- a/data/models/atanddev_qwen2.5-1.5b-continuous-learnt.json
+++ b/data/models/atanddev_qwen2.5-1.5b-continuous-learnt.json
@@ -5,7 +5,7 @@
     "developer": "AtAndDev",
     "inference_platform": "unknown",
     "additional_details": {
-      "precision": "bfloat16",
+      "precision": "float16",
       "architecture": "Qwen2ForCausalLM",
       "params_billions": "1.544"
     }
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4511
+            "score": 0.4605
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4275
+            "score": 0.4258
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1473
+            "score": 0.0748
           }
         },
         {
@@ -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": 0.3623
+            "score": 0.3636
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2806
+            "score": 0.2812
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4605
+            "score": 0.4511
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4258
+            "score": 0.4275
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0748
+            "score": 0.1473
           }
         },
         {
@@ -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": 0.3636
+            "score": 0.3623
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2812
+            "score": 0.2806
           }
         }
       ],
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 ed5c0ad9e23e3e1024094c595c2931cbc579e102..eb03ad8b35e71a4f26603a2960132d29f0246b60 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": "float16",
+      "precision": "bfloat16",
       "architecture": "LlamaForCausalLM",
       "params_billions": "8.03"
     }
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.459
+            "score": 0.7999
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5185
+            "score": 0.5152
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0937
+            "score": 0.1193
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2743
+            "score": 0.281
           }
         },
         {
@@ -116,7 +116,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4083
+            "score": 0.4019
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3631
+            "score": 0.3733
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7999
+            "score": 0.459
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5152
+            "score": 0.5185
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1193
+            "score": 0.0937
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.281
+            "score": 0.2743
           }
         },
         {
@@ -246,7 +246,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4019
+            "score": 0.4083
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3733
+            "score": 0.3631
           }
         }
       ],
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 c829321bc4e1b62229f276602c62e6f6bd9a3faf..05cbb770cffa010b799551a630bc7b1089a91900 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": "bfloat16",
+      "precision": "float16",
       "architecture": "LlamaForCausalLM",
-      "params_billions": "1.803"
+      "params_billions": "3.607"
     }
   },
   "evaluations": [
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1775
+            "score": 0.4652
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.295
+            "score": 0.4531
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0
+            "score": 0.1284
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2517
+            "score": 0.2643
           }
         },
         {
@@ -116,7 +116,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3647
+            "score": 0.3394
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1049
+            "score": 0.3152
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4652
+            "score": 0.1775
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4531
+            "score": 0.295
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1284
+            "score": 0.0
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2643
+            "score": 0.2517
           }
         },
         {
@@ -246,7 +246,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3394
+            "score": 0.3647
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3152
+            "score": 0.1049
           }
         }
       ],
diff --git a/data/models/cir-ams_btrm_qwen2_7b_0613.json b/data/models/cir-ams_btrm_qwen2_7b_0613.json
index 84a36ab2262aa5d4869e5d141d383b85699971f1..9fb827ce32fb32044e2247d7f86c70d1bc13d414 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/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",
@@ -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": 0.8172
+            "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"
           }
         }
       ],
@@ -141,10 +159,10 @@
       "generation_config": null
     },
     {
-      "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",
@@ -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": 0.5736
-          },
-          "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"
           }
         }
       ],
diff --git a/data/models/cohere_command-a-03-2025.json b/data/models/cohere_command-a-03-2025.json
index aedaf4e5f944a400d87afc543fa422bde24be135..205f7c496ed81b612dd2b182b3cf2e9fd9ac9c54 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-03-2025/1773936496.366405",
-      "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",
@@ -525,8 +525,8 @@
       "generation_config": null
     },
     {
-      "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",
diff --git a/data/models/cpayne1303_llama-43m-beta.json b/data/models/cpayne1303_llama-43m-beta.json
index 8e62d1be9edc1ccaeda7702d1a793fd5db4d4150..0f0d3430f35b22a1aef8ac071591532d594d6d4d 100644
--- a/data/models/cpayne1303_llama-43m-beta.json
+++ b/data/models/cpayne1303_llama-43m-beta.json
@@ -5,7 +5,7 @@
     "developer": "cpayne1303",
     "inference_platform": "unknown",
     "additional_details": {
-      "precision": "bfloat16",
+      "precision": "float16",
       "architecture": "LlamaForCausalLM",
       "params_billions": "0.043"
     }
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1916
+            "score": 0.1949
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2977
+            "score": 0.2965
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0
+            "score": 0.0045
           }
         },
         {
@@ -116,7 +116,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3872
+            "score": 0.3885
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1132
+            "score": 0.1111
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1949
+            "score": 0.1916
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2965
+            "score": 0.2977
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0045
+            "score": 0.0
           }
         },
         {
@@ -246,7 +246,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3885
+            "score": 0.3872
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1111
+            "score": 0.1132
           }
         }
       ],
diff --git a/data/models/daemontatox_pathfinderai.json b/data/models/daemontatox_pathfinderai.json
index 7a5f7d25c7278e2df08548a48abfe0b0ee9b4f2a..8b13e2aabf79ff36b82f8d8bd4c0bcdf2b41e385 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": "bfloat16",
+      "precision": "float16",
       "architecture": "Qwen2ForCausalLM",
       "params_billions": "32.764"
     }
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4855
+            "score": 0.3745
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6627
+            "score": 0.6668
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4841
+            "score": 0.4758
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3096
+            "score": 0.3943
           }
         },
         {
@@ -116,7 +116,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4256
+            "score": 0.4858
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5542
+            "score": 0.5593
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3745
+            "score": 0.4855
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6668
+            "score": 0.6627
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4758
+            "score": 0.4841
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3943
+            "score": 0.3096
           }
         },
         {
@@ -246,7 +246,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4858
+            "score": 0.4256
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5593
+            "score": 0.5542
           }
         }
       ],
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 2ea14b6e6da41d61b06880761473f45de63d9756..849a1d52d59a5f16eab6aaa35f259f630d9dc175 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": "float16",
+      "precision": "bfloat16",
       "architecture": "LlamaForCausalLM",
       "params_billions": "1.236"
     }
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1507
+            "score": 0.1549
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.293
+            "score": 0.2937
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0
+            "score": 0.006
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2534
+            "score": 0.2576
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1125
+            "score": 0.1128
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1549
+            "score": 0.1507
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2937
+            "score": 0.293
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.006
+            "score": 0.0
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2576
+            "score": 0.2534
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1128
+            "score": 0.1125
           }
         }
       ],
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 987b3112f03b34626e0421787b1c9cb2e2b55a46..a2dcf54fc8dfd61d5182710e882025f5ed46cdab 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": "bfloat16",
-      "architecture": "LlamaForCausalLM",
+      "precision": "float16",
+      "architecture": "?",
       "params_billions": "8.03"
     }
   },
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3
+            "score": 0.2835
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3853
+            "score": 0.3842
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0415
+            "score": 0.0521
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2617
+            "score": 0.2609
           }
         },
         {
@@ -116,7 +116,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3579
+            "score": 0.3566
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2281
+            "score": 0.2298
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2835
+            "score": 0.3
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3842
+            "score": 0.3853
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0521
+            "score": 0.0415
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2609
+            "score": 0.2617
           }
         },
         {
@@ -246,7 +246,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3566
+            "score": 0.3579
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2298
+            "score": 0.2281
           }
         }
       ],
diff --git a/data/models/doppelreflex_mn-12b-lilithframe.json b/data/models/doppelreflex_mn-12b-lilithframe.json
index 720fbe0846130d5605f8d9f0e7d4c1731ec8e47c..2532c65fe82e1d06f8d68b438dbffc94e3e4e4bb 100644
--- a/data/models/doppelreflex_mn-12b-lilithframe.json
+++ b/data/models/doppelreflex_mn-12b-lilithframe.json
@@ -5,7 +5,7 @@
     "developer": "DoppelReflEx",
     "inference_platform": "unknown",
     "additional_details": {
-      "precision": "float16",
+      "precision": "bfloat16",
       "architecture": "MistralForCausalLM",
       "params_billions": "12.248"
     }
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.451
+            "score": 0.436
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4944
+            "score": 0.4956
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1156
+            "score": 0.0589
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3196
+            "score": 0.3205
           }
         },
         {
@@ -116,7 +116,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3896
+            "score": 0.3843
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3256
+            "score": 0.3237
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.436
+            "score": 0.451
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4956
+            "score": 0.4944
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0589
+            "score": 0.1156
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3205
+            "score": 0.3196
           }
         },
         {
@@ -246,7 +246,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3843
+            "score": 0.3896
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3237
+            "score": 0.3256
           }
         }
       ],
diff --git a/data/models/google_flan-t5-xl.json b/data/models/google_flan-t5-xl.json
index f4504e45576f272b296c7e91d2af835d208d50a9..55626bf61977dcd421335d97681a7abdf7372f51 100644
--- a/data/models/google_flan-t5-xl.json
+++ b/data/models/google_flan-t5-xl.json
@@ -5,7 +5,7 @@
     "developer": "Google",
     "inference_platform": "unknown",
     "additional_details": {
-      "precision": "float16",
+      "precision": "bfloat16",
       "architecture": "T5ForConditionalGeneration",
       "params_billions": "2.85"
     }
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2237
+            "score": 0.2207
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4531
+            "score": 0.4537
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0076
+            "score": 0.0008
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2525
+            "score": 0.2458
           }
         },
         {
@@ -116,7 +116,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4181
+            "score": 0.422
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2147
+            "score": 0.2142
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2207
+            "score": 0.2237
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4537
+            "score": 0.4531
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0008
+            "score": 0.0076
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2458
+            "score": 0.2525
           }
         },
         {
@@ -246,7 +246,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.422
+            "score": 0.4181
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2142
+            "score": 0.2147
           }
         }
       ],
diff --git a/data/models/google_gemini-2.5-flash-preview-05-20.json b/data/models/google_gemini-2.5-flash-preview-05-20.json
index b4b59bae4ffec304ac091e2d0d21ff7a255dc5af..01b694cbaacb7c97812a9bb056c39eebb70c1f12 100644
--- a/data/models/google_gemini-2.5-flash-preview-05-20.json
+++ b/data/models/google_gemini-2.5-flash-preview-05-20.json
@@ -10,8 +10,8 @@
   },
   "evaluations": [
     {
-      "evaluation_id": "global-mmlu-lite/google_gemini-2.5-flash-preview-05-20/1773936496.366405",
-      "retrieved_timestamp": "1773936496.366405",
+      "evaluation_id": "global-mmlu-lite/google_gemini-2.5-flash-preview-05-20/1773936583.743359",
+      "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/google_gemini-2.5-flash-preview-05-20/1773936583.743359",
-      "retrieved_timestamp": "1773936583.743359",
+      "evaluation_id": "global-mmlu-lite/google_gemini-2.5-flash-preview-05-20/1773936496.366405",
+      "retrieved_timestamp": "1773936496.366405",
       "source_metadata": {
         "source_name": "Global MMLU Lite Leaderboard",
         "source_type": "documentation",
diff --git a/data/models/google_gemini-2.5-flash.json b/data/models/google_gemini-2.5-flash.json
index 5eaa67bbe68ea1014fddc37d9abaae6354738cf4..e86caee99d92f5b1111f5d4cfe31c4107b3564b0 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/gemini-cli__gemini-2.5-flash/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/terminus-2__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": "2025-11-04",
+          "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": 15.4,
+            "score": 16.9,
             "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 \"Terminus 2\" -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 \"Gemini CLI\" -m \"Gemini 2.5 Flash\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"Gemini 2.5 Flash\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -1343,7 +1343,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/mini-swe-agent__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",
@@ -1367,7 +1367,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-11-03",
+          "evaluation_timestamp": "2025-11-02",
           "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": 17.1,
+            "score": 16.4,
             "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 \"Mini-SWE-Agent\" -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": [
                   {
@@ -1403,7 +1403,7 @@
       "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 \"OpenHands\" -m \"Gemini 2.5 Flash\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -1417,7 +1417,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/openhands__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",
@@ -1441,7 +1441,7 @@
               "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,
@@ -1450,17 +1450,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 16.4,
+            "score": 15.4,
             "uncertainty": {
               "standard_error": {
-                "value": 2.4
+                "value": 2.3
               },
               "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 \"Gemini CLI\" -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 \"OpenHands\" -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": [
               {
@@ -1491,7 +1491,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/terminus-2__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",
@@ -1515,7 +1515,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-10-31",
+          "evaluation_timestamp": "2025-11-03",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -1524,17 +1524,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 16.9,
+            "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 \"Terminus 2\" -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": [
                   {
@@ -1551,7 +1551,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"Gemini 2.5 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": [
               {
diff --git a/data/models/google_gemini-2.5-pro.json b/data/models/google_gemini-2.5-pro.json
index ad69bc6f71351eff92acf181b72bb1ef3d2ca29a..f2d7e76912c502afd2dae0560e9a20a114690132 100644
--- a/data/models/google_gemini-2.5-pro.json
+++ b/data/models/google_gemini-2.5-pro.json
@@ -10,8 +10,8 @@
   },
   "evaluations": [
     {
-      "evaluation_id": "global-mmlu-lite/google_gemini-2.5-pro/1773936496.366405",
-      "retrieved_timestamp": "1773936496.366405",
+      "evaluation_id": "global-mmlu-lite/google_gemini-2.5-pro/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/google_gemini-2.5-pro/1773936583.743359",
-      "retrieved_timestamp": "1773936583.743359",
+      "evaluation_id": "global-mmlu-lite/google_gemini-2.5-pro/1773936496.366405",
+      "retrieved_timestamp": "1773936496.366405",
       "source_metadata": {
         "source_name": "Global MMLU Lite Leaderboard",
         "source_type": "documentation",
@@ -1269,7 +1269,7 @@
       "generation_config": null
     },
     {
-      "evaluation_id": "terminal-bench-2.0/terminus-2__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",
@@ -1293,7 +1293,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-10-31",
+          "evaluation_timestamp": "2025-11-03",
           "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": 32.6,
+            "score": 26.1,
             "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 \"Terminus 2\" -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": [
                   {
@@ -1329,7 +1329,7 @@
       "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 \"Mini-SWE-Agent\" -m \"Gemini 2.5 Pro\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -1343,7 +1343,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/mini-swe-agent__gemini-2.5-pro/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/openhands__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": "2025-11-03",
+          "evaluation_timestamp": "2025-11-02",
           "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": 26.1,
+            "score": 16.4,
             "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 \"Mini-SWE-Agent\" -m \"Gemini 2.5 Pro\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"OpenHands\" -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 \"Mini-SWE-Agent\" -m \"Gemini 2.5 Pro\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"OpenHands\" -m \"Gemini 2.5 Pro\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -1417,7 +1417,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/gemini-cli__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",
@@ -1441,7 +1441,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-11-04",
+          "evaluation_timestamp": "2025-10-31",
           "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": 19.6,
+            "score": 32.6,
             "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 \"Gemini CLI\" -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": [
                   {
@@ -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 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": [
               {
@@ -1491,7 +1491,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/openhands__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",
@@ -1515,7 +1515,7 @@
               "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,
@@ -1524,17 +1524,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 16.4,
+            "score": 19.6,
             "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 \"OpenHands\" -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": [
                   {
@@ -1551,7 +1551,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"OpenHands\" -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 6d70bb6cf77fa0c54cb9eb4fa0ff050319c617e5..8ad1fcf1488cbfb100a465260bd9105159bfdda1 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": "Terminus 2",
-      "agent_organization": "Terminal Bench"
+      "agent_name": "Junie CLI",
+      "agent_organization": "JetBrains"
     }
   },
   "evaluations": [
     {
-      "evaluation_id": "terminal-bench-2.0/terminus-2__gemini-3-flash/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/junie-cli__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": "2026-01-07",
+          "evaluation_timestamp": "2025-12-23",
           "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": 51.7,
+            "score": 64.3,
             "uncertainty": {
               "standard_error": {
-                "value": 3.1
+                "value": 2.8
               },
               "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 \"Junie CLI\" -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 \"Terminus 2\" -m \"Gemini 3 Flash\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Junie CLI\" -m \"Gemini 3 Flash\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -84,7 +84,7 @@
       }
     },
     {
-      "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",
@@ -108,7 +108,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2026-03-06",
+          "evaluation_timestamp": "2026-01-07",
           "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": 47.4,
+            "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": [
                   {
@@ -144,7 +144,7 @@
       "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": [
               {
@@ -158,7 +158,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/junie-cli__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",
@@ -182,7 +182,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-12-23",
+          "evaluation_timestamp": "2026-03-06",
           "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": 64.3,
+            "score": 47.4,
             "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 \"Junie CLI\" -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": [
                   {
@@ -218,7 +218,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Junie CLI\" -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": [
               {
diff --git a/data/models/google_gemini-3-pro-preview.json b/data/models/google_gemini-3-pro-preview.json
index fdc61e428a001318c9e1c391ace7515f63b19817..3f20467a04db22c43c2d253a7e0a111a72926152 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": "SmolAgents Code",
-      "agent_framework": "smolagents_code"
+      "agent_name": "LiteLLM Tool Calling with Shortlisting",
+      "agent_framework": "tool_calling_with_shortlisting"
     }
   },
   "evaluations": [
     {
-      "evaluation_id": "appworld/test_normal/smolagents-code__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",
@@ -42,23 +42,23 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.13,
+            "score": 0.55,
             "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": "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": "SmolAgents Code",
-                  "agent_framework": "smolagents_code"
+                  "agent_name": "LiteLLM Tool Calling with Shortlisting",
+                  "agent_framework": "tool_calling_with_shortlisting"
                 }
               }
             }
@@ -70,15 +70,15 @@
         "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": "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",
@@ -110,23 +110,23 @@
             "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"
                 }
               }
             }
@@ -138,15 +138,15 @@
         "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/openai-solo__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",
@@ -178,23 +178,23 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.582,
+            "score": 0.505,
             "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": "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": "OpenAI Solo",
-                  "agent_framework": "openai_solo"
+                  "agent_name": "LiteLLM Tool Calling",
+                  "agent_framework": "tool_calling"
                 }
               }
             }
@@ -206,15 +206,15 @@
         "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": "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",
@@ -246,23 +246,23 @@
             "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"
                 }
               }
             }
@@ -274,15 +274,15 @@
         "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/openai-solo__google_gemini-3-pro-preview/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": 0.57,
+            "score": 0.3333,
             "uncertainty": {
-              "num_samples": 100
+              "num_samples": 99
             },
             "details": {
-              "average_agent_cost": "2.39",
-              "total_run_cost": "239.0",
-              "average_steps": "29.63",
-              "percent_finished": "0.69"
+              "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": "SmolAgents Code",
-                  "agent_framework": "smolagents_code"
+                  "agent_name": "OpenAI Solo",
+                  "agent_framework": "openai_solo"
                 }
               }
             }
@@ -342,15 +342,15 @@
         "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/claude-code-cli__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",
@@ -363,34 +363,34 @@
         "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": 0.36,
+            "score": 0.51,
             "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": "2.85",
+              "total_run_cost": "284.68",
+              "average_steps": "22.88",
+              "percent_finished": "0.7"
             }
           },
           "generation_config": {
@@ -418,7 +418,7 @@
       }
     },
     {
-      "evaluation_id": "browsecompplus/claude-code-cli__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",
@@ -431,42 +431,42 @@
         "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": 0.13,
             "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": "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": "Claude Code CLI",
-                  "agent_framework": "claude_code"
+                  "agent_name": "SmolAgents Code",
+                  "agent_framework": "smolagents_code"
                 }
               }
             }
@@ -478,15 +478,15 @@
         "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": "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",
@@ -518,23 +518,23 @@
             "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"
                 }
               }
             }
@@ -546,15 +546,15 @@
         "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": "browsecompplus/litellm-tool-calling-with-shortlisting__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",
@@ -586,23 +586,23 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.48,
+            "score": 0.57,
             "uncertainty": {
               "num_samples": 100
             },
             "details": {
-              "average_agent_cost": "0.44",
-              "total_run_cost": "44.18",
-              "average_steps": "7.85",
-              "percent_finished": "0.99"
+              "average_agent_cost": "2.39",
+              "total_run_cost": "239.0",
+              "average_steps": "29.63",
+              "percent_finished": "0.69"
             }
           },
           "generation_config": {
             "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"
                 }
               }
             }
@@ -614,15 +614,15 @@
         "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": "browsecompplus/litellm-tool-calling__google_gemini-3-pro-preview/1774263615.0201504",
+      "evaluation_id": "browsecompplus/litellm-tool-calling-with-shortlisting__google_gemini-3-pro-preview/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -669,8 +669,8 @@
             "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"
                 }
               }
             }
@@ -682,8 +682,8 @@
         "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"
             }
           }
         }
@@ -1720,7 +1720,7 @@
       "generation_config": null
     },
     {
-      "evaluation_id": "swe-bench/litellm-tool-calling-with-shortlisting__google_gemini-3-pro-preview/1774263615.0201504",
+      "evaluation_id": "swe-bench/claude-code-cli__google_gemini-3-pro-preview/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -1752,14 +1752,14 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.71,
+            "score": 0.67,
             "uncertainty": {
               "num_samples": 100
             },
             "details": {
-              "average_agent_cost": "0.7",
-              "total_run_cost": "69.56",
-              "average_steps": "32.55",
+              "average_agent_cost": "3.68",
+              "total_run_cost": "367.97",
+              "average_steps": "43.72",
               "percent_finished": "1.0"
             }
           },
@@ -1767,8 +1767,8 @@
             "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"
                 }
               }
             }
@@ -1780,8 +1780,8 @@
         "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"
             }
           }
         }
@@ -1856,7 +1856,7 @@
       }
     },
     {
-      "evaluation_id": "swe-bench/openai-solo__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",
@@ -1869,33 +1869,33 @@
         "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": 0.7234,
+            "score": 0.62,
             "uncertainty": {
-              "num_samples": 94
+              "num_samples": 50
             },
             "details": {
-              "average_agent_cost": "1.58",
-              "total_run_cost": "148.44",
-              "average_steps": "32.36",
+              "average_agent_cost": "0.21",
+              "total_run_cost": "11.18",
+              "average_steps": "10.9",
               "percent_finished": "1.0"
             }
           },
@@ -1924,7 +1924,7 @@
       }
     },
     {
-      "evaluation_id": "swe-bench/claude-code-cli__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",
@@ -1956,14 +1956,14 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.67,
+            "score": 0.71,
             "uncertainty": {
               "num_samples": 100
             },
             "details": {
-              "average_agent_cost": "3.68",
-              "total_run_cost": "367.97",
-              "average_steps": "43.72",
+              "average_agent_cost": "0.7",
+              "total_run_cost": "69.56",
+              "average_steps": "32.55",
               "percent_finished": "1.0"
             }
           },
@@ -1971,8 +1971,8 @@
             "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"
                 }
               }
             }
@@ -1984,15 +1984,15 @@
         "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__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",
@@ -2039,8 +2039,8 @@
             "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"
                 }
               }
             }
@@ -2052,15 +2052,15 @@
         "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/airline/litellm-tool-calling__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",
@@ -2073,33 +2073,33 @@
         "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": 0.7,
+            "score": 0.7234,
             "uncertainty": {
-              "num_samples": 50
+              "num_samples": 94
             },
             "details": {
-              "average_agent_cost": "0.16",
-              "total_run_cost": "8.48",
-              "average_steps": "10.14",
+              "average_agent_cost": "1.58",
+              "total_run_cost": "148.44",
+              "average_steps": "32.36",
               "percent_finished": "1.0"
             }
           },
@@ -2107,8 +2107,8 @@
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "LiteLLM Tool Calling",
-                  "agent_framework": "tool_calling"
+                  "agent_name": "OpenAI Solo",
+                  "agent_framework": "openai_solo"
                 }
               }
             }
@@ -2120,8 +2120,8 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "LiteLLM Tool Calling",
-              "agent_framework": "tool_calling"
+              "agent_name": "OpenAI Solo",
+              "agent_framework": "openai_solo"
             }
           }
         }
@@ -2196,7 +2196,7 @@
       }
     },
     {
-      "evaluation_id": "tau-bench-2/airline/openai-solo__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",
@@ -2228,14 +2228,14 @@
             "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": "0.16",
+              "total_run_cost": "8.48",
+              "average_steps": "10.14",
               "percent_finished": "1.0"
             }
           },
@@ -2243,8 +2243,8 @@
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "OpenAI Solo",
-                  "agent_framework": "openai_solo"
+                  "agent_name": "LiteLLM Tool Calling",
+                  "agent_framework": "tool_calling"
                 }
               }
             }
@@ -2256,15 +2256,15 @@
         "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/airline/litellm-tool-calling-with-shortlisting__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",
@@ -2296,14 +2296,14 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7,
+            "score": 0.68,
             "uncertainty": {
               "num_samples": 50
             },
             "details": {
-              "average_agent_cost": "0.16",
-              "total_run_cost": "8.48",
-              "average_steps": "10.14",
+              "average_agent_cost": "0.2",
+              "total_run_cost": "10.29",
+              "average_steps": "12.28",
               "percent_finished": "1.0"
             }
           },
@@ -2311,8 +2311,8 @@
             "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"
                 }
               }
             }
@@ -2324,15 +2324,15 @@
         "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/airline/smolagents-code__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",
@@ -2364,14 +2364,14 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.68,
+            "score": 0.7,
             "uncertainty": {
               "num_samples": 50
             },
             "details": {
-              "average_agent_cost": "0.2",
-              "total_run_cost": "10.29",
-              "average_steps": "12.28",
+              "average_agent_cost": "0.16",
+              "total_run_cost": "8.48",
+              "average_steps": "10.14",
               "percent_finished": "1.0"
             }
           },
@@ -2379,8 +2379,8 @@
             "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"
                 }
               }
             }
@@ -2392,15 +2392,15 @@
         "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/litellm-tool-calling__google_gemini-3-pro-preview/1774263615.0201504",
+      "evaluation_id": "tau-bench-2/retail/litellm-tool-calling-with-shortlisting__google_gemini-3-pro-preview/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -2447,8 +2447,8 @@
             "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"
                 }
               }
             }
@@ -2460,15 +2460,15 @@
         "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/retail/openai-solo__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": 0.7576,
+            "score": 0.73,
             "uncertainty": {
               "num_samples": 100
             },
             "details": {
-              "average_agent_cost": "0.21",
-              "total_run_cost": "21.43",
-              "average_steps": "11.3",
+              "average_agent_cost": "0.27",
+              "total_run_cost": "27.48",
+              "average_steps": "10.62",
               "percent_finished": "1.0"
             }
           },
@@ -2515,8 +2515,8 @@
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "SmolAgents Code",
-                  "agent_framework": "smolagents_code"
+                  "agent_name": "OpenAI Solo",
+                  "agent_framework": "openai_solo"
                 }
               }
             }
@@ -2528,15 +2528,15 @@
         "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": "tau-bench-2/retail/litellm-tool-calling-with-shortlisting__google_gemini-3-pro-preview/1774263615.0201504",
+      "evaluation_id": "tau-bench-2/retail/litellm-tool-calling__google_gemini-3-pro-preview/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -2583,8 +2583,8 @@
             "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"
                 }
               }
             }
@@ -2596,15 +2596,15 @@
         "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/openai-solo__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",
@@ -2636,14 +2636,14 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.73,
+            "score": 0.7576,
             "uncertainty": {
               "num_samples": 100
             },
             "details": {
-              "average_agent_cost": "0.27",
-              "total_run_cost": "27.48",
-              "average_steps": "10.62",
+              "average_agent_cost": "0.21",
+              "total_run_cost": "21.43",
+              "average_steps": "11.3",
               "percent_finished": "1.0"
             }
           },
@@ -2651,8 +2651,8 @@
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "OpenAI Solo",
-                  "agent_framework": "openai_solo"
+                  "agent_name": "SmolAgents Code",
+                  "agent_framework": "smolagents_code"
                 }
               }
             }
@@ -2664,15 +2664,15 @@
         "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": "tau-bench-2/retail/claude-code-cli__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",
@@ -2685,33 +2685,33 @@
         "name": "exgentic",
         "version": "0.1.0"
       },
-      "benchmark": "tau-bench-2_retail",
+      "benchmark": "tau-bench-2_telecom",
       "evaluation_results": [
         {
-          "evaluation_name": "tau-bench-2/retail",
+          "evaluation_name": "tau-bench-2/telecom",
           "source_data": {
-            "dataset_name": "tau-bench-2/retail",
+            "dataset_name": "tau-bench-2/telecom",
             "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 (telecom subset)",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7805,
+            "score": 0.73,
             "uncertainty": {
               "num_samples": 100
             },
             "details": {
-              "average_agent_cost": "0.19",
-              "total_run_cost": "19.38",
-              "average_steps": "11.18",
+              "average_agent_cost": "0.3",
+              "total_run_cost": "36.75",
+              "average_steps": "14.84",
               "percent_finished": "1.0"
             }
           },
@@ -2719,8 +2719,8 @@
             "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"
                 }
               }
             }
@@ -2732,15 +2732,15 @@
         "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/telecom/claude-code-cli__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",
@@ -2772,23 +2772,23 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6852,
+            "score": 0.8876,
             "uncertainty": {
               "num_samples": 100
             },
             "details": {
-              "average_agent_cost": "0.21",
-              "total_run_cost": "25.48",
-              "average_steps": "9.9",
-              "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": "Claude Code CLI",
-                  "agent_framework": "claude_code"
+                  "agent_name": "OpenAI Solo",
+                  "agent_framework": "openai_solo"
                 }
               }
             }
@@ -2800,15 +2800,15 @@
         "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/telecom/litellm-tool-calling__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",
@@ -2840,14 +2840,14 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.73,
+            "score": 0.88,
             "uncertainty": {
               "num_samples": 100
             },
             "details": {
-              "average_agent_cost": "0.3",
-              "total_run_cost": "36.75",
-              "average_steps": "14.84",
+              "average_agent_cost": "0.35",
+              "total_run_cost": "40.25",
+              "average_steps": "12.71",
               "percent_finished": "1.0"
             }
           },
@@ -2855,8 +2855,8 @@
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "LiteLLM Tool Calling",
-                  "agent_framework": "tool_calling"
+                  "agent_name": "SmolAgents Code",
+                  "agent_framework": "smolagents_code"
                 }
               }
             }
@@ -2868,15 +2868,15 @@
         "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/telecom/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",
@@ -2889,33 +2889,33 @@
         "name": "exgentic",
         "version": "0.1.0"
       },
-      "benchmark": "tau-bench-2_telecom",
+      "benchmark": "tau-bench-2_retail",
       "evaluation_results": [
         {
-          "evaluation_name": "tau-bench-2/telecom",
+          "evaluation_name": "tau-bench-2/retail",
           "source_data": {
-            "dataset_name": "tau-bench-2/telecom",
+            "dataset_name": "tau-bench-2/retail",
             "source_type": "url",
             "url": [
               "https://github.com/Exgentic/exgentic"
             ]
           },
           "metric_config": {
-            "evaluation_description": "Tau Bench 2 benchmark evaluation (telecom 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": 0.88,
+            "score": 0.7805,
             "uncertainty": {
               "num_samples": 100
             },
             "details": {
-              "average_agent_cost": "0.35",
-              "total_run_cost": "40.25",
-              "average_steps": "12.71",
+              "average_agent_cost": "0.19",
+              "total_run_cost": "19.38",
+              "average_steps": "11.18",
               "percent_finished": "1.0"
             }
           },
@@ -2923,8 +2923,8 @@
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "SmolAgents Code",
-                  "agent_framework": "smolagents_code"
+                  "agent_name": "Claude Code CLI",
+                  "agent_framework": "claude_code"
                 }
               }
             }
@@ -2936,15 +2936,15 @@
         "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/litellm-tool-calling-with-shortlisting__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": 0.8876,
+            "score": 0.73,
             "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": "0.3",
+              "total_run_cost": "36.75",
+              "average_steps": "14.84",
+              "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 with Shortlisting",
+                  "agent_framework": "tool_calling_with_shortlisting"
                 }
               }
             }
@@ -3004,15 +3004,15 @@
         "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/litellm-tool-calling-with-shortlisting__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",
@@ -3044,14 +3044,14 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.73,
+            "score": 0.6852,
             "uncertainty": {
               "num_samples": 100
             },
             "details": {
-              "average_agent_cost": "0.3",
-              "total_run_cost": "36.75",
-              "average_steps": "14.84",
+              "average_agent_cost": "0.21",
+              "total_run_cost": "25.48",
+              "average_steps": "9.9",
               "percent_finished": "1.0"
             }
           },
@@ -3059,8 +3059,8 @@
             "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"
                 }
               }
             }
@@ -3072,8 +3072,8 @@
         "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"
             }
           }
         }
diff --git a/data/models/google_gemini-3-pro.json b/data/models/google_gemini-3-pro.json
index 3f400faaadf810745e49d759105088e642b483cc..5acfd6f3e4c0e364f178f7fde5f99550b7d69ddb 100644
--- a/data/models/google_gemini-3-pro.json
+++ b/data/models/google_gemini-3-pro.json
@@ -4,13 +4,13 @@
     "id": "google/gemini-3-pro",
     "developer": "Google",
     "additional_details": {
-      "agent_name": "SageAgent",
-      "agent_organization": "OpenSage"
+      "agent_name": "Droid",
+      "agent_organization": "Factory"
     }
   },
   "evaluations": [
     {
-      "evaluation_id": "terminal-bench-2.0/sageagent__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",
@@ -34,7 +34,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2026-02-23",
+          "evaluation_timestamp": "2025-12-24",
           "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": 65.2,
+            "score": 61.1,
             "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 \"SageAgent\" -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": [
                   {
@@ -70,7 +70,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"SageAgent\" -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": [
               {
@@ -84,7 +84,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/ante__gemini-3-pro/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/sageagent__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": "2026-01-06",
+          "evaluation_timestamp": "2026-02-23",
           "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": 69.4,
+            "score": 65.2,
             "uncertainty": {
               "standard_error": {
                 "value": 2.1
@@ -127,7 +127,7 @@
           },
           "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 \"SageAgent\" -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 \"Ante\" -m \"Gemini 3 Pro\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"SageAgent\" -m \"Gemini 3 Pro\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -158,7 +158,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/droid__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",
@@ -182,7 +182,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-12-24",
+          "evaluation_timestamp": "2025-11-21",
           "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": 61.1,
+            "score": 56.9,
             "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 \"Droid\" -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": [
                   {
@@ -218,7 +218,7 @@
       "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 \"Terminus 2\" -m \"Gemini 3 Pro\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -232,7 +232,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/codebrain-1__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",
@@ -256,7 +256,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2026-02-05",
+          "evaluation_timestamp": "2025-12-23",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -265,17 +265,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 62.2,
+            "score": 61.8,
             "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 \"II-Agent\" -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 \"CodeBrain-1\" -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": [
               {
@@ -306,7 +306,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/ii-agent__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",
@@ -330,7 +330,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-12-23",
+          "evaluation_timestamp": "2025-12-17",
           "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": 61.8,
+            "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 \"II-Agent\" -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": [
                   {
@@ -366,7 +366,7 @@
       "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 \"Letta Code\" -m \"Gemini 3 Pro\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -380,7 +380,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/letta-code__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",
@@ -404,7 +404,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-12-17",
+          "evaluation_timestamp": "2026-01-06",
           "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": 56.0,
+            "score": 69.4,
             "uncertainty": {
               "standard_error": {
-                "value": 3.0
+                "value": 2.1
               },
               "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 \"Ante\" -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 \"Letta Code\" -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": [
               {
@@ -454,7 +454,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/terminus-2__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",
@@ -478,7 +478,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-11-21",
+          "evaluation_timestamp": "2026-02-05",
           "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": 56.9,
+            "score": 62.2,
             "uncertainty": {
               "standard_error": {
-                "value": 2.5
+                "value": 2.6
               },
               "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 \"CodeBrain-1\" -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 \"Terminus 2\" -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": [
               {
diff --git a/data/models/google_gemini_3_flash.json b/data/models/google_gemini_3_flash.json
index 3a911939d887cdc9433884fdde5ee11c97c277a4..6beb736773081d366f65edf05d1bf54bd7e07ce2 100644
--- a/data/models/google_gemini_3_flash.json
+++ b/data/models/google_gemini_3_flash.json
@@ -6,53 +6,6 @@
     "inference_platform": "unknown"
   },
   "evaluations": [
-    {
-      "evaluation_id": "ace/google_gemini-3-flash/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": "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": 0.415
-          },
-          "generation_config": {
-            "additional_details": {
-              "run_setting": "High"
-            }
-          }
-        }
-      ],
-      "detailed_evaluation_results": null,
-      "generation_config": {
-        "additional_details": {
-          "run_setting": "High"
-        }
-      }
-    },
     {
       "evaluation_id": "apex-agents/google_gemini-3-flash/1773260200",
       "retrieved_timestamp": "1773260200",
@@ -252,6 +205,53 @@
         }
       }
     },
+    {
+      "evaluation_id": "ace/google_gemini-3-flash/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": "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": 0.415
+          },
+          "generation_config": {
+            "additional_details": {
+              "run_setting": "High"
+            }
+          }
+        }
+      ],
+      "detailed_evaluation_results": null,
+      "generation_config": {
+        "additional_details": {
+          "run_setting": "High"
+        }
+      }
+    },
     {
       "evaluation_id": "apex-v1/google_gemini-3-flash/1773260200",
       "retrieved_timestamp": "1773260200",
diff --git a/data/models/google_gemma-2-2b-jpn-it.json b/data/models/google_gemma-2-2b-jpn-it.json
index 208075f00df888593e36a118e84f64272df933ff..ad8eb46cb13cde4ab2a8a3521d4c0b618fb71ee6 100644
--- a/data/models/google_gemma-2-2b-jpn-it.json
+++ b/data/models/google_gemma-2-2b-jpn-it.json
@@ -5,7 +5,7 @@
     "developer": "Google",
     "inference_platform": "unknown",
     "additional_details": {
-      "precision": "float16",
+      "precision": "bfloat16",
       "architecture": "Gemma2ForCausalLM",
       "params_billions": "2.614"
     }
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5078
+            "score": 0.5288
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4226
+            "score": 0.4178
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0347
+            "score": 0.0476
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2852
+            "score": 0.2752
           }
         },
         {
@@ -116,7 +116,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3964
+            "score": 0.3728
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2578
+            "score": 0.2467
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5288
+            "score": 0.5078
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4178
+            "score": 0.4226
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0476
+            "score": 0.0347
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2752
+            "score": 0.2852
           }
         },
         {
@@ -246,7 +246,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3728
+            "score": 0.3964
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2467
+            "score": 0.2578
           }
         }
       ],
diff --git a/data/models/google_gemma-3-27b-it.json b/data/models/google_gemma-3-27b-it.json
index 31e90c4548397bec1dec70a558a4830dc0c4f7c9..0d22aa7a55f613493f23d93430a44590b7aa715d 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/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",
@@ -525,8 +525,8 @@
       "generation_config": null
     },
     {
-      "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",
diff --git a/data/models/gunulhona_gemma-ko-merge-peft.json b/data/models/gunulhona_gemma-ko-merge-peft.json
index 7aaca8e76ac4d54a166ddba85afcaa38d76748c4..632db743d31cc31d893a565c873ea7be7cc73fb2 100644
--- a/data/models/gunulhona_gemma-ko-merge-peft.json
+++ b/data/models/gunulhona_gemma-ko-merge-peft.json
@@ -5,7 +5,7 @@
     "developer": "Gunulhona",
     "inference_platform": "unknown",
     "additional_details": {
-      "precision": "float16",
+      "precision": "bfloat16",
       "architecture": "?",
       "params_billions": "20.318"
     }
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4441
+            "score": 0.288
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4863
+            "score": 0.5154
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.307
+            "score": 0.3247
           }
         },
         {
@@ -116,7 +116,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3986
+            "score": 0.408
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3098
+            "score": 0.3817
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.288
+            "score": 0.4441
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5154
+            "score": 0.4863
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3247
+            "score": 0.307
           }
         },
         {
@@ -246,7 +246,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.408
+            "score": 0.3986
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3817
+            "score": 0.3098
           }
         }
       ],
diff --git a/data/models/hendrydong_mistral-rm-for-raft-gshf-v0.json b/data/models/hendrydong_mistral-rm-for-raft-gshf-v0.json
index 69bdc21b5b14ca68b6163472e8eef6fd89e268f5..357f438b07831c53712dd63f870b6b2401c4d681 100644
--- a/data/models/hendrydong_mistral-rm-for-raft-gshf-v0.json
+++ b/data/models/hendrydong_mistral-rm-for-raft-gshf-v0.json
@@ -9,10 +9,10 @@
   },
   "evaluations": [
     {
-      "evaluation_id": "reward-bench/hendrydong_Mistral-RM-for-RAFT-GSHF-v0/1766412838.146816",
+      "evaluation_id": "reward-bench-2/hendrydong_Mistral-RM-for-RAFT-GSHF-v0/1766412838.146816",
       "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": 0.7847
+            "score": 0.5851
           },
           "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": 0.9832
+            "score": 0.5779
           },
           "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": 0.5789
+            "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": 0.6011
+          },
+          "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": 0.85
+            "score": 0.6956
           },
           "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": 0.7434
+            "score": 0.6747
           },
           "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": 0.7508
+            "score": 0.5988
           },
           "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/hendrydong_Mistral-RM-for-RAFT-GSHF-v0/1766412838.146816",
+      "evaluation_id": "reward-bench/hendrydong_Mistral-RM-for-RAFT-GSHF-v0/1766412838.146816",
       "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": 0.5851
-          },
-          "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": 0.5779
+            "score": 0.7847
           },
           "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": 0.9832
           },
           "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": 0.6011
+            "score": 0.5789
           },
           "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": 0.6956
+            "score": 0.85
           },
           "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": 0.6747
+            "score": 0.7434
           },
           "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": 0.5988
+            "score": 0.7508
           },
           "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/huggingfacetb_smollm2-135m-instruct.json b/data/models/huggingfacetb_smollm2-135m-instruct.json
index 7413ccc13689271f5c637f0314f401eea3acbcec..4930fd119b327af5dcaff7489655e3b5a735f796 100644
--- a/data/models/huggingfacetb_smollm2-135m-instruct.json
+++ b/data/models/huggingfacetb_smollm2-135m-instruct.json
@@ -5,7 +5,7 @@
     "developer": "HuggingFaceTB",
     "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": 0.0593
+            "score": 0.2883
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3135
+            "score": 0.3124
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0144
+            "score": 0.003
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2341
+            "score": 0.2357
           }
         },
         {
@@ -116,7 +116,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3871
+            "score": 0.3662
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1092
+            "score": 0.1115
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2883
+            "score": 0.0593
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3124
+            "score": 0.3135
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.003
+            "score": 0.0144
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2357
+            "score": 0.2341
           }
         },
         {
@@ -246,7 +246,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3662
+            "score": 0.3871
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1115
+            "score": 0.1092
           }
         }
       ],
diff --git a/data/models/icefog72_icesakev6rp-7b.json b/data/models/icefog72_icesakev6rp-7b.json
new file mode 100644
index 0000000000000000000000000000000000000000..f3267e4e350d12bc0c15245dbc590141fe9832d9
--- /dev/null
+++ b/data/models/icefog72_icesakev6rp-7b.json
@@ -0,0 +1,145 @@
+{
+  "model_info": {
+    "name": "IceSakeV6RP-7b",
+    "id": "icefog72/IceSakeV6RP-7b",
+    "developer": "icefog72",
+    "inference_platform": "unknown",
+    "additional_details": {
+      "precision": "float16",
+      "architecture": "MistralForCausalLM",
+      "params_billions": "7.242"
+    }
+  },
+  "evaluations": [
+    {
+      "evaluation_id": "hfopenllm_v2/icefog72_IceSakeV6RP-7b/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": 0.5033
+          }
+        },
+        {
+          "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": 0.4976
+          }
+        },
+        {
+          "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": 0.0619
+          }
+        },
+        {
+          "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": 0.2911
+          }
+        },
+        {
+          "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": 0.42
+          }
+        },
+        {
+          "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": 0.3093
+          }
+        }
+      ],
+      "detailed_evaluation_results": null,
+      "generation_config": null
+    }
+  ]
+}
\ No newline at end of file
diff --git a/data/models/internlm_internlm2-1_8b-reward.json b/data/models/internlm_internlm2-1_8b-reward.json
index fdd95af043dae0ccf6943006b6d82bc9a69847ba..db02a96edd7d4deec66c9db68ed23c5ecfdc96f9 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-2/internlm_internlm2-1_8b-reward/1766412838.146816",
+      "evaluation_id": "reward-bench/internlm_internlm2-1_8b-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",
@@ -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": 0.3902
+            "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": "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": 0.2758
+            "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": "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": 0.3625
+            "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": "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": 0.4426
+            "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": "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": 0.4711
+            "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"
           }
-        },
+        }
+      ],
+      "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": "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": 0.596
+            "score": 0.3902
           },
           "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": 0.1934
+            "score": 0.2758
           },
           "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": "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": 0.8217
+            "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": "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": 0.9358
+            "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": "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": 0.6623
+            "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"
           }
         },
         {
-          "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": 0.8162
+            "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": "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": 0.8724
+            "score": 0.1934
           },
           "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_internlm2-20b-reward.json b/data/models/internlm_internlm2-20b-reward.json
index 4de166855af75438b275f87369424e25bd91920e..db57bc6ddd293d585b6bca7ac06b0b270dabb864 100644
--- a/data/models/internlm_internlm2-20b-reward.json
+++ b/data/models/internlm_internlm2-20b-reward.json
@@ -9,10 +9,10 @@
   },
   "evaluations": [
     {
-      "evaluation_id": "reward-bench/internlm_internlm2-20b-reward/1766412838.146816",
+      "evaluation_id": "reward-bench-2/internlm_internlm2-20b-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": 0.9016
+            "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": "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": 0.9888
+            "score": 0.5558
           },
           "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": 0.7654
+            "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": 0.8946
+            "score": 0.5738
           },
           "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": 0.9576
+            "score": 0.6111
           },
           "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_internlm2-20b-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": 0.5628
+            "score": 0.7253
           },
           "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": 0.5558
+            "score": 0.5483
           },
           "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_internlm2-20b-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": 0.9016
           },
           "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": 0.5738
+            "score": 0.9888
           },
           "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": 0.6111
+            "score": 0.7654
           },
           "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": 0.7253
+            "score": 0.8946
           },
           "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": 0.5483
+            "score": 0.9576
           },
           "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 850f56827380f314c355f2c532b41bbbb69062e8..5907aad77cdf2d42a7b25e1a1a35520112be4497 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-2/internlm_internlm2-7b-reward/1766412838.146816",
+      "evaluation_id": "reward-bench/internlm_internlm2-7b-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",
@@ -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": 0.5335
+            "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": "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": 0.4211
+            "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": "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": 0.4
+            "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": "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": 0.5628
+            "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": "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": 0.5956
+            "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"
           }
-        },
+        }
+      ],
+      "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": "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": 0.7051
+            "score": 0.5335
           },
           "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": 0.5164
+            "score": 0.4211
           },
           "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": "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": 0.8759
+            "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": "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": 0.9916
+            "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": "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": 0.6952
+            "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"
           }
         },
         {
-          "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": 0.8716
+            "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": "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": 0.9453
+            "score": 0.5164
           },
           "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/isaak-carter_josiev4o-8b-stage1-v4.json b/data/models/isaak-carter_josiev4o-8b-stage1-v4.json
index 3d8b7bc1575ec467cf84b27d25552c6269300054..4be5b49897aa6863276434fc48c4d6962992c15e 100644
--- a/data/models/isaak-carter_josiev4o-8b-stage1-v4.json
+++ b/data/models/isaak-carter_josiev4o-8b-stage1-v4.json
@@ -5,7 +5,7 @@
     "developer": "Isaak-Carter",
     "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": 0.2477
+            "score": 0.2553
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4758
+            "score": 0.4725
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0453
+            "score": 0.0529
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2911
+            "score": 0.2919
           }
         },
         {
@@ -116,7 +116,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3641
+            "score": 0.3654
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3292
+            "score": 0.3316
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2553
+            "score": 0.2477
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4725
+            "score": 0.4758
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0529
+            "score": 0.0453
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2919
+            "score": 0.2911
           }
         },
         {
@@ -246,7 +246,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3654
+            "score": 0.3641
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3316
+            "score": 0.3292
           }
         }
       ],
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 7b050770aeb59148493da52d2a21dee32c7d2c89..4462dbdfa0461cc5c2fd5d7ac79308c4e0a0cd93 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": "float16",
+      "precision": "bfloat16",
       "architecture": "MistralForCausalLM",
       "params_billions": "7.242"
     }
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3036
+            "score": 0.3066
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4575
+            "score": 0.4577
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3012
+            "score": 0.2995
           }
         },
         {
@@ -116,7 +116,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4253
+            "score": 0.4254
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2329
+            "score": 0.2318
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3066
+            "score": 0.3036
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4577
+            "score": 0.4575
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2995
+            "score": 0.3012
           }
         },
         {
@@ -246,7 +246,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4254
+            "score": 0.4253
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2318
+            "score": 0.2329
           }
         }
       ],
diff --git a/data/models/llmat_mistral-v0.3-7b-orpo.json b/data/models/llmat_mistral-v0.3-7b-orpo.json
index 3a1b947d84c5d76bb2423237a20cbf150415592e..c2c9120f6bd010e2ff566effb35617377de554ee 100644
--- a/data/models/llmat_mistral-v0.3-7b-orpo.json
+++ b/data/models/llmat_mistral-v0.3-7b-orpo.json
@@ -5,7 +5,7 @@
     "developer": "llmat",
     "inference_platform": "unknown",
     "additional_details": {
-      "precision": "float16",
+      "precision": "bfloat16",
       "architecture": "MistralForCausalLM",
       "params_billions": "7.248"
     }
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.364
+            "score": 0.377
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4005
+            "score": 0.3978
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0015
+            "score": 0.0242
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2693
+            "score": 0.2668
           }
         },
         {
@@ -116,7 +116,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3529
+            "score": 0.3555
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2301
+            "score": 0.2278
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.377
+            "score": 0.364
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3978
+            "score": 0.4005
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0242
+            "score": 0.0015
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2668
+            "score": 0.2693
           }
         },
         {
@@ -246,7 +246,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3555
+            "score": 0.3529
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2278
+            "score": 0.2301
           }
         }
       ],
diff --git a/data/models/microsoft_phi-3-mini-4k-instruct.json b/data/models/microsoft_phi-3-mini-4k-instruct.json
index f0214854e07bd3ad87162726609ad6d31e31396a..9787f21694f92686e734f02c35c722665943d7d4 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": "float16",
+      "precision": "bfloat16",
       "architecture": "Phi3ForCausalLM",
       "params_billions": "3.821"
     }
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5477
+            "score": 0.5613
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5491
+            "score": 0.5676
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1639
+            "score": 0.1163
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3322
+            "score": 0.3196
           }
         },
         {
@@ -116,7 +116,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4284
+            "score": 0.395
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4022
+            "score": 0.3866
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5613
+            "score": 0.5477
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5676
+            "score": 0.5491
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1163
+            "score": 0.1639
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3196
+            "score": 0.3322
           }
         },
         {
@@ -246,7 +246,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.395
+            "score": 0.4284
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3866
+            "score": 0.4022
           }
         }
       ],
diff --git a/data/models/microsoft_phi-4.json b/data/models/microsoft_phi-4.json
index 32eb099ab1f2e61ac11a8ea3a80df6bc18e5c656..c9fca4565946dbb26825690fda8366b38bda6709 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": "bfloat16",
+      "precision": "float16",
       "architecture": "Phi3ForCausalLM",
       "params_billions": "14.66"
     }
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0585
+            "score": 0.0488
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6691
+            "score": 0.6703
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3165
+            "score": 0.2787
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.406
+            "score": 0.401
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5287
+            "score": 0.5295
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0488
+            "score": 0.0585
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6703
+            "score": 0.6691
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2787
+            "score": 0.3165
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.401
+            "score": 0.406
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5295
+            "score": 0.5287
           }
         }
       ],
diff --git a/data/models/mistralai_mixtral-8x7b-v0.1.json b/data/models/mistralai_mixtral-8x7b-v0.1.json
index 9d997e3527157e47894ae0f49b424a1634297e78..c3ac844f0072de0a86748b754d6c90570298768c 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": "bfloat16",
+      "precision": "float16",
       "architecture": "MixtralForCausalLM",
       "params_billions": "46.703"
     }
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2415
+            "score": 0.2326
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5087
+            "score": 0.5098
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.102
+            "score": 0.0937
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3138
+            "score": 0.3205
           }
         },
         {
@@ -116,7 +116,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4321
+            "score": 0.4413
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.385
+            "score": 0.3871
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2326
+            "score": 0.2415
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5098
+            "score": 0.5087
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0937
+            "score": 0.102
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3205
+            "score": 0.3138
           }
         },
         {
@@ -246,7 +246,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4413
+            "score": 0.4321
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3871
+            "score": 0.385
           }
         }
       ],
diff --git a/data/models/mlabonne_neuraldaredevil-8b-abliterated.json b/data/models/mlabonne_neuraldaredevil-8b-abliterated.json
index d443de39bb7ed82b00df80190432e583c21fd660..7ef165972eafdeec56d923c82e02fdbbc9479eac 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": "float16",
+      "precision": "bfloat16",
       "architecture": "LlamaForCausalLM",
       "params_billions": "8.03"
     }
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7561
+            "score": 0.4162
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5111
+            "score": 0.5124
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0906
+            "score": 0.0853
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3062
+            "score": 0.3029
           }
         },
         {
@@ -116,7 +116,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4019
+            "score": 0.415
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3841
+            "score": 0.3802
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4162
+            "score": 0.7561
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5124
+            "score": 0.5111
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0853
+            "score": 0.0906
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3029
+            "score": 0.3062
           }
         },
         {
@@ -246,7 +246,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.415
+            "score": 0.4019
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3802
+            "score": 0.3841
           }
         }
       ],
diff --git a/data/models/multiple_multiple.json b/data/models/multiple_multiple.json
index c7a1aa9eb1cb1dfc4d88c122729fc6bae4148158..01b06a48bec6c0ec600ef83ad482f6552d46d980 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": "Abacus AI Desktop",
-      "agent_organization": "Abacus.AI"
+      "agent_name": "Warp",
+      "agent_organization": "Warp"
     }
   },
   "evaluations": [
     {
-      "evaluation_id": "terminal-bench-2.0/abacus-ai-desktop__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",
@@ -34,7 +34,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-12-11",
+          "evaluation_timestamp": "2025-12-12",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -43,17 +43,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 58.4,
+            "score": 61.2,
             "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 \"Abacus AI Desktop\" -m \"Multiple\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Warp\" -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 \"Abacus AI Desktop\" -m \"Multiple\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Warp\" -m \"Multiple\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -306,7 +306,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/warp__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",
@@ -330,7 +330,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-12-12",
+          "evaluation_timestamp": "2026-03-07",
           "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": 61.2,
+            "score": 71.0,
             "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 \"Warp\" -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": [
                   {
@@ -366,7 +366,7 @@
       "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 \"Junie CLI\" -m \"Multiple\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -380,7 +380,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/junie-cli__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",
@@ -404,7 +404,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2026-03-07",
+          "evaluation_timestamp": "2025-12-11",
           "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": 71.0,
+            "score": 58.4,
             "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 \"Abacus AI Desktop\" -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 \"Junie CLI\" -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": [
               {
diff --git a/data/models/nazimali_mistral-nemo-kurdish-instruct.json b/data/models/nazimali_mistral-nemo-kurdish-instruct.json
index 7bcf436e7a29205a95d8b228b8e52bcfb9264e7a..bf12d1ac4ce4431e1cc4657892f1de48dd5df10b 100644
--- a/data/models/nazimali_mistral-nemo-kurdish-instruct.json
+++ b/data/models/nazimali_mistral-nemo-kurdish-instruct.json
@@ -5,7 +5,7 @@
     "developer": "nazimali",
     "inference_platform": "unknown",
     "additional_details": {
-      "precision": "bfloat16",
+      "precision": "float16",
       "architecture": "MistralForCausalLM",
       "params_billions": "12.248"
     }
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4964
+            "score": 0.486
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4699
+            "score": 0.4721
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0045
+            "score": 0.0846
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2827
+            "score": 0.2844
           }
         },
         {
@@ -116,7 +116,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3979
+            "score": 0.4006
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3063
+            "score": 0.3087
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.486
+            "score": 0.4964
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4721
+            "score": 0.4699
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0846
+            "score": 0.0045
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2844
+            "score": 0.2827
           }
         },
         {
@@ -246,7 +246,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4006
+            "score": 0.3979
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3087
+            "score": 0.3063
           }
         }
       ],
diff --git a/data/models/nexusflow_starling-rm-34b.json b/data/models/nexusflow_starling-rm-34b.json
index 8ab4f392fbf3047e7bcb88c6ed9f3a2b6d8e5a37..0373bd963cc9795a2ad38fc9da30f8417d64ff6d 100644
--- a/data/models/nexusflow_starling-rm-34b.json
+++ b/data/models/nexusflow_starling-rm-34b.json
@@ -9,10 +9,10 @@
   },
   "evaluations": [
     {
-      "evaluation_id": "reward-bench-2/Nexusflow_Starling-RM-34B/1766412838.146816",
+      "evaluation_id": "reward-bench/Nexusflow_Starling-RM-34B/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": 0.4553
-          },
-          "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": 0.4589
+            "score": 0.8133
           },
           "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": 0.3187
+            "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": 0.6175
+            "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": 0.7556
+            "score": 0.877
           },
           "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": 0.4808
+            "score": 0.8845
           },
           "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": 0.1004
+            "score": 0.7137
           },
           "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/Nexusflow_Starling-RM-34B/1766412838.146816",
+      "evaluation_id": "reward-bench-2/Nexusflow_Starling-RM-34B/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": 0.8133
+            "score": 0.4553
           },
           "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": 0.4589
           },
           "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": 0.3187
           },
           "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": 0.6175
+          },
+          "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": 0.877
+            "score": 0.7556
           },
           "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": 0.8845
+            "score": 0.4808
           },
           "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": 0.7137
+            "score": 0.1004
           },
           "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/nicolinho_qrm-llama3.1-8b-v2.json b/data/models/nicolinho_qrm-llama3.1-8b-v2.json
index 0df8878cad15f33ea391f78f6a5406e147177591..71e586c5d191f366e8b76150e58f0f9807a69f6b 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-2/nicolinho_QRM-Llama3.1-8B-v2/1766412838.146816",
+      "evaluation_id": "reward-bench/nicolinho_QRM-Llama3.1-8B-v2/1766412838.146816",
       "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": 0.7074
+            "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": "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": 0.6653
+            "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": 0.4062
+            "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": "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": 0.612
+            "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": "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": 0.9467
+            "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"
           }
-        },
+        }
+      ],
+      "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": "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": 0.8909
+            "score": 0.7074
           },
           "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": 0.7234
+            "score": 0.6653
           },
           "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": "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": 0.9314
+            "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": "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": 0.612
           },
           "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": "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": 0.8684
+            "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"
           }
         },
         {
-          "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": 0.9257
+            "score": 0.8909
           },
           "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": 0.9677
+            "score": 0.7234
           },
           "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/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 f86ab61b521749eb0f8fa030a3c29f5a32d327a1..486ba5e61208261c68f73d7d2bf88d78b1b36131 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": "float16",
+      "precision": "bfloat16",
       "architecture": "Qwen2ForCausalLM",
       "params_billions": "3.759"
     }
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1162
+            "score": 0.1128
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3184
+            "score": 0.3171
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0076
+            "score": 0.0113
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2634
+            "score": 0.2685
           }
         },
         {
@@ -116,7 +116,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3447
+            "score": 0.346
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1124
+            "score": 0.1129
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1128
+            "score": 0.1162
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3171
+            "score": 0.3184
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0113
+            "score": 0.0076
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2685
+            "score": 0.2634
           }
         },
         {
@@ -246,7 +246,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.346
+            "score": 0.3447
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1129
+            "score": 0.1124
           }
         }
       ],
diff --git a/data/models/openai_gpt-4o-2024-08-06.json b/data/models/openai_gpt-4o-2024-08-06.json
index 4523783fb76c33e56985cf8706dfcde93c76d009..ca15abfce433f9cf3b132cc5fefadfcef719867a 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/openai_gpt-4o-2024-08-06/1766412838.146816",
+      "evaluation_id": "reward-bench-2/openai_gpt-4o-2024-08-06/1766412838.146816",
       "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",
@@ -1922,128 +1922,104 @@
         {
           "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": 0.8673
+            "score": 0.6493
           },
           "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": 0.9609
+            "score": 0.5684
           },
           "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": 0.3312
           },
           "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": 0.8811
+            "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": "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": 0.8661
+            "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"
           }
-        }
-      ],
-      "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": "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": 0.6493
+            "score": 0.7293
           },
           "source_data": {
             "dataset_name": "RewardBench 2",
@@ -2052,111 +2028,135 @@
           }
         },
         {
-          "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": 0.5684
+            "score": 0.7819
           },
           "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": "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": 0.8673
           },
           "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": "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": 0.623
+            "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": "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": 0.8619
+            "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": "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": 0.7293
+            "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": "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": 0.7819
+            "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"
           }
         }
       ],
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 f38f4e1ddedf08dfff3e3ceeb97aeebb3dcce913..1b3fb4c30102ee1f603e3640bb4c4b14c38b8cac 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/openai_gpt-4o-mini-2024-07-18/1766412838.146816",
+      "evaluation_id": "reward-bench-2/openai_gpt-4o-mini-2024-07-18/1766412838.146816",
       "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",
@@ -2146,128 +2146,104 @@
         {
           "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": 0.8007
+            "score": 0.5796
           },
           "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": 0.9497
+            "score": 0.4105
           },
           "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": 0.6075
+            "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": "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": 0.8081
+            "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": "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": 0.8374
+            "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"
           }
-        }
-      ],
-      "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": "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": 0.5796
+            "score": 0.7414
           },
           "source_data": {
             "dataset_name": "RewardBench 2",
@@ -2276,111 +2252,135 @@
           }
         },
         {
-          "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": 0.4105
+            "score": 0.6962
           },
           "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": "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": 0.3438
+            "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": "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": 0.5191
+            "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": "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": 0.7667
+            "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": "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": 0.7414
+            "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": "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": 0.6962
+            "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"
           }
         }
       ],
diff --git a/data/models/openai_gpt-5-2025-08-07.json b/data/models/openai_gpt-5-2025-08-07.json
index 0853492fcc4bbd45f07185718454686350fe1be2..fdb97ce4111978e08938be252c1bd72645c11969 100644
--- a/data/models/openai_gpt-5-2025-08-07.json
+++ b/data/models/openai_gpt-5-2025-08-07.json
@@ -10,8 +10,8 @@
   },
   "evaluations": [
     {
-      "evaluation_id": "global-mmlu-lite/openai_gpt-5-2025-08-07/1773936496.366405",
-      "retrieved_timestamp": "1773936496.366405",
+      "evaluation_id": "global-mmlu-lite/openai_gpt-5-2025-08-07/1773936583.743359",
+      "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/openai_gpt-5-2025-08-07/1773936583.743359",
-      "retrieved_timestamp": "1773936583.743359",
+      "evaluation_id": "global-mmlu-lite/openai_gpt-5-2025-08-07/1773936496.366405",
+      "retrieved_timestamp": "1773936496.366405",
       "source_metadata": {
         "source_name": "Global MMLU Lite Leaderboard",
         "source_type": "documentation",
diff --git a/data/models/openai_gpt-5-codex.json b/data/models/openai_gpt-5-codex.json
index a875eb11356a27d3b1b0f42875c13e7560d24fec..bfb9d809d90faf4023c720a69d517cc43ddb6092 100644
--- a/data/models/openai_gpt-5-codex.json
+++ b/data/models/openai_gpt-5-codex.json
@@ -4,13 +4,13 @@
     "id": "openai/gpt-5-codex",
     "developer": "OpenAI",
     "additional_details": {
-      "agent_name": "Codex CLI",
-      "agent_organization": "OpenAI"
+      "agent_name": "Terminus 2",
+      "agent_organization": "Terminal Bench"
     }
   },
   "evaluations": [
     {
-      "evaluation_id": "terminal-bench-2.0/codex-cli__gpt-5-codex/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/terminus-2__gpt-5-codex/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": "2025-10-31",
           "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": 44.3,
+            "score": 43.4,
             "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 \"Codex CLI\" -m \"GPT-5-Codex\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"GPT-5-Codex\" -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-Codex\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"GPT-5-Codex\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -84,7 +84,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/mini-swe-agent__gpt-5-codex/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/codex-cli__gpt-5-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": "2025-11-03",
+          "evaluation_timestamp": "2025-11-04",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -117,17 +117,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 41.3,
+            "score": 44.3,
             "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 \"Mini-SWE-Agent\" -m \"GPT-5-Codex\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Codex CLI\" -m \"GPT-5-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 \"Mini-SWE-Agent\" -m \"GPT-5-Codex\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Codex CLI\" -m \"GPT-5-Codex\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -158,7 +158,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/terminus-2__gpt-5-codex/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/mini-swe-agent__gpt-5-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": "2025-10-31",
+          "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": 43.4,
+            "score": 41.3,
             "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 \"Terminus 2\" -m \"GPT-5-Codex\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Mini-SWE-Agent\" -m \"GPT-5-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 \"Terminus 2\" -m \"GPT-5-Codex\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Mini-SWE-Agent\" -m \"GPT-5-Codex\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
diff --git a/data/models/openai_gpt-5-mini.json b/data/models/openai_gpt-5-mini.json
index c2c25e33d8592b0cf47f06cc9166a5f66ec8f591..c2da3f31323642732ef7d6d76ecea92f3ae2ea0b 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": "Mini-SWE-Agent",
-      "agent_organization": "Princeton"
+      "agent_name": "Codex CLI",
+      "agent_organization": "OpenAI"
     }
   },
   "evaluations": [
     {
-      "evaluation_id": "terminal-bench-2.0/mini-swe-agent__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",
@@ -34,7 +34,7 @@
               "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,
@@ -43,17 +43,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 22.2,
+            "score": 31.9,
             "uncertainty": {
               "standard_error": {
-                "value": 2.6
+                "value": 3.0
               },
               "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 \"Codex CLI\" -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 \"Mini-SWE-Agent\" -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": [
               {
@@ -84,7 +84,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/terminus-2__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",
@@ -108,7 +108,7 @@
               "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,
@@ -117,17 +117,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 24.0,
+            "score": 29.2,
             "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 \"Terminus 2\" -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": [
                   {
@@ -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-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": [
               {
@@ -158,7 +158,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/spoox-m__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",
@@ -182,7 +182,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-12-24",
+          "evaluation_timestamp": "2025-10-31",
           "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": 24.0,
             "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 \"spoox-m\" -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": [
                   {
@@ -218,7 +218,7 @@
       "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 \"Terminus 2\" -m \"GPT-5-Mini\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -232,7 +232,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/openhands__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",
@@ -256,7 +256,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-11-02",
+          "evaluation_timestamp": "2025-12-24",
           "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": 29.2,
+            "score": 34.8,
             "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 \"OpenHands\" -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": [
                   {
@@ -292,7 +292,7 @@
       "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 \"spoox-m\" -m \"GPT-5-Mini\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -306,7 +306,7 @@
       }
     },
     {
-      "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",
@@ -330,7 +330,7 @@
               "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,
@@ -339,17 +339,17 @@
             "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": [
                   {
@@ -366,7 +366,7 @@
       "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": [
               {
diff --git a/data/models/openai_gpt-5-nano.json b/data/models/openai_gpt-5-nano.json
index f1c6d8f032d8015d1380b26ffc2082a7ad57137f..17031b27e97ab53bd889b020db9c4f3335b70c14 100644
--- a/data/models/openai_gpt-5-nano.json
+++ b/data/models/openai_gpt-5-nano.json
@@ -4,13 +4,13 @@
     "id": "openai/gpt-5-nano",
     "developer": "OpenAI",
     "additional_details": {
-      "agent_name": "OpenHands",
-      "agent_organization": "OpenHands"
+      "agent_name": "Mini-SWE-Agent",
+      "agent_organization": "Princeton"
     }
   },
   "evaluations": [
     {
-      "evaluation_id": "terminal-bench-2.0/openhands__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",
@@ -34,7 +34,7 @@
               "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,
@@ -43,17 +43,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 9.9,
+            "score": 7.0,
             "uncertainty": {
               "standard_error": {
-                "value": 2.1
+                "value": 1.9
               },
               "num_samples": 435
             }
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"OpenHands\" -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": [
                   {
@@ -70,7 +70,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"OpenHands\" -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": [
               {
@@ -84,7 +84,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/terminus-2__gpt-5-nano/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/openhands__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": "2025-10-31",
+          "evaluation_timestamp": "2025-11-02",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -117,17 +117,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 7.9,
+            "score": 9.9,
             "uncertainty": {
               "standard_error": {
-                "value": 1.9
+                "value": 2.1
               },
               "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 \"OpenHands\" -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 \"Terminus 2\" -m \"GPT-5-Nano\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"OpenHands\" -m \"GPT-5-Nano\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -232,7 +232,7 @@
       }
     },
     {
-      "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",
@@ -256,7 +256,7 @@
               "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,
@@ -265,7 +265,7 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 7.0,
+            "score": 7.9,
             "uncertainty": {
               "standard_error": {
                 "value": 1.9
@@ -275,7 +275,7 @@
           },
           "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": [
                   {
@@ -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 \"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": [
               {
diff --git a/data/models/openai_gpt-5.1-codex.json b/data/models/openai_gpt-5.1-codex.json
index 5ac777453649e155d2cf4ca5c0edb4c1fb8d16a4..d4b36a19fcc7086223ae8f218d54f2b1a6ca0184 100644
--- a/data/models/openai_gpt-5.1-codex.json
+++ b/data/models/openai_gpt-5.1-codex.json
@@ -4,13 +4,13 @@
     "id": "openai/gpt-5.1-codex",
     "developer": "OpenAI",
     "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__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",
@@ -34,7 +34,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-11-17",
+          "evaluation_timestamp": "2025-11-16",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -43,17 +43,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 36.9,
+            "score": 57.8,
             "uncertainty": {
               "standard_error": {
-                "value": 3.2
+                "value": 2.9
               },
               "num_samples": 435
             }
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -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": [
                   {
@@ -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-5.1-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": [
               {
@@ -84,7 +84,7 @@
       }
     },
     {
-      "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",
@@ -108,7 +108,7 @@
               "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,
@@ -117,17 +117,17 @@
             "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": [
                   {
@@ -144,7 +144,7 @@
       "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": [
               {
@@ -158,7 +158,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/letta-code__gpt-5.1-codex/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/terminus-2__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": "2025-12-17",
+          "evaluation_timestamp": "2025-11-17",
           "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": 53.5,
+            "score": 36.9,
             "uncertainty": {
               "standard_error": {
-                "value": 2.8
+                "value": 3.2
               },
               "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 \"Terminus 2\" -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 \"Letta Code\" -m \"GPT-5.1-Codex\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -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 c3a672d6300dfa51d07ee396880a48a053600e4c..296a87eb83719a9fcbce40e624e36b0e1264dcb7 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": "OpenAI Solo",
-      "agent_framework": "openai_solo"
+      "agent_name": "SmolAgents Code",
+      "agent_framework": "smolagents_code"
     }
   },
   "evaluations": [
     {
-      "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",
@@ -42,23 +42,23 @@
             "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"
                 }
               }
             }
@@ -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": "appworld/test_normal/smolagents-code__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",
@@ -110,23 +110,23 @@
             "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": "LiteLLM Tool Calling",
+                  "agent_framework": "tool_calling"
                 }
               }
             }
@@ -138,8 +138,8 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "SmolAgents Code",
-              "agent_framework": "smolagents_code"
+              "agent_name": "LiteLLM Tool Calling",
+              "agent_framework": "tool_calling"
             }
           }
         }
@@ -214,7 +214,7 @@
       }
     },
     {
-      "evaluation_id": "appworld/test_normal/litellm-tool-calling__openai_gpt-5.2-2025-12-11/1774263615.0201504",
+      "evaluation_id": "appworld/test_normal/claude-code-cli__openai_gpt-5.2-2025-12-11/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -261,8 +261,8 @@
             "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"
                 }
               }
             }
@@ -274,15 +274,15 @@
         "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": "appworld/test_normal/claude-code-cli__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",
@@ -329,8 +329,8 @@
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "Claude Code CLI",
-                  "agent_framework": "claude_code"
+                  "agent_name": "OpenAI Solo",
+                  "agent_framework": "openai_solo"
                 }
               }
             }
@@ -342,8 +342,8 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "Claude Code CLI",
-              "agent_framework": "claude_code"
+              "agent_name": "OpenAI Solo",
+              "agent_framework": "openai_solo"
             }
           }
         }
@@ -418,7 +418,7 @@
       }
     },
     {
-      "evaluation_id": "browsecompplus/openai-solo__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",
@@ -450,23 +450,23 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.48,
+            "score": 0.26,
             "uncertainty": {
               "num_samples": 100
             },
             "details": {
-              "average_agent_cost": "0.38",
-              "total_run_cost": "38.21",
-              "average_steps": "14.27",
-              "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": "OpenAI Solo",
-                  "agent_framework": "openai_solo"
+                  "agent_name": "SmolAgents Code",
+                  "agent_framework": "smolagents_code"
                 }
               }
             }
@@ -478,8 +478,8 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "OpenAI Solo",
-              "agent_framework": "openai_solo"
+              "agent_name": "SmolAgents Code",
+              "agent_framework": "smolagents_code"
             }
           }
         }
@@ -622,7 +622,7 @@
       }
     },
     {
-      "evaluation_id": "browsecompplus/smolagents-code__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",
@@ -654,23 +654,23 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.26,
+            "score": 0.48,
             "uncertainty": {
               "num_samples": 100
             },
             "details": {
-              "average_agent_cost": "0.17",
-              "total_run_cost": "17.31",
-              "average_steps": "6.57",
-              "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": "SmolAgents Code",
-                  "agent_framework": "smolagents_code"
+                  "agent_name": "OpenAI Solo",
+                  "agent_framework": "openai_solo"
                 }
               }
             }
@@ -682,8 +682,8 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "SmolAgents Code",
-              "agent_framework": "smolagents_code"
+              "agent_name": "OpenAI Solo",
+              "agent_framework": "openai_solo"
             }
           }
         }
@@ -769,7 +769,7 @@
       "generation_config": null
     },
     {
-      "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",
@@ -801,14 +801,14 @@
             "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"
             }
           },
@@ -816,8 +816,8 @@
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "LiteLLM Tool Calling",
-                  "agent_framework": "tool_calling"
+                  "agent_name": "SmolAgents Code",
+                  "agent_framework": "smolagents_code"
                 }
               }
             }
@@ -829,15 +829,15 @@
         "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/openai-solo__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",
@@ -869,14 +869,14 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5455,
+            "score": 0.57,
             "uncertainty": {
-              "num_samples": 99
+              "num_samples": 100
             },
             "details": {
-              "average_agent_cost": "0.26",
-              "total_run_cost": "25.64",
-              "average_steps": "20.44",
+              "average_agent_cost": "0.25",
+              "total_run_cost": "24.76",
+              "average_steps": "20.47",
               "percent_finished": "1.0"
             }
           },
@@ -884,8 +884,8 @@
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "OpenAI Solo",
-                  "agent_framework": "openai_solo"
+                  "agent_name": "LiteLLM Tool Calling",
+                  "agent_framework": "tool_calling"
                 }
               }
             }
@@ -897,15 +897,15 @@
         "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": "swe-bench/smolagents-code__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",
@@ -937,14 +937,14 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5253,
+            "score": 0.57,
             "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": "0.25",
+              "total_run_cost": "24.76",
+              "average_steps": "20.47",
               "percent_finished": "1.0"
             }
           },
@@ -952,8 +952,8 @@
             "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"
                 }
               }
             }
@@ -965,8 +965,8 @@
         "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"
             }
           }
         }
@@ -1041,7 +1041,7 @@
       }
     },
     {
-      "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",
@@ -1073,14 +1073,14 @@
             "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"
             }
           },
@@ -1088,8 +1088,8 @@
             "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"
                 }
               }
             }
@@ -1101,15 +1101,15 @@
         "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": "swe-bench/litellm-tool-calling-with-shortlisting__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",
@@ -1122,33 +1122,33 @@
         "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": 0.57,
+            "score": 0.5,
             "uncertainty": {
-              "num_samples": 100
+              "num_samples": 50
             },
             "details": {
-              "average_agent_cost": "0.25",
-              "total_run_cost": "24.76",
-              "average_steps": "20.47",
+              "average_agent_cost": "0.11",
+              "total_run_cost": "5.77",
+              "average_steps": "11.4",
               "percent_finished": "1.0"
             }
           },
@@ -1156,8 +1156,8 @@
             "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"
                 }
               }
             }
@@ -1169,15 +1169,15 @@
         "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-with-shortlisting__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",
@@ -1209,14 +1209,14 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.54,
+            "score": 0.6,
             "uncertainty": {
               "num_samples": 50
             },
             "details": {
-              "average_agent_cost": "0.13",
-              "total_run_cost": "6.96",
-              "average_steps": "11.22",
+              "average_agent_cost": "0.29",
+              "total_run_cost": "15.28",
+              "average_steps": "10.68",
               "percent_finished": "1.0"
             }
           },
@@ -1224,8 +1224,8 @@
             "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"
                 }
               }
             }
@@ -1237,15 +1237,15 @@
         "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/airline/claude-code-cli__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",
@@ -1277,14 +1277,14 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.48,
+            "score": 0.54,
             "uncertainty": {
               "num_samples": 50
             },
             "details": {
-              "average_agent_cost": "0.21",
-              "total_run_cost": "11.23",
-              "average_steps": "10.18",
+              "average_agent_cost": "0.13",
+              "total_run_cost": "6.96",
+              "average_steps": "11.22",
               "percent_finished": "1.0"
             }
           },
@@ -1292,8 +1292,8 @@
             "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"
                 }
               }
             }
@@ -1305,15 +1305,15 @@
         "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/litellm-tool-calling__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",
@@ -1326,33 +1326,33 @@
         "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": 0.54,
+            "score": 0.5455,
             "uncertainty": {
-              "num_samples": 50
+              "num_samples": 99
             },
             "details": {
-              "average_agent_cost": "0.13",
-              "total_run_cost": "6.96",
-              "average_steps": "11.22",
+              "average_agent_cost": "0.26",
+              "total_run_cost": "25.64",
+              "average_steps": "20.44",
               "percent_finished": "1.0"
             }
           },
@@ -1360,8 +1360,8 @@
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "LiteLLM Tool Calling",
-                  "agent_framework": "tool_calling"
+                  "agent_name": "OpenAI Solo",
+                  "agent_framework": "openai_solo"
                 }
               }
             }
@@ -1373,15 +1373,15 @@
         "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/smolagents-code__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",
@@ -1413,14 +1413,14 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6,
+            "score": 0.48,
             "uncertainty": {
               "num_samples": 50
             },
             "details": {
-              "average_agent_cost": "0.29",
-              "total_run_cost": "15.28",
-              "average_steps": "10.68",
+              "average_agent_cost": "0.21",
+              "total_run_cost": "11.23",
+              "average_steps": "10.18",
               "percent_finished": "1.0"
             }
           },
@@ -1428,8 +1428,8 @@
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "SmolAgents Code",
-                  "agent_framework": "smolagents_code"
+                  "agent_name": "Claude Code CLI",
+                  "agent_framework": "claude_code"
                 }
               }
             }
@@ -1441,15 +1441,15 @@
         "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/retail/openai-solo__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",
@@ -1481,23 +1481,23 @@
             "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 with Shortlisting",
+                  "agent_framework": "tool_calling_with_shortlisting"
                 }
               }
             }
@@ -1509,15 +1509,15 @@
         "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-with-shortlisting__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",
@@ -1564,8 +1564,8 @@
             "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"
                 }
               }
             }
@@ -1577,15 +1577,15 @@
         "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/litellm-tool-calling__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",
@@ -1617,14 +1617,14 @@
             "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"
             }
           },
@@ -1632,8 +1632,8 @@
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "LiteLLM Tool Calling",
-                  "agent_framework": "tool_calling"
+                  "agent_name": "SmolAgents Code",
+                  "agent_framework": "smolagents_code"
                 }
               }
             }
@@ -1645,15 +1645,15 @@
         "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__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",
@@ -1685,23 +1685,23 @@
             "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"
                 }
               }
             }
@@ -1713,15 +1713,15 @@
         "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/retail/smolagents-code__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",
@@ -1734,33 +1734,33 @@
         "name": "exgentic",
         "version": "0.1.0"
       },
-      "benchmark": "tau-bench-2_retail",
+      "benchmark": "tau-bench-2_telecom",
       "evaluation_results": [
         {
-          "evaluation_name": "tau-bench-2/retail",
+          "evaluation_name": "tau-bench-2/telecom",
           "source_data": {
-            "dataset_name": "tau-bench-2/retail",
+            "dataset_name": "tau-bench-2/telecom",
             "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 (telecom subset)",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.68,
+            "score": 0.71,
             "uncertainty": {
               "num_samples": 100
             },
             "details": {
-              "average_agent_cost": "0.25",
-              "total_run_cost": "26.27",
-              "average_steps": "11.08",
+              "average_agent_cost": "0.3",
+              "total_run_cost": "35.31",
+              "average_steps": "10.11",
               "percent_finished": "1.0"
             }
           },
@@ -1789,7 +1789,7 @@
       }
     },
     {
-      "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/claude-code-cli__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": 0.5354,
+            "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 with Shortlisting",
-                  "agent_framework": "tool_calling_with_shortlisting"
+                  "agent_name": "Claude Code CLI",
+                  "agent_framework": "claude_code"
                 }
               }
             }
@@ -1849,15 +1849,15 @@
         "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": "tau-bench-2/telecom/smolagents-code__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",
@@ -1889,14 +1889,14 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.71,
+            "score": 0.53,
             "uncertainty": {
               "num_samples": 100
             },
             "details": {
-              "average_agent_cost": "0.3",
-              "total_run_cost": "35.31",
-              "average_steps": "10.11",
+              "average_agent_cost": "0.15",
+              "total_run_cost": "18.88",
+              "average_steps": "9.92",
               "percent_finished": "1.0"
             }
           },
@@ -1904,8 +1904,8 @@
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "SmolAgents Code",
-                  "agent_framework": "smolagents_code"
+                  "agent_name": "OpenAI Solo",
+                  "agent_framework": "openai_solo"
                 }
               }
             }
@@ -1917,15 +1917,15 @@
         "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": "tau-bench-2/telecom/openai-solo__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",
@@ -1957,23 +1957,23 @@
             "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",
+                  "agent_framework": "tool_calling"
                 }
               }
             }
@@ -1985,15 +1985,15 @@
         "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/telecom/claude-code-cli__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",
@@ -2025,23 +2025,23 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.55,
+            "score": 0.5354,
             "uncertainty": {
               "num_samples": 100
             },
             "details": {
-              "average_agent_cost": "0.1",
-              "total_run_cost": "15.15",
-              "average_steps": "9.36",
-              "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": "Claude Code CLI",
-                  "agent_framework": "claude_code"
+                  "agent_name": "LiteLLM Tool Calling with Shortlisting",
+                  "agent_framework": "tool_calling_with_shortlisting"
                 }
               }
             }
@@ -2053,15 +2053,15 @@
         "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__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",
@@ -2074,42 +2074,42 @@
         "name": "exgentic",
         "version": "0.1.0"
       },
-      "benchmark": "tau-bench-2_telecom",
+      "benchmark": "tau-bench-2_retail",
       "evaluation_results": [
         {
-          "evaluation_name": "tau-bench-2/telecom",
+          "evaluation_name": "tau-bench-2/retail",
           "source_data": {
-            "dataset_name": "tau-bench-2/telecom",
+            "dataset_name": "tau-bench-2/retail",
             "source_type": "url",
             "url": [
               "https://github.com/Exgentic/exgentic"
             ]
           },
           "metric_config": {
-            "evaluation_description": "Tau Bench 2 benchmark evaluation (telecom 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": 0.5354,
+            "score": 0.51,
             "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": "0.12",
+              "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"
                 }
               }
             }
@@ -2121,8 +2121,8 @@
         "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"
             }
           }
         }
diff --git a/data/models/openai_gpt-5.2.json b/data/models/openai_gpt-5.2.json
index 1f373630f767c55e79d63767d1456fe1b49fa7e4..ff63f2052ea0b7c9a5cea40f5696ce46050721df 100644
--- a/data/models/openai_gpt-5.2.json
+++ b/data/models/openai_gpt-5.2.json
@@ -4,13 +4,13 @@
     "id": "openai/gpt-5.2",
     "developer": "OpenAI",
     "additional_details": {
-      "agent_name": "Droid",
-      "agent_organization": "Factory"
+      "agent_name": "Codex CLI",
+      "agent_organization": "OpenAI"
     }
   },
   "evaluations": [
     {
-      "evaluation_id": "terminal-bench-2.0/droid__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",
@@ -34,7 +34,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-12-24",
+          "evaluation_timestamp": "2025-12-18",
           "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": 64.9,
+            "score": 62.9,
             "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 \"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": [
                   {
@@ -70,7 +70,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Droid\" -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": [
               {
@@ -84,7 +84,7 @@
       }
     },
     {
-      "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",
@@ -108,7 +108,7 @@
               "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,
@@ -117,17 +117,11 @@
             "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": [
                   {
@@ -144,7 +138,7 @@
       "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": [
               {
@@ -158,7 +152,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/terminus-2__gpt-5.2/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/droid__gpt-5.2/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -182,7 +176,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-12-12",
+          "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 +185,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 54.0,
+            "score": 64.9,
             "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 \"Terminus 2\" -m \"GPT-5.2\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Droid\" -m \"GPT-5.2\" -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 \"Terminus 2\" -m \"GPT-5.2\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Droid\" -m \"GPT-5.2\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -232,7 +226,7 @@
       }
     },
     {
-      "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",
@@ -256,7 +250,7 @@
               "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,
@@ -265,11 +259,17 @@
             "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": [
                   {
@@ -286,7 +286,7 @@
       "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": [
               {
diff --git a/data/models/openai_gpt-5.3-codex.json b/data/models/openai_gpt-5.3-codex.json
index 71af5af4fde2b8fad2d4e8ea66842bf1cb778d6d..65f8130b44c7c4318430a774c580739b4e8b1cab 100644
--- a/data/models/openai_gpt-5.3-codex.json
+++ b/data/models/openai_gpt-5.3-codex.json
@@ -4,13 +4,13 @@
     "id": "openai/gpt-5.3-codex",
     "developer": "OpenAI",
     "additional_details": {
-      "agent_name": "Terminus 2",
-      "agent_organization": "Terminal Bench"
+      "agent_name": "Mux",
+      "agent_organization": "Coder"
     }
   },
   "evaluations": [
     {
-      "evaluation_id": "terminal-bench-2.0/terminus-2__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",
@@ -34,7 +34,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2026-02-05",
+          "evaluation_timestamp": "2026-03-06",
           "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": 64.7,
+            "score": 74.6,
             "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 \"Terminus 2\" -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": [
                   {
@@ -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-5.3-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": [
               {
@@ -84,7 +84,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/simple-codex__gpt-5.3-codex/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/codebrain-1__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": "2026-02-06",
+          "evaluation_timestamp": "2026-02-10",
           "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": 75.1,
+            "score": 70.3,
             "uncertainty": {
               "standard_error": {
-                "value": 2.4
+                "value": 2.6
               },
               "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 \"CodeBrain-1\" -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 \"Simple Codex\" -m \"GPT-5.3-Codex\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"CodeBrain-1\" -m \"GPT-5.3-Codex\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -158,7 +158,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/droid__gpt-5.3-codex/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/terminus-2__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": "2026-02-24",
+          "evaluation_timestamp": "2026-02-05",
           "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": 77.3,
+            "score": 64.7,
             "uncertainty": {
               "standard_error": {
-                "value": 2.2
+                "value": 2.7
               },
               "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 \"Terminus 2\" -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 \"Droid\" -m \"GPT-5.3-Codex\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"GPT-5.3-Codex\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -232,7 +232,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/codebrain-1__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",
@@ -256,7 +256,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2026-02-10",
+          "evaluation_timestamp": "2026-02-06",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -265,17 +265,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 70.3,
+            "score": 75.1,
             "uncertainty": {
               "standard_error": {
-                "value": 2.6
+                "value": 2.4
               },
               "num_samples": 435
             }
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"CodeBrain-1\" -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": [
                   {
@@ -292,7 +292,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"CodeBrain-1\" -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": [
               {
@@ -306,7 +306,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/mux__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",
@@ -330,7 +330,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2026-03-06",
+          "evaluation_timestamp": "2026-02-24",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -339,17 +339,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 74.6,
+            "score": 77.3,
             "uncertainty": {
               "standard_error": {
-                "value": 2.5
+                "value": 2.2
               },
               "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 \"Droid\" -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 \"Mux\" -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": [
               {
diff --git a/data/models/openai_gpt-5.json b/data/models/openai_gpt-5.json
index 9d09df6c74b83cb2a4dd70946717742ac0b7c9f5..9005bf4e58d9a5ca4b1df67ba70d59695c801ffb 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": "OpenHands",
-      "agent_organization": "OpenHands"
+      "agent_name": "Mini-SWE-Agent",
+      "agent_organization": "Princeton"
     }
   },
   "evaluations": [
     {
-      "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",
@@ -34,7 +34,7 @@
               "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,
@@ -43,17 +43,17 @@
             "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": [
                   {
@@ -70,7 +70,7 @@
       "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": [
               {
@@ -84,7 +84,7 @@
       }
     },
     {
-      "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",
@@ -108,7 +108,7 @@
               "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,
@@ -117,17 +117,17 @@
             "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": [
                   {
@@ -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\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"OpenHands\" -m \"GPT-5\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -158,7 +158,7 @@
       }
     },
     {
-      "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",
@@ -182,7 +182,7 @@
               "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,
@@ -191,17 +191,17 @@
             "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": [
                   {
@@ -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\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"GPT-5\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
diff --git a/data/models/openai_gpt_5.2.json b/data/models/openai_gpt_5.2.json
index fec8e3d9659540e746cd368872cad0ec3c496416..e5de01feca478b0842db2b2533d006446492021b 100644
--- a/data/models/openai_gpt_5.2.json
+++ b/data/models/openai_gpt_5.2.json
@@ -7,10 +7,10 @@
   },
   "evaluations": [
     {
-      "evaluation_id": "ace/openai_gpt-5.2/1773260200",
+      "evaluation_id": "apex-agents/openai_gpt-5.2/1773260200",
       "retrieved_timestamp": "1773260200",
       "source_metadata": {
-        "source_name": "Mercor ACE Leaderboard",
+        "source_name": "Mercor APEX-Agents Leaderboard",
         "source_type": "evaluation_run",
         "source_organization_name": "Mercor",
         "source_organization_url": "https://www.mercor.com",
@@ -20,24 +20,24 @@
         "name": "archipelago",
         "version": "1.0.0"
       },
-      "benchmark": "ace",
+      "benchmark": "apex-agents",
       "evaluation_results": [
         {
-          "evaluation_name": "Overall Score",
+          "evaluation_name": "Overall Pass@1",
           "source_data": {
-            "dataset_name": "ace",
+            "dataset_name": "apex-agents",
             "source_type": "hf_dataset",
-            "hf_repo": "Mercor/ACE"
+            "hf_repo": "mercor/apex-agents"
           },
           "metric_config": {
-            "evaluation_description": "Overall ACE score across all consumer-task domains.",
+            "evaluation_description": "Overall Pass@1 (dataset card / paper snapshot).",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0,
             "max_score": 1
           },
           "score_details": {
-            "score": 0.515,
+            "score": 0.23,
             "uncertainty": {
               "confidence_interval": {
                 "lower": -0.032,
@@ -53,21 +53,28 @@
           }
         },
         {
-          "evaluation_name": "Food Score",
+          "evaluation_name": "Overall Pass@8",
           "source_data": {
-            "dataset_name": "ace",
+            "dataset_name": "apex-agents",
             "source_type": "hf_dataset",
-            "hf_repo": "Mercor/ACE"
+            "hf_repo": "mercor/apex-agents"
           },
           "metric_config": {
-            "evaluation_description": "Food domain score.",
+            "evaluation_description": "Overall Pass@8 (dataset card / paper snapshot).",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0,
             "max_score": 1
           },
           "score_details": {
-            "score": 0.65
+            "score": 0.4,
+            "uncertainty": {
+              "confidence_interval": {
+                "lower": -0.044,
+                "upper": 0.044,
+                "method": "bootstrap"
+              }
+            }
           },
           "generation_config": {
             "additional_details": {
@@ -76,75 +83,44 @@
           }
         },
         {
-          "evaluation_name": "Gaming Score",
+          "evaluation_name": "Overall Mean Score",
           "source_data": {
-            "dataset_name": "ace",
+            "dataset_name": "apex-agents",
             "source_type": "hf_dataset",
-            "hf_repo": "Mercor/ACE"
+            "hf_repo": "mercor/apex-agents"
           },
           "metric_config": {
-            "evaluation_description": "Gaming domain score.",
+            "evaluation_description": "Overall mean rubric score.",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0,
             "max_score": 1
           },
           "score_details": {
-            "score": 0.578
+            "score": 0.387
           },
           "generation_config": {
             "additional_details": {
               "run_setting": "High"
             }
           }
-        }
-      ],
-      "detailed_evaluation_results": null,
-      "generation_config": {
-        "additional_details": {
-          "run_setting": "High"
-        }
-      }
-    },
-    {
-      "evaluation_id": "apex-agents/openai_gpt-5.2/1773260200",
-      "retrieved_timestamp": "1773260200",
-      "source_metadata": {
-        "source_name": "Mercor APEX-Agents 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": "apex-agents",
-      "evaluation_results": [
+        },
         {
-          "evaluation_name": "Overall Pass@1",
+          "evaluation_name": "Investment Banking Pass@1",
           "source_data": {
             "dataset_name": "apex-agents",
             "source_type": "hf_dataset",
             "hf_repo": "mercor/apex-agents"
           },
           "metric_config": {
-            "evaluation_description": "Overall Pass@1 (dataset card / paper snapshot).",
+            "evaluation_description": "Investment banking world Pass@1.",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0,
             "max_score": 1
           },
           "score_details": {
-            "score": 0.23,
-            "uncertainty": {
-              "confidence_interval": {
-                "lower": -0.032,
-                "upper": 0.032,
-                "method": "bootstrap"
-              }
-            }
+            "score": 0.273
           },
           "generation_config": {
             "additional_details": {
@@ -153,28 +129,21 @@
           }
         },
         {
-          "evaluation_name": "Overall Pass@8",
+          "evaluation_name": "Management Consulting Pass@1",
           "source_data": {
             "dataset_name": "apex-agents",
             "source_type": "hf_dataset",
             "hf_repo": "mercor/apex-agents"
           },
           "metric_config": {
-            "evaluation_description": "Overall Pass@8 (dataset card / paper snapshot).",
+            "evaluation_description": "Management consulting world Pass@1.",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0,
             "max_score": 1
           },
           "score_details": {
-            "score": 0.4,
-            "uncertainty": {
-              "confidence_interval": {
-                "lower": -0.044,
-                "upper": 0.044,
-                "method": "bootstrap"
-              }
-            }
+            "score": 0.227
           },
           "generation_config": {
             "additional_details": {
@@ -183,21 +152,21 @@
           }
         },
         {
-          "evaluation_name": "Overall Mean Score",
+          "evaluation_name": "Corporate Law Pass@1",
           "source_data": {
             "dataset_name": "apex-agents",
             "source_type": "hf_dataset",
             "hf_repo": "mercor/apex-agents"
           },
           "metric_config": {
-            "evaluation_description": "Overall mean rubric score.",
+            "evaluation_description": "Corporate law world Pass@1.",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0,
             "max_score": 1
           },
           "score_details": {
-            "score": 0.387
+            "score": 0.189
           },
           "generation_config": {
             "additional_details": {
@@ -206,44 +175,75 @@
           }
         },
         {
-          "evaluation_name": "Investment Banking Pass@1",
+          "evaluation_name": "Corporate Lawyer Mean Score",
           "source_data": {
             "dataset_name": "apex-agents",
             "source_type": "hf_dataset",
             "hf_repo": "mercor/apex-agents"
           },
           "metric_config": {
-            "evaluation_description": "Investment banking world Pass@1.",
+            "evaluation_description": "Corporate lawyer world mean score.",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0,
             "max_score": 1
           },
           "score_details": {
-            "score": 0.273
+            "score": 0.443
           },
           "generation_config": {
             "additional_details": {
               "run_setting": "High"
             }
           }
-        },
+        }
+      ],
+      "detailed_evaluation_results": null,
+      "generation_config": {
+        "additional_details": {
+          "run_setting": "High"
+        }
+      }
+    },
+    {
+      "evaluation_id": "ace/openai_gpt-5.2/1773260200",
+      "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": "Management Consulting Pass@1",
+          "evaluation_name": "Overall Score",
           "source_data": {
-            "dataset_name": "apex-agents",
+            "dataset_name": "ace",
             "source_type": "hf_dataset",
-            "hf_repo": "mercor/apex-agents"
+            "hf_repo": "Mercor/ACE"
           },
           "metric_config": {
-            "evaluation_description": "Management consulting world Pass@1.",
+            "evaluation_description": "Overall ACE score across all consumer-task domains.",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0,
             "max_score": 1
           },
           "score_details": {
-            "score": 0.227
+            "score": 0.515,
+            "uncertainty": {
+              "confidence_interval": {
+                "lower": -0.032,
+                "upper": 0.032,
+                "method": "bootstrap"
+              }
+            }
           },
           "generation_config": {
             "additional_details": {
@@ -252,21 +252,21 @@
           }
         },
         {
-          "evaluation_name": "Corporate Law Pass@1",
+          "evaluation_name": "Food Score",
           "source_data": {
-            "dataset_name": "apex-agents",
+            "dataset_name": "ace",
             "source_type": "hf_dataset",
-            "hf_repo": "mercor/apex-agents"
+            "hf_repo": "Mercor/ACE"
           },
           "metric_config": {
-            "evaluation_description": "Corporate law world Pass@1.",
+            "evaluation_description": "Food domain score.",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0,
             "max_score": 1
           },
           "score_details": {
-            "score": 0.189
+            "score": 0.65
           },
           "generation_config": {
             "additional_details": {
@@ -275,21 +275,21 @@
           }
         },
         {
-          "evaluation_name": "Corporate Lawyer Mean Score",
+          "evaluation_name": "Gaming Score",
           "source_data": {
-            "dataset_name": "apex-agents",
+            "dataset_name": "ace",
             "source_type": "hf_dataset",
-            "hf_repo": "mercor/apex-agents"
+            "hf_repo": "Mercor/ACE"
           },
           "metric_config": {
-            "evaluation_description": "Corporate lawyer world mean score.",
+            "evaluation_description": "Gaming domain score.",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0,
             "max_score": 1
           },
           "score_details": {
-            "score": 0.443
+            "score": 0.578
           },
           "generation_config": {
             "additional_details": {
diff --git a/data/models/openai_o4-mini-2025-04-16.json b/data/models/openai_o4-mini-2025-04-16.json
index 751e567f80107ae7403958c0915864809e731407..2445a24c2417bbf08441a2388a2fba31fa9d6f49 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-2025-04-16/1760492095.8105888",
-      "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",
@@ -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 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
           }
         }
       ],
@@ -828,13 +828,13 @@
       "generation_config": null
     },
     {
-      "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",
@@ -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 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
           }
         }
       ],
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 cdfb6729d8ee2c00438e79bd148b5b9825fbce54..34afb9663c74112d98337da6fd83b3594c465f50 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-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",
@@ -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": 0.2653
-          },
-          "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"
           }
         }
       ],
@@ -159,10 +141,10 @@
       "generation_config": null
     },
     {
-      "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",
@@ -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": 0.615
+            "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"
           }
         }
       ],
diff --git a/data/models/openassistant_oasst-rm-2.1-pythia-1.4b-epoch-2.5.json b/data/models/openassistant_oasst-rm-2.1-pythia-1.4b-epoch-2.5.json
index 4f200b5bed952e0790f7951e7076e297510a1c46..d028cad4784e7392a6a614670c5c27a9b8900f31 100644
--- a/data/models/openassistant_oasst-rm-2.1-pythia-1.4b-epoch-2.5.json
+++ b/data/models/openassistant_oasst-rm-2.1-pythia-1.4b-epoch-2.5.json
@@ -9,10 +9,10 @@
   },
   "evaluations": [
     {
-      "evaluation_id": "reward-bench-2/OpenAssistant_oasst-rm-2.1-pythia-1.4b-epoch-2.5/1766412838.146816",
+      "evaluation_id": "reward-bench/OpenAssistant_oasst-rm-2.1-pythia-1.4b-epoch-2.5/1766412838.146816",
       "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": 0.2648
-          },
-          "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": 0.3179
+            "score": 0.6901
           },
           "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": 0.2625
+            "score": 0.8855
           },
           "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": 0.3934
+            "score": 0.4868
           },
           "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": 0.3244
+            "score": 0.6311
           },
           "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": 0.2707
+            "score": 0.7752
           },
           "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": 0.0198
+            "score": 0.6533
           },
           "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/OpenAssistant_oasst-rm-2.1-pythia-1.4b-epoch-2.5/1766412838.146816",
+      "evaluation_id": "reward-bench-2/OpenAssistant_oasst-rm-2.1-pythia-1.4b-epoch-2.5/1766412838.146816",
       "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": 0.6901
+            "score": 0.2648
           },
           "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": 0.8855
+            "score": 0.3179
           },
           "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": 0.4868
+            "score": 0.2625
           },
           "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": 0.3934
+          },
+          "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": 0.6311
+            "score": 0.3244
           },
           "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": 0.7752
+            "score": 0.2707
           },
           "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": 0.6533
+            "score": 0.0198
           },
           "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/openassistant_reward-model-deberta-v3-large-v2.json b/data/models/openassistant_reward-model-deberta-v3-large-v2.json
index cf1ba02f6dd573bf3e0770ff614660b73e92dbb8..b28ca5c5700af0f5cf22d77dcb1c4fea033ecc2d 100644
--- a/data/models/openassistant_reward-model-deberta-v3-large-v2.json
+++ b/data/models/openassistant_reward-model-deberta-v3-large-v2.json
@@ -9,10 +9,10 @@
   },
   "evaluations": [
     {
-      "evaluation_id": "reward-bench-2/OpenAssistant_reward-model-deberta-v3-large-v2/1766412838.146816",
+      "evaluation_id": "reward-bench/OpenAssistant_reward-model-deberta-v3-large-v2/1766412838.146816",
       "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": 0.32
-          },
-          "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": 0.3853
+            "score": 0.6126
           },
           "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": 0.2687
+            "score": 0.8939
           },
           "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": 0.5027
+            "score": 0.4518
           },
           "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": 0.3667
+            "score": 0.7338
           },
           "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": 0.2768
+            "score": 0.3855
           },
           "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": 0.12
+            "score": 0.5836
           },
           "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/OpenAssistant_reward-model-deberta-v3-large-v2/1766412838.146816",
+      "evaluation_id": "reward-bench-2/OpenAssistant_reward-model-deberta-v3-large-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",
@@ -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": 0.6126
+            "score": 0.32
           },
           "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": 0.8939
+            "score": 0.3853
           },
           "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": 0.4518
+            "score": 0.2687
           },
           "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": 0.5027
+          },
+          "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": 0.7338
+            "score": 0.3667
           },
           "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": 0.3855
+            "score": 0.2768
           },
           "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": 0.5836
+            "score": 0.12
           },
           "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/openbmb_eurus-rm-7b.json b/data/models/openbmb_eurus-rm-7b.json
index e1154a660c89f219cec7ec844602d9d8fdfa08ad..44637ca17276f082725f61866dcfa3229cc54274 100644
--- a/data/models/openbmb_eurus-rm-7b.json
+++ b/data/models/openbmb_eurus-rm-7b.json
@@ -9,10 +9,10 @@
   },
   "evaluations": [
     {
-      "evaluation_id": "reward-bench-2/openbmb_Eurus-RM-7b/1766412838.146816",
+      "evaluation_id": "reward-bench/openbmb_Eurus-RM-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": 0.5806
-          },
-          "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": 0.6
+            "score": 0.8159
           },
           "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": 0.9804
           },
           "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": 0.5683
+            "score": 0.6557
           },
           "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": 0.6267
+            "score": 0.8135
           },
           "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": 0.7475
+            "score": 0.8633
           },
           "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": 0.5972
+            "score": 0.7172
           },
           "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/openbmb_Eurus-RM-7b/1766412838.146816",
+      "evaluation_id": "reward-bench-2/openbmb_Eurus-RM-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": 0.8159
+            "score": 0.5806
           },
           "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": 0.9804
+            "score": 0.6
           },
           "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": 0.6557
+            "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": 0.5683
+          },
+          "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": 0.8135
+            "score": 0.6267
           },
           "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": 0.8633
+            "score": 0.7475
           },
           "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": 0.7172
+            "score": 0.5972
           },
           "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/openbmb_ultrarm-13b.json b/data/models/openbmb_ultrarm-13b.json
index c52a509adb327ccd9798d5a844c78601940ebb17..84bdd483e26f91976f0250093c6ea14b4f0ff97c 100644
--- a/data/models/openbmb_ultrarm-13b.json
+++ b/data/models/openbmb_ultrarm-13b.json
@@ -9,10 +9,10 @@
   },
   "evaluations": [
     {
-      "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",
@@ -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": 0.4683
-          },
-          "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"
           }
         }
       ],
@@ -159,10 +141,10 @@
       "generation_config": null
     },
     {
-      "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",
@@ -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": 0.6903
+            "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"
           }
         }
       ],
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 adf890d6a20deeb5311651870c4e5638866b9733..ee66fd95461643d78856676dc7b45eb953fc109f 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-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",
@@ -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": 0.1606
-          },
-          "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"
           }
         }
       ],
@@ -159,10 +141,10 @@
       "generation_config": null
     },
     {
-      "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",
@@ -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": 0.4727
+            "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"
           }
         }
       ],
diff --git a/data/models/primeintellect_intellect-1.json b/data/models/primeintellect_intellect-1.json
index 7d9ec915394b34f60309abc9ed073a5aa8bce5ab..b8fa0710a43fde559062289de677b131f6527599 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": "float16",
+      "precision": "bfloat16",
       "architecture": "LlamaForCausalLM",
       "params_billions": "10.211"
     }
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.274
+            "score": 0.276
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.25
+            "score": 0.2534
           }
         },
         {
@@ -116,7 +116,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3753
+            "score": 0.3339
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.112
+            "score": 0.1123
           }
         }
       ],
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.276
+            "score": 0.274
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2534
+            "score": 0.25
           }
         },
         {
@@ -246,7 +246,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3339
+            "score": 0.3753
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1123
+            "score": 0.112
           }
         }
       ],
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 e065032f9e09241e38d49be10f5ffa3d463b4775..a2239eea28a466521ab226132351f6bc4c958619 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
@@ -5,12 +5,142 @@
     "developer": "princeton-nlp",
     "inference_platform": "unknown",
     "additional_details": {
-      "precision": "bfloat16",
+      "precision": "float16",
       "architecture": "LlamaForCausalLM",
       "params_billions": "8.03"
     }
   },
   "evaluations": [
+    {
+      "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
+    },
     {
       "evaluation_id": "hfopenllm_v2/princeton-nlp_Llama-3-8B-ProLong-512k-Instruct/1773936498.240187",
       "retrieved_timestamp": "1773936498.240187",
diff --git a/data/models/prithivmlmods_calcium-opus-14b-elite.json b/data/models/prithivmlmods_calcium-opus-14b-elite.json
index 89a0dd9277acb0b40655f39809af8ab4d96076ef..746fd41957e7795e0f0f3751181ce9bfef3d8e70 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": "bfloat16",
+      "precision": "float16",
       "architecture": "Qwen2ForCausalLM",
       "params_billions": "14.766"
     }
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6052
+            "score": 0.6064
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6317
+            "score": 0.6296
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4789
+            "score": 0.3708
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3742
+            "score": 0.3733
           }
         },
         {
@@ -116,7 +116,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.486
+            "score": 0.4873
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5302
+            "score": 0.5307
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6064
+            "score": 0.6052
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6296
+            "score": 0.6317
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3708
+            "score": 0.4789
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3733
+            "score": 0.3742
           }
         },
         {
@@ -246,7 +246,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4873
+            "score": 0.486
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5307
+            "score": 0.5302
           }
         }
       ],
diff --git a/data/models/qingy2019_oracle-14b.json b/data/models/qingy2019_oracle-14b.json
index 22bb2fc596a8b7a91dfafd1db7c00009286e84b4..8fc1dd082923a347043a18d5c18fb5d4904fae42 100644
--- a/data/models/qingy2019_oracle-14b.json
+++ b/data/models/qingy2019_oracle-14b.json
@@ -5,7 +5,7 @@
     "developer": "qingy2019",
     "inference_platform": "unknown",
     "additional_details": {
-      "precision": "float16",
+      "precision": "bfloat16",
       "architecture": "MixtralForCausalLM",
       "params_billions": "13.668"
     }
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2358
+            "score": 0.2401
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4612
+            "score": 0.4622
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0642
+            "score": 0.0725
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2576
+            "score": 0.2609
           }
         },
         {
@@ -116,7 +116,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3717
+            "score": 0.3703
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2382
+            "score": 0.2379
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2401
+            "score": 0.2358
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4622
+            "score": 0.4612
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0725
+            "score": 0.0642
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2609
+            "score": 0.2576
           }
         },
         {
@@ -246,7 +246,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3703
+            "score": 0.3717
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2379
+            "score": 0.2382
           }
         }
       ],
diff --git a/data/models/qingy2019_qwen2.5-math-14b-instruct.json b/data/models/qingy2019_qwen2.5-math-14b-instruct.json
index 21a12461d0cce8974037575db54605a0da19b661..d07b0024c79975f453423bba6d277d902ff3056c 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": "bfloat16",
+      "precision": "float16",
       "architecture": "Qwen2ForCausalLM",
       "params_billions": "14.0"
     }
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6005
+            "score": 0.6066
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6356
+            "score": 0.635
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2764
+            "score": 0.3716
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3691
+            "score": 0.3725
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5339
+            "score": 0.5331
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6066
+            "score": 0.6005
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.635
+            "score": 0.6356
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3716
+            "score": 0.2764
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3725
+            "score": 0.3691
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5331
+            "score": 0.5339
           }
         }
       ],
diff --git a/data/models/quazim0t0_odb-14b-sce.json b/data/models/quazim0t0_odb-14b-sce.json
index 0894dd13c3bc882b56c1b90b77e354b0b8fcf1b3..b2854fae2e7ea9ad5a32eb4ec453ef9c1365f1b7 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": "Unknown",
-      "params_billions": "0.0",
+      "architecture": "LlamaForCausalLM",
+      "params_billions": "14.66",
       "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": 0.2922
+            "score": 0.7016
           }
         },
         {
@@ -65,7 +65,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6559
+            "score": 0.6942
           }
         },
         {
@@ -83,7 +83,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2545
+            "score": 0.4116
           }
         },
         {
@@ -101,7 +101,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2659
+            "score": 0.3624
           }
         },
         {
@@ -119,7 +119,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3929
+            "score": 0.4571
           }
         },
         {
@@ -137,7 +137,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5207
+            "score": 0.5411
           }
         }
       ],
@@ -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": 0.7016
+            "score": 0.2922
           }
         },
         {
@@ -195,7 +195,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6942
+            "score": 0.6559
           }
         },
         {
@@ -213,7 +213,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4116
+            "score": 0.2545
           }
         },
         {
@@ -231,7 +231,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3624
+            "score": 0.2659
           }
         },
         {
@@ -249,7 +249,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4571
+            "score": 0.3929
           }
         },
         {
@@ -267,7 +267,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5411
+            "score": 0.5207
           }
         }
       ],
diff --git a/data/models/qwen_qwen2.5-coder-7b-instruct.json b/data/models/qwen_qwen2.5-coder-7b-instruct.json
index 0cdcd4044d4f077bb1870a78d07a83c3bbc7d0d0..96b0a8af52fb442affa2ad7ba1ed017d80ec2231 100644
--- a/data/models/qwen_qwen2.5-coder-7b-instruct.json
+++ b/data/models/qwen_qwen2.5-coder-7b-instruct.json
@@ -5,7 +5,7 @@
     "developer": "Qwen",
     "inference_platform": "unknown",
     "additional_details": {
-      "precision": "float16",
+      "precision": "bfloat16",
       "architecture": "Qwen2ForCausalLM",
       "params_billions": "7.616"
     }
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6147
+            "score": 0.6101
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4999
+            "score": 0.5008
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.031
+            "score": 0.3716
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2936
+            "score": 0.2919
           }
         },
         {
@@ -116,7 +116,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4099
+            "score": 0.4073
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3354
+            "score": 0.3352
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6101
+            "score": 0.6147
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5008
+            "score": 0.4999
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3716
+            "score": 0.031
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2919
+            "score": 0.2936
           }
         },
         {
@@ -246,7 +246,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4073
+            "score": 0.4099
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3352
+            "score": 0.3354
           }
         }
       ],
diff --git a/data/models/ray2333_grm-llama3-8b-distill.json b/data/models/ray2333_grm-llama3-8b-distill.json
index a698e2dc0120e472c95dbd375c2ce72c243acf20..28bee941f1d39ce464ca73210ca8cbef67a5d082 100644
--- a/data/models/ray2333_grm-llama3-8b-distill.json
+++ b/data/models/ray2333_grm-llama3-8b-distill.json
@@ -9,10 +9,10 @@
   },
   "evaluations": [
     {
-      "evaluation_id": "reward-bench/Ray2333_GRM-llama3-8B-distill/1766412838.146816",
+      "evaluation_id": "reward-bench-2/Ray2333_GRM-llama3-8B-distill/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": 0.8464
+            "score": 0.589
           },
           "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": 0.9832
+            "score": 0.5874
           },
           "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": 0.6842
+            "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": 0.5902
+          },
+          "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": 0.7222
           },
           "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": 0.9133
+            "score": 0.6727
           },
           "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": 0.7209
+            "score": 0.5743
           },
           "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/Ray2333_GRM-llama3-8B-distill/1766412838.146816",
+      "evaluation_id": "reward-bench/Ray2333_GRM-llama3-8B-distill/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": 0.589
-          },
-          "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": 0.5874
+            "score": 0.8464
           },
           "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": 0.9832
           },
           "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": 0.5902
+            "score": 0.6842
           },
           "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": 0.7222
+            "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": 0.6727
+            "score": 0.9133
           },
           "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": 0.5743
+            "score": 0.7209
           },
           "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 bd70639489991e3e8880cad041284119bd35ecc9..15f35c842dfd5169bfd85bae53f76a90d5850421 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/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",
@@ -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": 0.8542
+            "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"
           }
         }
       ],
@@ -141,10 +159,10 @@
       "generation_config": null
     },
     {
-      "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",
@@ -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": 0.6089
-          },
-          "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"
           }
         }
       ],
diff --git a/data/models/rombodawg_rombos-llm-v2.5.1-qwen-3b.json b/data/models/rombodawg_rombos-llm-v2.5.1-qwen-3b.json
index 12ab734b7e3e0cffe5b67bb178df3f51d09ec598..9d341a3c927e4d25f7836c99807ee069a16cbedc 100644
--- a/data/models/rombodawg_rombos-llm-v2.5.1-qwen-3b.json
+++ b/data/models/rombodawg_rombos-llm-v2.5.1-qwen-3b.json
@@ -5,7 +5,7 @@
     "developer": "rombodawg",
     "inference_platform": "unknown",
     "additional_details": {
-      "precision": "float16",
+      "precision": "bfloat16",
       "architecture": "Qwen2ForCausalLM",
       "params_billions": "3.397"
     }
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2566
+            "score": 0.2595
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.39
+            "score": 0.3884
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1208
+            "score": 0.0914
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2626
+            "score": 0.2743
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2741
+            "score": 0.2719
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2595
+            "score": 0.2566
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3884
+            "score": 0.39
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0914
+            "score": 0.1208
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2743
+            "score": 0.2626
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2719
+            "score": 0.2741
           }
         }
       ],
diff --git a/data/models/sfairxc_fsfairx-llama3-rm-v0.1.json b/data/models/sfairxc_fsfairx-llama3-rm-v0.1.json
index 83ff30916d3f35c6333d5f652927c45d63836756..ecef2ed14b1e2210796bfe9e4943404f7ebd3b7c 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/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",
@@ -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": 0.8338
+            "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"
           }
         }
       ],
@@ -141,10 +159,10 @@
       "generation_config": null
     },
     {
-      "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",
@@ -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": 0.6292
-          },
-          "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"
           }
         }
       ],
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 4a85b178092e7e5acaf395eb054cb8adc61e2891..988f599afd76311b87e49f16160d0ca534436cdd 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/ShikaiChen_LDL-Reward-Gemma-2-27B-v0.1/1766412838.146816",
+      "evaluation_id": "reward-bench-2/ShikaiChen_LDL-Reward-Gemma-2-27B-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",
@@ -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": 0.9499
+            "score": 0.7249
           },
           "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": 0.7558
           },
           "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": 0.9079
+            "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": 0.9378
+            "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": "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": 0.9903
+            "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/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": "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": 0.7249
+            "score": 0.9131
           },
           "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": 0.7558
+            "score": 0.7633
           },
           "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": "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": 0.9499
           },
           "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": "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": 0.6448
+            "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": 0.9222
+            "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": "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": 0.9131
+            "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": "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": 0.7633
+            "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"
           }
         }
       ],
diff --git a/data/models/skywork_skywork-reward-gemma-2-27b-v0.2.json b/data/models/skywork_skywork-reward-gemma-2-27b-v0.2.json
index 4109d07feac30d842a656539e17ae764cf441c79..52952d2b07ce3bbc9c007749585e45b758ae4213 100644
--- a/data/models/skywork_skywork-reward-gemma-2-27b-v0.2.json
+++ b/data/models/skywork_skywork-reward-gemma-2-27b-v0.2.json
@@ -142,10 +142,10 @@
       "generation_config": null
     },
     {
-      "evaluation_id": "reward-bench-2/Skywork_Skywork-Reward-Gemma-2-27B-v0.2/1766412838.146816",
+      "evaluation_id": "reward-bench/Skywork_Skywork-Reward-Gemma-2-27B-v0.2/1766412838.146816",
       "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",
@@ -164,104 +164,128 @@
         {
           "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": 0.7531
+            "score": 0.9426
           },
           "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": 0.7674
+            "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": 0.375
+            "score": 0.8991
           },
           "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": 0.6721
+            "score": 0.9297
           },
           "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": 0.9689
+            "score": 0.9807
           },
           "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/Skywork_Skywork-Reward-Gemma-2-27B-v0.2/1766412838.146816",
+      "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": 0.9172
+            "score": 0.7531
           },
           "source_data": {
             "dataset_name": "RewardBench 2",
@@ -270,135 +294,111 @@
           }
         },
         {
-          "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": 0.8182
+            "score": 0.7674
           },
           "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-v0.2/1766412838.146816",
-      "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": 0.9426
+            "score": 0.375
           },
           "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": 0.6721
           },
           "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": 0.8991
+            "score": 0.9689
           },
           "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": 0.9297
+            "score": 0.9172
           },
           "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": 0.9807
+            "score": 0.8182
           },
           "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-llama-3.1-8b.json b/data/models/skywork_skywork-reward-llama-3.1-8b.json
index d700e3f49377a01e2f9d11b4773879e002a65e98..dedd0015bc30c7a59cc8db5e1fbdb3b6b6cbc978 100644
--- a/data/models/skywork_skywork-reward-llama-3.1-8b.json
+++ b/data/models/skywork_skywork-reward-llama-3.1-8b.json
@@ -9,10 +9,10 @@
   },
   "evaluations": [
     {
-      "evaluation_id": "reward-bench-2/Skywork_Skywork-Reward-Llama-3.1-8B/1766412838.146816",
+      "evaluation_id": "reward-bench/Skywork_Skywork-Reward-Llama-3.1-8B/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": 0.7314
+            "score": 0.9252
           },
           "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": 0.6989
+            "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": "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": 0.425
+            "score": 0.8728
           },
           "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": 0.6284
+            "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": "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": 0.9333
+            "score": 0.962
           },
           "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/Skywork_Skywork-Reward-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": "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": 0.9616
+            "score": 0.7314
           },
           "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": 0.741
+            "score": 0.6989
           },
           "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-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": "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": 0.9252
+            "score": 0.425
           },
           "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": 0.9581
+            "score": 0.6284
           },
           "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": 0.8728
+            "score": 0.9333
           },
           "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": 0.9081
+            "score": 0.9616
           },
           "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": 0.962
+            "score": 0.741
           },
           "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/tanliboy_lambda-gemma-2-9b-dpo.json b/data/models/tanliboy_lambda-gemma-2-9b-dpo.json
index 5d50cd0f56f0ac33470efc8c81f51c02a702598e..7fb384620bce09b34b0d31ff763d2b1e971d0558 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": "float16",
+      "precision": "bfloat16",
       "architecture": "Gemma2ForCausalLM",
       "params_billions": "9.242"
     }
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4501
+            "score": 0.1829
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5472
+            "score": 0.5488
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0944
+            "score": 0.0
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3138
+            "score": 0.3104
           }
         },
         {
@@ -116,7 +116,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4017
+            "score": 0.4056
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3792
+            "score": 0.3805
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1829
+            "score": 0.4501
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5488
+            "score": 0.5472
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0
+            "score": 0.0944
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3104
+            "score": 0.3138
           }
         },
         {
@@ -246,7 +246,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4056
+            "score": 0.4017
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3805
+            "score": 0.3792
           }
         }
       ],
diff --git a/data/models/valiantlabs_llama3.1-8b-cobalt.json b/data/models/valiantlabs_llama3.1-8b-cobalt.json
index e1d1a85c95f8deab607165ea40b9f93f0dba9c6d..c47cbaf67f9d28f7ee6c973b80a6e624aec4a0cc 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": "bfloat16",
+      "precision": "float16",
       "architecture": "LlamaForCausalLM",
       "params_billions": "8.03"
     }
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7168
+            "score": 0.3496
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4911
+            "score": 0.4947
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1533
+            "score": 0.1269
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2861
+            "score": 0.3037
           }
         },
         {
@@ -116,7 +116,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3512
+            "score": 0.3959
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3663
+            "score": 0.3644
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3496
+            "score": 0.7168
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4947
+            "score": 0.4911
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1269
+            "score": 0.1533
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3037
+            "score": 0.2861
           }
         },
         {
@@ -246,7 +246,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3959
+            "score": 0.3512
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3644
+            "score": 0.3663
           }
         }
       ],
diff --git a/data/models/valiantlabs_llama3.1-8b-shiningvaliant2.json b/data/models/valiantlabs_llama3.1-8b-shiningvaliant2.json
index f3e37b204fa779a9e21a0521a813b464c3fe641b..0736460b872bea97a209be68cef1f113fa7d9f3d 100644
--- a/data/models/valiantlabs_llama3.1-8b-shiningvaliant2.json
+++ b/data/models/valiantlabs_llama3.1-8b-shiningvaliant2.json
@@ -5,7 +5,7 @@
     "developer": "ValiantLabs",
     "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": 0.6496
+            "score": 0.2678
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4774
+            "score": 0.4429
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0566
+            "score": 0.0521
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3104
+            "score": 0.302
           }
         },
         {
@@ -116,7 +116,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3909
+            "score": 0.3959
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3382
+            "score": 0.2927
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2678
+            "score": 0.6496
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4429
+            "score": 0.4774
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0521
+            "score": 0.0566
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.302
+            "score": 0.3104
           }
         },
         {
@@ -246,7 +246,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3959
+            "score": 0.3909
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2927
+            "score": 0.3382
           }
         }
       ],
diff --git a/data/models/xai_grok-4-0709.json b/data/models/xai_grok-4-0709.json
index ed63df2424f42d0db9790c340d534a65bcfb0c8a..c9c4c964a3fc0712105da9d9e183b32a52cc54bc 100644
--- a/data/models/xai_grok-4-0709.json
+++ b/data/models/xai_grok-4-0709.json
@@ -10,8 +10,8 @@
   },
   "evaluations": [
     {
-      "evaluation_id": "global-mmlu-lite/xai_grok-4-0709/1773936496.366405",
-      "retrieved_timestamp": "1773936496.366405",
+      "evaluation_id": "global-mmlu-lite/xai_grok-4-0709/1773936583.743359",
+      "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/xai_grok-4-0709/1773936583.743359",
-      "retrieved_timestamp": "1773936583.743359",
+      "evaluation_id": "global-mmlu-lite/xai_grok-4-0709/1773936496.366405",
+      "retrieved_timestamp": "1773936496.366405",
       "source_metadata": {
         "source_name": "Global MMLU Lite Leaderboard",
         "source_type": "documentation",
diff --git a/data/models/xai_grok-4.json b/data/models/xai_grok-4.json
index 8fb7b1b24e602a14c14ed4217ea5e7cd9fdf0b69..1a7ae0a5e37faeab9841b8816b2f9d9332f7d639 100644
--- a/data/models/xai_grok-4.json
+++ b/data/models/xai_grok-4.json
@@ -4,13 +4,13 @@
     "id": "xai/grok-4",
     "developer": "xAI",
     "additional_details": {
-      "agent_name": "OpenHands",
-      "agent_organization": "OpenHands"
+      "agent_name": "Terminus 2",
+      "agent_organization": "Terminal Bench"
     }
   },
   "evaluations": [
     {
-      "evaluation_id": "terminal-bench-2.0/openhands__grok-4/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/terminus-2__grok-4/1773776901.772108",
       "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": "2025-10-31",
           "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": 27.2,
+            "score": 23.1,
             "uncertainty": {
               "standard_error": {
-                "value": 3.1
+                "value": 2.9
               },
               "num_samples": 435
             }
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"OpenHands\" -m \"Grok 4\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"Grok 4\" -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 \"Grok 4\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"Grok 4\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -84,7 +84,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/mini-swe-agent__grok-4/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/openhands__grok-4/1773776901.772108",
       "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": "2025-11-02",
           "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": 25.4,
+            "score": 27.2,
             "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 \"Grok 4\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"OpenHands\" -m \"Grok 4\" -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 \"Grok 4\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"OpenHands\" -m \"Grok 4\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -158,7 +158,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/terminus-2__grok-4/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/mini-swe-agent__grok-4/1773776901.772108",
       "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": "2025-11-03",
           "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": 23.1,
+            "score": 25.4,
             "uncertainty": {
               "standard_error": {
                 "value": 2.9
@@ -201,7 +201,7 @@
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"Grok 4\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Mini-SWE-Agent\" -m \"Grok 4\" -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 \"Grok 4\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Mini-SWE-Agent\" -m \"Grok 4\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
diff --git a/data/models/yam-peleg_hebrew-mistral-7b-200k.json b/data/models/yam-peleg_hebrew-mistral-7b-200k.json
index baae674a05af479a549c721b22d1c0240e173193..1a70a6eb9b375af7d3ae622e407043222ccb78a0 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": "float16",
+      "precision": "bfloat16",
       "architecture": "MistralForCausalLM",
       "params_billions": "7.504"
     }
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1856
+            "score": 0.177
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4149
+            "score": 0.3411
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0234
+            "score": 0.031
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.276
+            "score": 0.2534
           }
         },
         {
@@ -116,7 +116,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3765
+            "score": 0.374
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2573
+            "score": 0.2529
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.177
+            "score": 0.1856
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3411
+            "score": 0.4149
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.031
+            "score": 0.0234
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2534
+            "score": 0.276
           }
         },
         {
@@ -246,7 +246,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.374
+            "score": 0.3765
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2529
+            "score": 0.2573
           }
         }
       ],
diff --git a/data/models/ycros_bagelmisterytour-v2-8x7b.json b/data/models/ycros_bagelmisterytour-v2-8x7b.json
index ba69aabd10b1f09ccc48e0969d876027b03e3a4b..c7b7f840ab350df665db2f8b289c03a4556651c3 100644
--- a/data/models/ycros_bagelmisterytour-v2-8x7b.json
+++ b/data/models/ycros_bagelmisterytour-v2-8x7b.json
@@ -5,7 +5,7 @@
     "developer": "ycros",
     "inference_platform": "unknown",
     "additional_details": {
-      "precision": "bfloat16",
+      "precision": "float16",
       "architecture": "MixtralForCausalLM",
       "params_billions": "46.703"
     }
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6262
+            "score": 0.5994
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5142
+            "score": 0.5159
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0937
+            "score": 0.0785
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3079
+            "score": 0.3045
           }
         },
         {
@@ -116,7 +116,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4138
+            "score": 0.4203
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3481
+            "score": 0.3473
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5994
+            "score": 0.6262
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5159
+            "score": 0.5142
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0785
+            "score": 0.0937
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3045
+            "score": 0.3079
           }
         },
         {
@@ -246,7 +246,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4203
+            "score": 0.4138
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3473
+            "score": 0.3481
           }
         }
       ],
diff --git a/data/models/zhipu-ai_glm-4.7.json b/data/models/zhipu-ai_glm-4.7.json
index 9ffeed9fa5797e0518c941376cc795f418b5ed1c..ef6efd4fd9091259b58749fefdf86e2517723096 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": "Crux",
-      "agent_organization": "Roam"
+      "agent_name": "Terminus 2",
+      "agent_organization": "Terminal Bench"
     }
   },
   "evaluations": [
     {
-      "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",
@@ -34,7 +34,7 @@
               "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,
@@ -43,17 +43,17 @@
             "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": [
                   {
@@ -70,7 +70,7 @@
       "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": [
               {
@@ -84,7 +84,7 @@
       }
     },
     {
-      "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",
@@ -108,7 +108,7 @@
               "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,
@@ -117,17 +117,17 @@
             "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": [
                   {
@@ -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 \"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": [
               {