diff --git a/data/benchmarks/appworld_test_normal.json b/data/benchmarks/appworld_test_normal.json
index f3651490370442b9e2747ece9b07271eac5de3ad..4b1f2e226ce0f177163e0b4f9252a3d5461ce07f 100644
--- a/data/benchmarks/appworld_test_normal.json
+++ b/data/benchmarks/appworld_test_normal.json
@@ -5,7 +5,7 @@
       "name": "claude-opus-4-5",
       "developer": "Anthropic",
       "scores": {
-        "appworld/test_normal": 0.64
+        "appworld/test_normal": 0.66
       }
     },
     {
@@ -13,7 +13,7 @@
       "name": "gemini-3-pro-preview",
       "developer": "Google",
       "scores": {
-        "appworld/test_normal": 0.13
+        "appworld/test_normal": 0.36
       }
     },
     {
@@ -21,7 +21,7 @@
       "name": "gpt-5.2-2025-12-11",
       "developer": "OpenAI",
       "scores": {
-        "appworld/test_normal": 0.0
+        "appworld/test_normal": 0.071
       }
     }
   ]
diff --git a/data/benchmarks/browsecompplus.json b/data/benchmarks/browsecompplus.json
index 130d44f42fc301b55e5c6bce906e1c1263721368..613b29235acc848a4b6fbc21b6e89e5e195bd256 100644
--- a/data/benchmarks/browsecompplus.json
+++ b/data/benchmarks/browsecompplus.json
@@ -21,7 +21,7 @@
       "name": "gpt-5.2-2025-12-11",
       "developer": "OpenAI",
       "scores": {
-        "browsecompplus": 0.48
+        "browsecompplus": 0.46
       }
     }
   ]
diff --git a/data/benchmarks/hfopenllm_v2.json b/data/benchmarks/hfopenllm_v2.json
index 589e88495313e5113fd7851135b88baeeba06feb..f63d6b4e97df8ea6a39802305cc7efdb2683daed 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": 0.4511,
-        "BBH": 0.4275,
-        "MATH Level 5": 0.1473,
-        "GPQA": 0.2701,
-        "MUSR": 0.3623,
-        "MMLU-PRO": 0.2806
+        "IFEval": 0.4605,
+        "BBH": 0.4258,
+        "MATH Level 5": 0.0748,
+        "GPQA": 0.2659,
+        "MUSR": 0.3636,
+        "MMLU-PRO": 0.2812
       }
     },
     {
@@ -1747,12 +1747,12 @@
       "name": "NeuralDaredevil-SuperNova-Lite-7B-DARETIES-abliterated",
       "developer": "BoltMonkey",
       "scores": {
-        "IFEval": 0.459,
-        "BBH": 0.5185,
-        "MATH Level 5": 0.0937,
-        "GPQA": 0.2743,
-        "MUSR": 0.4083,
-        "MMLU-PRO": 0.3631
+        "IFEval": 0.7999,
+        "BBH": 0.5152,
+        "MATH Level 5": 0.1193,
+        "GPQA": 0.281,
+        "MUSR": 0.4019,
+        "MMLU-PRO": 0.3733
       }
     },
     {
@@ -2176,12 +2176,12 @@
       "name": "LION-Gemma-2b-dpo-v1.0",
       "developer": "Columbia-NLP",
       "scores": {
-        "IFEval": 0.3278,
-        "BBH": 0.392,
-        "MATH Level 5": 0.0431,
-        "GPQA": 0.2492,
-        "MUSR": 0.412,
-        "MMLU-PRO": 0.1666
+        "IFEval": 0.3102,
+        "BBH": 0.3881,
+        "MATH Level 5": 0.0536,
+        "GPQA": 0.2534,
+        "MUSR": 0.4081,
+        "MMLU-PRO": 0.1665
       }
     },
     {
@@ -3125,12 +3125,12 @@
       "name": "DocumentCogito",
       "developer": "Daemontatox",
       "scores": {
-        "IFEval": 0.777,
-        "BBH": 0.5187,
-        "MATH Level 5": 0.2198,
-        "GPQA": 0.2936,
-        "MUSR": 0.3911,
-        "MMLU-PRO": 0.3738
+        "IFEval": 0.5064,
+        "BBH": 0.5112,
+        "MATH Level 5": 0.1631,
+        "GPQA": 0.3163,
+        "MUSR": 0.3973,
+        "MMLU-PRO": 0.3802
       }
     },
     {
@@ -3229,12 +3229,12 @@
       "name": "PathfinderAI",
       "developer": "Daemontatox",
       "scores": {
-        "IFEval": 0.4855,
-        "BBH": 0.6627,
-        "MATH Level 5": 0.4841,
-        "GPQA": 0.3096,
-        "MUSR": 0.4256,
-        "MMLU-PRO": 0.5542
+        "IFEval": 0.3745,
+        "BBH": 0.6668,
+        "MATH Level 5": 0.4758,
+        "GPQA": 0.3943,
+        "MUSR": 0.4858,
+        "MMLU-PRO": 0.5593
       }
     },
     {
@@ -4321,12 +4321,12 @@
       "name": "Llama-3.1-8b-ITA",
       "developer": "DeepMount00",
       "scores": {
-        "IFEval": 0.7917,
-        "BBH": 0.5109,
-        "MATH Level 5": 0.1088,
-        "GPQA": 0.2878,
-        "MUSR": 0.4136,
-        "MMLU-PRO": 0.3876
+        "IFEval": 0.5365,
+        "BBH": 0.517,
+        "MATH Level 5": 0.1707,
+        "GPQA": 0.3062,
+        "MUSR": 0.4487,
+        "MMLU-PRO": 0.396
       }
     },
     {
@@ -4646,12 +4646,12 @@
       "name": "MN-12B-LilithFrame",
       "developer": "DoppelReflEx",
       "scores": {
-        "IFEval": 0.451,
-        "BBH": 0.4944,
-        "MATH Level 5": 0.1156,
-        "GPQA": 0.3196,
-        "MUSR": 0.3896,
-        "MMLU-PRO": 0.3256
+        "IFEval": 0.436,
+        "BBH": 0.4956,
+        "MATH Level 5": 0.0589,
+        "GPQA": 0.3205,
+        "MUSR": 0.3843,
+        "MMLU-PRO": 0.3237
       }
     },
     {
@@ -7025,12 +7025,12 @@
       "name": "Fireball-Meta-Llama-3.1-8B-Instruct-Agent-0.003-128K-code-ds-auto",
       "developer": "EpistemeAI",
       "scores": {
-        "IFEval": 0.7207,
-        "BBH": 0.461,
-        "MATH Level 5": 0.1314,
-        "GPQA": 0.2701,
-        "MUSR": 0.3432,
-        "MMLU-PRO": 0.3354
+        "IFEval": 0.7305,
+        "BBH": 0.4649,
+        "MATH Level 5": 0.1397,
+        "GPQA": 0.2659,
+        "MUSR": 0.3209,
+        "MMLU-PRO": 0.348
       }
     },
     {
@@ -7675,12 +7675,12 @@
       "name": "Herplete-LLM-Llama-3.1-8b",
       "developer": "Etherll",
       "scores": {
-        "IFEval": 0.4672,
-        "BBH": 0.5013,
-        "MATH Level 5": 0.0279,
-        "GPQA": 0.2861,
-        "MUSR": 0.386,
-        "MMLU-PRO": 0.3482
+        "IFEval": 0.6106,
+        "BBH": 0.5347,
+        "MATH Level 5": 0.1548,
+        "GPQA": 0.3146,
+        "MUSR": 0.3991,
+        "MMLU-PRO": 0.3752
       }
     },
     {
@@ -8572,12 +8572,12 @@
       "name": "josie-7b-v6.0-step2000",
       "developer": "Goekdeniz-Guelmez",
       "scores": {
-        "IFEval": 0.7598,
-        "BBH": 0.5107,
-        "MATH Level 5": 0.4237,
-        "GPQA": 0.2768,
-        "MUSR": 0.4539,
-        "MMLU-PRO": 0.4012
+        "IFEval": 0.7628,
+        "BBH": 0.5098,
+        "MATH Level 5": 0.0,
+        "GPQA": 0.2802,
+        "MUSR": 0.4579,
+        "MMLU-PRO": 0.4033
       }
     },
     {
@@ -8728,12 +8728,12 @@
       "name": "Gemma-Ko-Merge-PEFT",
       "developer": "Gunulhona",
       "scores": {
-        "IFEval": 0.4441,
-        "BBH": 0.4863,
+        "IFEval": 0.288,
+        "BBH": 0.5154,
         "MATH Level 5": 0.0,
-        "GPQA": 0.307,
-        "MUSR": 0.3986,
-        "MMLU-PRO": 0.3098
+        "GPQA": 0.3247,
+        "MUSR": 0.408,
+        "MMLU-PRO": 0.3817
       }
     },
     {
@@ -9170,12 +9170,12 @@
       "name": "SmolLM2-360M-Instruct",
       "developer": "HuggingFaceTB",
       "scores": {
-        "IFEval": 0.3842,
-        "BBH": 0.3144,
-        "MATH Level 5": 0.0151,
-        "GPQA": 0.255,
-        "MUSR": 0.3461,
-        "MMLU-PRO": 0.1117
+        "IFEval": 0.083,
+        "BBH": 0.3053,
+        "MATH Level 5": 0.0083,
+        "GPQA": 0.2651,
+        "MUSR": 0.3423,
+        "MMLU-PRO": 0.1126
       }
     },
     {
@@ -9378,12 +9378,12 @@
       "name": "JOSIEv4o-8b-stage1-v4",
       "developer": "Isaak-Carter",
       "scores": {
-        "IFEval": 0.2477,
-        "BBH": 0.4758,
-        "MATH Level 5": 0.0453,
-        "GPQA": 0.2911,
-        "MUSR": 0.3641,
-        "MMLU-PRO": 0.3292
+        "IFEval": 0.2553,
+        "BBH": 0.4725,
+        "MATH Level 5": 0.0529,
+        "GPQA": 0.2919,
+        "MUSR": 0.3654,
+        "MMLU-PRO": 0.3316
       }
     },
     {
@@ -14305,12 +14305,12 @@
       "name": "Llama-3-8B-Magpie-Align-v0.1",
       "developer": "Magpie-Align",
       "scores": {
-        "IFEval": 0.4118,
-        "BBH": 0.4811,
-        "MATH Level 5": 0.034,
-        "GPQA": 0.2752,
-        "MUSR": 0.3047,
-        "MMLU-PRO": 0.3006
+        "IFEval": 0.4027,
+        "BBH": 0.4789,
+        "MATH Level 5": 0.0461,
+        "GPQA": 0.2768,
+        "MUSR": 0.3087,
+        "MMLU-PRO": 0.3001
       }
     },
     {
@@ -19986,12 +19986,12 @@
       "name": "Replete-LLM-Qwen2-7b",
       "developer": "Replete-AI",
       "scores": {
-        "IFEval": 0.0932,
-        "BBH": 0.2977,
+        "IFEval": 0.0905,
+        "BBH": 0.2985,
         "MATH Level 5": 0.0,
-        "GPQA": 0.2475,
-        "MUSR": 0.3941,
-        "MMLU-PRO": 0.1157
+        "GPQA": 0.2534,
+        "MUSR": 0.3848,
+        "MMLU-PRO": 0.1158
       }
     },
     {
@@ -21130,12 +21130,12 @@
       "name": "L3-70B-Euryale-v2.1",
       "developer": "Sao10K",
       "scores": {
-        "IFEval": 0.7281,
-        "BBH": 0.6503,
-        "MATH Level 5": 0.2243,
+        "IFEval": 0.7384,
+        "BBH": 0.6471,
+        "MATH Level 5": 0.2137,
         "GPQA": 0.3314,
-        "MUSR": 0.4196,
-        "MMLU-PRO": 0.5096
+        "MUSR": 0.4209,
+        "MMLU-PRO": 0.5104
       }
     },
     {
@@ -25121,12 +25121,12 @@
       "name": "Llama3.1-8B-ShiningValiant2",
       "developer": "ValiantLabs",
       "scores": {
-        "IFEval": 0.6496,
-        "BBH": 0.4774,
-        "MATH Level 5": 0.0566,
-        "GPQA": 0.3104,
-        "MUSR": 0.3909,
-        "MMLU-PRO": 0.3382
+        "IFEval": 0.2678,
+        "BBH": 0.4429,
+        "MATH Level 5": 0.0521,
+        "GPQA": 0.302,
+        "MUSR": 0.3959,
+        "MMLU-PRO": 0.2927
       }
     },
     {
@@ -26603,12 +26603,12 @@
       "name": "QAIMath-Qwen2.5-7B-TIES",
       "developer": "adriszmar",
       "scores": {
-        "IFEval": 0.1746,
-        "BBH": 0.3126,
-        "MATH Level 5": 0.0,
-        "GPQA": 0.245,
-        "MUSR": 0.4096,
-        "MMLU-PRO": 0.1087
+        "IFEval": 0.1685,
+        "BBH": 0.3124,
+        "MATH Level 5": 0.0015,
+        "GPQA": 0.2492,
+        "MUSR": 0.3963,
+        "MMLU-PRO": 0.1066
       }
     },
     {
@@ -26915,12 +26915,12 @@
       "name": "Llama-3.1-Tulu-3-70B",
       "developer": "allenai",
       "scores": {
-        "IFEval": 0.8379,
-        "BBH": 0.6157,
-        "MATH Level 5": 0.3829,
+        "IFEval": 0.8291,
+        "BBH": 0.6164,
+        "MATH Level 5": 0.4502,
         "GPQA": 0.3733,
-        "MUSR": 0.4988,
-        "MMLU-PRO": 0.4656
+        "MUSR": 0.4948,
+        "MMLU-PRO": 0.4645
       }
     },
     {
@@ -26954,12 +26954,12 @@
       "name": "Llama-3.1-Tulu-3-8B",
       "developer": "allenai",
       "scores": {
-        "IFEval": 0.8267,
-        "BBH": 0.405,
-        "MATH Level 5": 0.1964,
-        "GPQA": 0.2987,
+        "IFEval": 0.8255,
+        "BBH": 0.4061,
+        "MATH Level 5": 0.2115,
+        "GPQA": 0.297,
         "MUSR": 0.4175,
-        "MMLU-PRO": 0.2827
+        "MMLU-PRO": 0.2821
       }
     },
     {
@@ -28449,11 +28449,11 @@
       "name": "AMD-Llama-135m",
       "developer": "amd",
       "scores": {
-        "IFEval": 0.1918,
-        "BBH": 0.2969,
-        "MATH Level 5": 0.0076,
-        "GPQA": 0.2584,
-        "MUSR": 0.3846,
+        "IFEval": 0.1842,
+        "BBH": 0.2974,
+        "MATH Level 5": 0.0053,
+        "GPQA": 0.2525,
+        "MUSR": 0.378,
         "MMLU-PRO": 0.1169
       }
     },
@@ -28709,12 +28709,12 @@
       "name": "Arcee-Spark",
       "developer": "arcee-ai",
       "scores": {
-        "IFEval": 0.5621,
-        "BBH": 0.5489,
-        "MATH Level 5": 0.2953,
-        "GPQA": 0.307,
-        "MUSR": 0.4021,
-        "MMLU-PRO": 0.3822
+        "IFEval": 0.5718,
+        "BBH": 0.5481,
+        "MATH Level 5": 0.114,
+        "GPQA": 0.3062,
+        "MUSR": 0.4008,
+        "MMLU-PRO": 0.3813
       }
     },
     {
@@ -31647,12 +31647,12 @@
       "name": "dolphin-2.9.2-Phi-3-Medium-abliterated",
       "developer": "cognitivecomputations",
       "scores": {
-        "IFEval": 0.3613,
-        "BBH": 0.6123,
-        "MATH Level 5": 0.1239,
-        "GPQA": 0.328,
-        "MUSR": 0.4112,
-        "MMLU-PRO": 0.4494
+        "IFEval": 0.4124,
+        "BBH": 0.6383,
+        "MATH Level 5": 0.182,
+        "GPQA": 0.3289,
+        "MUSR": 0.4349,
+        "MMLU-PRO": 0.4525
       }
     },
     {
@@ -31790,12 +31790,12 @@
       "name": "llama-43m-beta",
       "developer": "cpayne1303",
       "scores": {
-        "IFEval": 0.1916,
-        "BBH": 0.2977,
-        "MATH Level 5": 0.0,
+        "IFEval": 0.1949,
+        "BBH": 0.2965,
+        "MATH Level 5": 0.0045,
         "GPQA": 0.2685,
-        "MUSR": 0.3872,
-        "MMLU-PRO": 0.1132
+        "MUSR": 0.3885,
+        "MMLU-PRO": 0.1111
       }
     },
     {
@@ -33506,12 +33506,12 @@
       "name": "TheBeagle-v2beta-32B-MGS",
       "developer": "fblgit",
       "scores": {
-        "IFEval": 0.5181,
-        "BBH": 0.7033,
-        "MATH Level 5": 0.4947,
-        "GPQA": 0.3826,
-        "MUSR": 0.5008,
-        "MMLU-PRO": 0.5915
+        "IFEval": 0.4503,
+        "BBH": 0.7035,
+        "MATH Level 5": 0.3943,
+        "GPQA": 0.401,
+        "MUSR": 0.5021,
+        "MMLU-PRO": 0.5911
       }
     },
     {
@@ -37705,12 +37705,12 @@
       "name": "Kosmos-EVAA-Fusion-8B",
       "developer": "jaspionjader",
       "scores": {
-        "IFEval": 0.4345,
-        "BBH": 0.5419,
-        "MATH Level 5": 0.1292,
-        "GPQA": 0.3087,
+        "IFEval": 0.4418,
+        "BBH": 0.5406,
+        "MATH Level 5": 0.1352,
+        "GPQA": 0.3062,
         "MUSR": 0.4277,
-        "MMLU-PRO": 0.3854
+        "MMLU-PRO": 0.386
       }
     },
     {
@@ -41332,12 +41332,12 @@
       "name": "BunderMaxx-0710",
       "developer": "kavonalds",
       "scores": {
-        "IFEval": 0.2701,
-        "BBH": 0.5566,
+        "IFEval": 0.3283,
+        "BBH": 0.6651,
         "MATH Level 5": 0.068,
-        "GPQA": 0.2802,
-        "MUSR": 0.3682,
-        "MMLU-PRO": 0.1449
+        "GPQA": 0.2609,
+        "MUSR": 0.3393,
+        "MMLU-PRO": 0.1314
       }
     },
     {
@@ -43893,12 +43893,12 @@
       "name": "Meta-Llama-3-8B-Instruct",
       "developer": "meta-llama",
       "scores": {
-        "IFEval": 0.4782,
-        "BBH": 0.491,
-        "MATH Level 5": 0.0914,
-        "GPQA": 0.2928,
-        "MUSR": 0.3805,
-        "MMLU-PRO": 0.3591
+        "IFEval": 0.7408,
+        "BBH": 0.4989,
+        "MATH Level 5": 0.0869,
+        "GPQA": 0.2592,
+        "MUSR": 0.3568,
+        "MMLU-PRO": 0.3664
       }
     },
     {
@@ -44426,12 +44426,12 @@
       "name": "Mistral-Small-Instruct-2409",
       "developer": "mistralai",
       "scores": {
-        "IFEval": 0.6283,
-        "BBH": 0.583,
-        "MATH Level 5": 0.2039,
-        "GPQA": 0.3331,
-        "MUSR": 0.4063,
-        "MMLU-PRO": 0.4099
+        "IFEval": 0.667,
+        "BBH": 0.5213,
+        "MATH Level 5": 0.1435,
+        "GPQA": 0.3238,
+        "MUSR": 0.3632,
+        "MMLU-PRO": 0.396
       }
     },
     {
@@ -44738,12 +44738,12 @@
       "name": "NeuralDaredevil-8B-abliterated",
       "developer": "mlabonne",
       "scores": {
-        "IFEval": 0.7561,
-        "BBH": 0.5111,
-        "MATH Level 5": 0.0906,
-        "GPQA": 0.3062,
-        "MUSR": 0.4019,
-        "MMLU-PRO": 0.3841
+        "IFEval": 0.4162,
+        "BBH": 0.5124,
+        "MATH Level 5": 0.0853,
+        "GPQA": 0.3029,
+        "MUSR": 0.415,
+        "MMLU-PRO": 0.3802
       }
     },
     {
@@ -47611,12 +47611,12 @@
       "name": "wide_3b_sft_stage1.1-ss1-with_generics_intr_math_stories.no_issue",
       "developer": "ontocord",
       "scores": {
-        "IFEval": 0.1162,
-        "BBH": 0.3184,
-        "MATH Level 5": 0.0076,
-        "GPQA": 0.2634,
-        "MUSR": 0.3447,
-        "MMLU-PRO": 0.1124
+        "IFEval": 0.1128,
+        "BBH": 0.3171,
+        "MATH Level 5": 0.0113,
+        "GPQA": 0.2685,
+        "MUSR": 0.346,
+        "MMLU-PRO": 0.1129
       }
     },
     {
@@ -49444,12 +49444,12 @@
       "name": "Calcium-Opus-14B-Elite",
       "developer": "prithivMLmods",
       "scores": {
-        "IFEval": 0.6052,
-        "BBH": 0.6317,
-        "MATH Level 5": 0.4789,
-        "GPQA": 0.3742,
-        "MUSR": 0.486,
-        "MMLU-PRO": 0.5302
+        "IFEval": 0.6064,
+        "BBH": 0.6296,
+        "MATH Level 5": 0.3708,
+        "GPQA": 0.3733,
+        "MUSR": 0.4873,
+        "MMLU-PRO": 0.5307
       }
     },
     {
@@ -50874,12 +50874,12 @@
       "name": "Qwen2.5-Math-14B-Instruct",
       "developer": "qingy2019",
       "scores": {
-        "IFEval": 0.6005,
-        "BBH": 0.6356,
-        "MATH Level 5": 0.2764,
-        "GPQA": 0.3691,
+        "IFEval": 0.6066,
+        "BBH": 0.635,
+        "MATH Level 5": 0.3716,
+        "GPQA": 0.3725,
         "MUSR": 0.4757,
-        "MMLU-PRO": 0.5339
+        "MMLU-PRO": 0.5331
       }
     },
     {
@@ -51303,12 +51303,12 @@
       "name": "Gemma-2-Ataraxy-Gemmasutra-9B-slerp",
       "developer": "recoilme",
       "scores": {
-        "IFEval": 0.2854,
-        "BBH": 0.5984,
-        "MATH Level 5": 0.1005,
-        "GPQA": 0.3297,
-        "MUSR": 0.4607,
-        "MMLU-PRO": 0.4162
+        "IFEval": 0.7649,
+        "BBH": 0.5974,
+        "MATH Level 5": 0.0174,
+        "GPQA": 0.3305,
+        "MUSR": 0.4245,
+        "MMLU-PRO": 0.4207
       }
     },
     {
@@ -51329,12 +51329,12 @@
       "name": "recoilme-gemma-2-9B-v0.2",
       "developer": "recoilme",
       "scores": {
-        "IFEval": 0.2747,
-        "BBH": 0.6031,
-        "MATH Level 5": 0.0831,
-        "GPQA": 0.3305,
-        "MUSR": 0.4686,
-        "MMLU-PRO": 0.4122
+        "IFEval": 0.7592,
+        "BBH": 0.6026,
+        "MATH Level 5": 0.0529,
+        "GPQA": 0.3289,
+        "MUSR": 0.4099,
+        "MMLU-PRO": 0.4163
       }
     },
     {
@@ -51342,12 +51342,12 @@
       "name": "recoilme-gemma-2-9B-v0.3",
       "developer": "recoilme",
       "scores": {
-        "IFEval": 0.7439,
-        "BBH": 0.5993,
-        "MATH Level 5": 0.0876,
-        "GPQA": 0.3238,
-        "MUSR": 0.4204,
-        "MMLU-PRO": 0.4072
+        "IFEval": 0.5761,
+        "BBH": 0.602,
+        "MATH Level 5": 0.1888,
+        "GPQA": 0.3372,
+        "MUSR": 0.4632,
+        "MMLU-PRO": 0.4039
       }
     },
     {
@@ -51459,12 +51459,12 @@
       "name": "FineLlama-3.1-8B",
       "developer": "riaz",
       "scores": {
-        "IFEval": 0.4373,
-        "BBH": 0.4586,
-        "MATH Level 5": 0.0514,
-        "GPQA": 0.2752,
-        "MUSR": 0.3763,
-        "MMLU-PRO": 0.2964
+        "IFEval": 0.4137,
+        "BBH": 0.4565,
+        "MATH Level 5": 0.0453,
+        "GPQA": 0.276,
+        "MUSR": 0.3776,
+        "MMLU-PRO": 0.2978
       }
     },
     {
@@ -51602,12 +51602,12 @@
       "name": "Rombos-LLM-V2.5.1-Qwen-3b",
       "developer": "rombodawg",
       "scores": {
-        "IFEval": 0.2566,
-        "BBH": 0.39,
-        "MATH Level 5": 0.1208,
-        "GPQA": 0.2626,
+        "IFEval": 0.2595,
+        "BBH": 0.3884,
+        "MATH Level 5": 0.0914,
+        "GPQA": 0.2743,
         "MUSR": 0.3991,
-        "MMLU-PRO": 0.2741
+        "MMLU-PRO": 0.2719
       }
     },
     {
@@ -54345,12 +54345,12 @@
       "name": "lambda-gemma-2-9b-dpo",
       "developer": "tanliboy",
       "scores": {
-        "IFEval": 0.4501,
-        "BBH": 0.5472,
-        "MATH Level 5": 0.0944,
-        "GPQA": 0.3138,
-        "MUSR": 0.4017,
-        "MMLU-PRO": 0.3792
+        "IFEval": 0.1829,
+        "BBH": 0.5488,
+        "MATH Level 5": 0.0,
+        "GPQA": 0.3104,
+        "MUSR": 0.4056,
+        "MMLU-PRO": 0.3805
       }
     },
     {
@@ -56945,12 +56945,12 @@
       "name": "Hebrew-Mistral-7B-200K",
       "developer": "yam-peleg",
       "scores": {
-        "IFEval": 0.1856,
-        "BBH": 0.4149,
-        "MATH Level 5": 0.0234,
-        "GPQA": 0.276,
-        "MUSR": 0.3765,
-        "MMLU-PRO": 0.2573
+        "IFEval": 0.177,
+        "BBH": 0.3411,
+        "MATH Level 5": 0.031,
+        "GPQA": 0.2534,
+        "MUSR": 0.374,
+        "MMLU-PRO": 0.2529
       }
     },
     {
diff --git a/data/benchmarks/reward-bench.json b/data/benchmarks/reward-bench.json
index 435eb05406175ffe8530e3141464bcd0e3abcc31..083fee6e840e33c85c4fe87b781938b7ad720c00 100644
--- a/data/benchmarks/reward-bench.json
+++ b/data/benchmarks/reward-bench.json
@@ -453,16 +453,16 @@
       "name": "LxzGordon/URM-LLaMa-3.1-8B",
       "developer": "LxzGordon",
       "scores": {
-        "Score": 0.9294,
+        "Score": 0.7394,
+        "Chat": 0.9553,
+        "Chat Hard": 0.8816,
+        "Safety": 0.9178,
+        "Reasoning": 0.9698,
         "Factuality": 0.6884,
         "Precise IF": 0.45,
         "Math": 0.6393,
-        "Safety": 0.9108,
         "Focus": 0.9758,
-        "Ties": 0.7653,
-        "Chat": 0.9553,
-        "Chat Hard": 0.8816,
-        "Reasoning": 0.9698
+        "Ties": 0.7653
       }
     },
     {
@@ -482,16 +482,16 @@
       "name": "NCSOFT/Llama-3-OffsetBias-RM-8B",
       "developer": "NCSOFT",
       "scores": {
-        "Score": 0.8942,
+        "Score": 0.648,
+        "Chat": 0.9721,
+        "Chat Hard": 0.818,
+        "Safety": 0.7222,
+        "Reasoning": 0.9192,
         "Factuality": 0.6084,
         "Precise IF": 0.4,
         "Math": 0.5191,
-        "Safety": 0.8676,
         "Focus": 0.9596,
-        "Ties": 0.6786,
-        "Chat": 0.9721,
-        "Chat Hard": 0.818,
-        "Reasoning": 0.9192
+        "Ties": 0.6786
       }
     },
     {
@@ -499,17 +499,17 @@
       "name": "Nexusflow/Starling-RM-34B",
       "developer": "Nexusflow",
       "scores": {
-        "Score": 0.4553,
-        "Chat": 0.9693,
-        "Chat Hard": 0.5724,
-        "Safety": 0.7556,
-        "Reasoning": 0.8845,
-        "Prior Sets (0.5 weight)": 0.7137,
+        "Score": 0.8133,
         "Factuality": 0.4589,
         "Precise IF": 0.3187,
         "Math": 0.6175,
+        "Safety": 0.877,
         "Focus": 0.4808,
-        "Ties": 0.1004
+        "Ties": 0.1004,
+        "Chat": 0.9693,
+        "Chat Hard": 0.5724,
+        "Reasoning": 0.8845,
+        "Prior Sets (0.5 weight)": 0.7137
       }
     },
     {
@@ -591,17 +591,17 @@
       "name": "OpenAssistant/reward-model-deberta-v3-large-v2",
       "developer": "OpenAssistant",
       "scores": {
-        "Score": 0.32,
-        "Chat": 0.8939,
-        "Chat Hard": 0.4518,
-        "Safety": 0.3667,
-        "Reasoning": 0.3855,
-        "Prior Sets (0.5 weight)": 0.5836,
+        "Score": 0.6126,
         "Factuality": 0.3853,
         "Precise IF": 0.2687,
         "Math": 0.5027,
+        "Safety": 0.7338,
         "Focus": 0.2768,
-        "Ties": 0.12
+        "Ties": 0.12,
+        "Chat": 0.8939,
+        "Chat Hard": 0.4518,
+        "Reasoning": 0.3855,
+        "Prior Sets (0.5 weight)": 0.5836
       }
     },
     {
@@ -609,17 +609,17 @@
       "name": "PKU-Alignment/beaver-7b-v1.0-cost",
       "developer": "PKU-Alignment",
       "scores": {
-        "Score": 0.3332,
-        "Chat": 0.6173,
-        "Chat Hard": 0.4232,
-        "Safety": 0.7589,
-        "Reasoning": 0.5482,
-        "Prior Sets (0.5 weight)": 0.57,
+        "Score": 0.5798,
         "Factuality": 0.3263,
         "Precise IF": 0.2313,
         "Math": 0.3989,
+        "Safety": 0.7351,
         "Focus": 0.2939,
-        "Ties": -0.01
+        "Ties": -0.01,
+        "Chat": 0.6173,
+        "Chat Hard": 0.4232,
+        "Reasoning": 0.5482,
+        "Prior Sets (0.5 weight)": 0.57
       }
     },
     {
@@ -904,16 +904,16 @@
       "name": "Ray2333/GRM-Llama3-8B-rewardmodel-ft",
       "developer": "Ray2333",
       "scores": {
-        "Score": 0.9154,
+        "Score": 0.6766,
+        "Chat": 0.9553,
+        "Chat Hard": 0.8618,
+        "Safety": 0.9222,
+        "Reasoning": 0.9362,
         "Factuality": 0.6274,
         "Precise IF": 0.35,
         "Math": 0.5847,
-        "Safety": 0.9081,
         "Focus": 0.8929,
-        "Ties": 0.6824,
-        "Chat": 0.9553,
-        "Chat Hard": 0.8618,
-        "Reasoning": 0.9362
+        "Ties": 0.6824
       }
     },
     {
@@ -938,17 +938,17 @@
       "name": "Ray2333/GRM-llama3-8B-distill",
       "developer": "Ray2333",
       "scores": {
-        "Score": 0.8464,
+        "Score": 0.589,
+        "Chat": 0.9832,
+        "Chat Hard": 0.6842,
+        "Safety": 0.7222,
+        "Reasoning": 0.9133,
+        "Prior Sets (0.5 weight)": 0.7209,
         "Factuality": 0.5874,
         "Precise IF": 0.3875,
         "Math": 0.5902,
-        "Safety": 0.8676,
         "Focus": 0.6727,
-        "Ties": 0.5743,
-        "Chat": 0.9832,
-        "Chat Hard": 0.6842,
-        "Reasoning": 0.9133,
-        "Prior Sets (0.5 weight)": 0.7209
+        "Ties": 0.5743
       }
     },
     {
@@ -956,17 +956,17 @@
       "name": "Ray2333/GRM-llama3-8B-sftreg",
       "developer": "Ray2333",
       "scores": {
-        "Score": 0.8542,
+        "Score": 0.6089,
+        "Chat": 0.986,
+        "Chat Hard": 0.6776,
+        "Safety": 0.7867,
+        "Reasoning": 0.9229,
+        "Prior Sets (0.5 weight)": 0.7309,
         "Factuality": 0.6189,
         "Precise IF": 0.3875,
         "Math": 0.5792,
-        "Safety": 0.8919,
         "Focus": 0.6828,
-        "Ties": 0.5981,
-        "Chat": 0.986,
-        "Chat Hard": 0.6776,
-        "Reasoning": 0.9229,
-        "Prior Sets (0.5 weight)": 0.7309
+        "Ties": 0.5981
       }
     },
     {
@@ -1098,16 +1098,16 @@
       "name": "ShikaiChen/LDL-Reward-Gemma-2-27B-v0.1",
       "developer": "ShikaiChen",
       "scores": {
-        "Score": 0.9499,
+        "Score": 0.7249,
+        "Chat": 0.9637,
+        "Chat Hard": 0.9079,
+        "Safety": 0.9222,
+        "Reasoning": 0.9903,
         "Factuality": 0.7558,
         "Precise IF": 0.35,
         "Math": 0.6448,
-        "Safety": 0.9378,
         "Focus": 0.9131,
-        "Ties": 0.7633,
-        "Chat": 0.9637,
-        "Chat Hard": 0.9079,
-        "Reasoning": 0.9903
+        "Ties": 0.7633
       }
     },
     {
@@ -1156,16 +1156,16 @@
       "name": "Skywork/Skywork-Reward-Gemma-2-27B-v0.2",
       "developer": "Skywork",
       "scores": {
-        "Score": 0.7531,
-        "Chat": 0.9609,
-        "Chat Hard": 0.8991,
-        "Safety": 0.9689,
-        "Reasoning": 0.9807,
+        "Score": 0.9426,
         "Factuality": 0.7674,
         "Precise IF": 0.375,
         "Math": 0.6721,
+        "Safety": 0.9297,
         "Focus": 0.9172,
-        "Ties": 0.8182
+        "Ties": 0.8182,
+        "Chat": 0.9609,
+        "Chat Hard": 0.8991,
+        "Reasoning": 0.9807
       }
     },
     {
@@ -1379,9 +1379,9 @@
       "name": "ai2/tulu-2-7b-rm-v0-nectar-binarized-3.8m-check...",
       "developer": "AI2",
       "scores": {
-        "Score": 0.7008,
-        "Chat": 0.9385,
-        "Chat Hard": 0.3882,
+        "Score": 0.6924,
+        "Chat": 0.9441,
+        "Chat Hard": 0.3575,
         "Safety": 0.7757
       }
     },
@@ -1423,17 +1423,17 @@
       "name": "allenai/Llama-3.1-70B-Instruct-RM-RB2",
       "developer": "allenai",
       "scores": {
-        "Score": 0.9021,
+        "Score": 0.7606,
+        "Chat": 0.9665,
+        "Chat Hard": 0.8355,
+        "Safety": 0.8844,
+        "Reasoning": 0.8969,
+        "Prior Sets (0.5 weight)": 0.0,
         "Factuality": 0.8126,
         "Precise IF": 0.4188,
         "Math": 0.6995,
-        "Safety": 0.9095,
         "Focus": 0.8646,
-        "Ties": 0.8835,
-        "Chat": 0.9665,
-        "Chat Hard": 0.8355,
-        "Reasoning": 0.8969,
-        "Prior Sets (0.5 weight)": 0.0
+        "Ties": 0.8835
       }
     },
     {
@@ -1513,17 +1513,17 @@
       "name": "allenai/Llama-3.1-Tulu-3-8B-RL-RM-RB2",
       "developer": "allenai",
       "scores": {
-        "Score": 0.8369,
+        "Score": 0.6871,
+        "Chat": 0.9469,
+        "Chat Hard": 0.7588,
+        "Safety": 0.8644,
+        "Reasoning": 0.7715,
+        "Prior Sets (0.5 weight)": 0.0,
         "Factuality": 0.7642,
         "Precise IF": 0.4,
         "Math": 0.6175,
-        "Safety": 0.8703,
         "Focus": 0.8485,
-        "Ties": 0.6281,
-        "Chat": 0.9469,
-        "Chat Hard": 0.7588,
-        "Reasoning": 0.7715,
-        "Prior Sets (0.5 weight)": 0.0
+        "Ties": 0.6281
       }
     },
     {
@@ -3504,16 +3504,16 @@
       "name": "Claude 3 Opus 20240229",
       "developer": "Anthropic",
       "scores": {
-        "Score": 0.5744,
-        "Chat": 0.9469,
-        "Chat Hard": 0.6031,
-        "Safety": 0.8378,
-        "Reasoning": 0.7868,
+        "Score": 0.8008,
         "Factuality": 0.5389,
         "Precise IF": 0.3312,
         "Math": 0.5137,
+        "Safety": 0.8662,
         "Focus": 0.6646,
-        "Ties": 0.5601
+        "Ties": 0.5601,
+        "Chat": 0.9469,
+        "Chat Hard": 0.6031,
+        "Reasoning": 0.7868
       }
     },
     {
@@ -3766,17 +3766,17 @@
       "name": "hendrydong/Mistral-RM-for-RAFT-GSHF-v0",
       "developer": "hendrydong",
       "scores": {
-        "Score": 0.7847,
+        "Score": 0.5851,
+        "Chat": 0.9832,
+        "Chat Hard": 0.5789,
+        "Safety": 0.6956,
+        "Reasoning": 0.7434,
+        "Prior Sets (0.5 weight)": 0.7508,
         "Factuality": 0.5779,
         "Precise IF": 0.3625,
         "Math": 0.6011,
-        "Safety": 0.85,
         "Focus": 0.6747,
-        "Ties": 0.5988,
-        "Chat": 0.9832,
-        "Chat Hard": 0.5789,
-        "Reasoning": 0.7434,
-        "Prior Sets (0.5 weight)": 0.7508
+        "Ties": 0.5988
       }
     },
     {
@@ -3784,16 +3784,16 @@
       "name": "infly/INF-ORM-Llama3.1-70B",
       "developer": "infly",
       "scores": {
-        "Score": 0.7648,
-        "Chat": 0.9665,
-        "Chat Hard": 0.9101,
-        "Safety": 0.9644,
-        "Reasoning": 0.9912,
+        "Score": 0.9511,
         "Factuality": 0.7411,
         "Precise IF": 0.4188,
         "Math": 0.6995,
+        "Safety": 0.9365,
         "Focus": 0.903,
-        "Ties": 0.8622
+        "Ties": 0.8622,
+        "Chat": 0.9665,
+        "Chat Hard": 0.9101,
+        "Reasoning": 0.9912
       }
     },
     {
@@ -3801,16 +3801,16 @@
       "name": "internlm/internlm2-1_8b-reward",
       "developer": "internlm",
       "scores": {
-        "Score": 0.3902,
-        "Chat": 0.9358,
-        "Chat Hard": 0.6623,
-        "Safety": 0.4711,
-        "Reasoning": 0.8724,
+        "Score": 0.8217,
         "Factuality": 0.2758,
         "Precise IF": 0.3625,
         "Math": 0.4426,
+        "Safety": 0.8162,
         "Focus": 0.596,
-        "Ties": 0.1934
+        "Ties": 0.1934,
+        "Chat": 0.9358,
+        "Chat Hard": 0.6623,
+        "Reasoning": 0.8724
       }
     },
     {
@@ -3818,16 +3818,16 @@
       "name": "internlm/internlm2-20b-reward",
       "developer": "internlm",
       "scores": {
-        "Score": 0.9016,
+        "Score": 0.5628,
+        "Chat": 0.9888,
+        "Chat Hard": 0.7654,
+        "Safety": 0.6111,
+        "Reasoning": 0.9576,
         "Factuality": 0.5558,
         "Precise IF": 0.3625,
         "Math": 0.5738,
-        "Safety": 0.8946,
         "Focus": 0.7253,
-        "Ties": 0.5483,
-        "Chat": 0.9888,
-        "Chat Hard": 0.7654,
-        "Reasoning": 0.9576
+        "Ties": 0.5483
       }
     },
     {
@@ -4202,16 +4202,16 @@
       "name": "GPT-4o 2024-08-06",
       "developer": "OpenAI",
       "scores": {
-        "Score": 0.8673,
+        "Score": 0.6493,
+        "Chat": 0.9609,
+        "Chat Hard": 0.761,
+        "Safety": 0.8619,
+        "Reasoning": 0.8661,
         "Factuality": 0.5684,
         "Precise IF": 0.3312,
         "Math": 0.623,
-        "Safety": 0.8811,
         "Focus": 0.7293,
-        "Ties": 0.7819,
-        "Chat": 0.9609,
-        "Chat Hard": 0.761,
-        "Reasoning": 0.8661
+        "Ties": 0.7819
       }
     },
     {
@@ -4219,16 +4219,16 @@
       "name": "GPT-4o mini 2024-07-18",
       "developer": "OpenAI",
       "scores": {
-        "Score": 0.8007,
+        "Score": 0.5796,
+        "Chat": 0.9497,
+        "Chat Hard": 0.6075,
+        "Safety": 0.7667,
+        "Reasoning": 0.8374,
         "Factuality": 0.4105,
         "Precise IF": 0.3438,
         "Math": 0.5191,
-        "Safety": 0.8081,
         "Focus": 0.7414,
-        "Ties": 0.6962,
-        "Chat": 0.9497,
-        "Chat Hard": 0.6075,
-        "Reasoning": 0.8374
+        "Ties": 0.6962
       }
     },
     {
@@ -4249,17 +4249,17 @@
       "name": "openbmb/Eurus-RM-7b",
       "developer": "openbmb",
       "scores": {
-        "Score": 0.5806,
-        "Chat": 0.9804,
-        "Chat Hard": 0.6557,
-        "Safety": 0.6267,
-        "Reasoning": 0.8633,
-        "Prior Sets (0.5 weight)": 0.7172,
+        "Score": 0.8159,
         "Factuality": 0.6,
         "Precise IF": 0.3438,
         "Math": 0.5683,
+        "Safety": 0.8135,
         "Focus": 0.7475,
-        "Ties": 0.5972
+        "Ties": 0.5972,
+        "Chat": 0.9804,
+        "Chat Hard": 0.6557,
+        "Reasoning": 0.8633,
+        "Prior Sets (0.5 weight)": 0.7172
       }
     },
     {
@@ -4510,17 +4510,17 @@
       "name": "weqweasdas/RM-Gemma-7B",
       "developer": "weqweasdas",
       "scores": {
-        "Score": 0.4826,
-        "Chat": 0.9693,
-        "Chat Hard": 0.4978,
-        "Safety": 0.4822,
-        "Reasoning": 0.7362,
-        "Prior Sets (0.5 weight)": 0.7069,
+        "Score": 0.6967,
         "Factuality": 0.4926,
         "Precise IF": 0.3937,
         "Math": 0.6066,
+        "Safety": 0.5784,
         "Focus": 0.497,
-        "Ties": 0.4232
+        "Ties": 0.4232,
+        "Chat": 0.9693,
+        "Chat Hard": 0.4978,
+        "Reasoning": 0.7362,
+        "Prior Sets (0.5 weight)": 0.7069
       }
     },
     {
@@ -4559,17 +4559,17 @@
       "name": "weqweasdas/hh_rlhf_rm_open_llama_3b",
       "developer": "weqweasdas",
       "scores": {
-        "Score": 0.2498,
-        "Chat": 0.8184,
-        "Chat Hard": 0.3728,
-        "Safety": 0.24,
-        "Reasoning": 0.3281,
-        "Prior Sets (0.5 weight)": 0.6564,
+        "Score": 0.5027,
         "Factuality": 0.3642,
         "Precise IF": 0.275,
         "Math": 0.3497,
+        "Safety": 0.4149,
         "Focus": 0.2384,
-        "Ties": 0.0315
+        "Ties": 0.0315,
+        "Chat": 0.8184,
+        "Chat Hard": 0.3728,
+        "Reasoning": 0.3281,
+        "Prior Sets (0.5 weight)": 0.6564
       }
     }
   ]
diff --git a/data/benchmarks/swe-bench.json b/data/benchmarks/swe-bench.json
index 093176be195c26e24230b48d3e9b488139a6d6bf..3b6c1cd3a38d41c01ec61c5d181997bdb0b7b011 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": 0.8072
+        "swe-bench": 0.65
       }
     },
     {
@@ -21,7 +21,7 @@
       "name": "gpt-5.2-2025-12-11",
       "developer": "OpenAI",
       "scores": {
-        "swe-bench": 0.5455
+        "swe-bench": 0.57
       }
     }
   ]
diff --git a/data/benchmarks/tau-bench-2_airline.json b/data/benchmarks/tau-bench-2_airline.json
index 203ba536a38c5fd6f5a3b4f5a7c625bb98c214a5..3829696a07bc037642c69851a891e0aeb0e5febf 100644
--- a/data/benchmarks/tau-bench-2_airline.json
+++ b/data/benchmarks/tau-bench-2_airline.json
@@ -5,7 +5,7 @@
       "name": "claude-opus-4-5",
       "developer": "Anthropic",
       "scores": {
-        "tau-bench-2/airline": 0.66
+        "tau-bench-2/airline": 0.72
       }
     },
     {
@@ -13,7 +13,7 @@
       "name": "gemini-3-pro-preview",
       "developer": "Google",
       "scores": {
-        "tau-bench-2/airline": 0.7
+        "tau-bench-2/airline": 0.68
       }
     },
     {
@@ -21,7 +21,7 @@
       "name": "gpt-5.2-2025-12-11",
       "developer": "OpenAI",
       "scores": {
-        "tau-bench-2/airline": 0.48
+        "tau-bench-2/airline": 0.6
       }
     }
   ]
diff --git a/data/benchmarks/tau-bench-2_retail.json b/data/benchmarks/tau-bench-2_retail.json
index bb3c509d520d0e5ab84b4c3e44db8c84041b45fa..43bf4e72d939794b39171defb2c6b721324ab767 100644
--- a/data/benchmarks/tau-bench-2_retail.json
+++ b/data/benchmarks/tau-bench-2_retail.json
@@ -13,7 +13,7 @@
       "name": "gemini-3-pro-preview",
       "developer": "Google",
       "scores": {
-        "tau-bench-2/retail": 0.7805
+        "tau-bench-2/retail": 0.82
       }
     },
     {
@@ -21,7 +21,7 @@
       "name": "gpt-5.2-2025-12-11",
       "developer": "OpenAI",
       "scores": {
-        "tau-bench-2/retail": 0.51
+        "tau-bench-2/retail": 0.73
       }
     }
   ]
diff --git a/data/benchmarks/tau-bench-2_telecom.json b/data/benchmarks/tau-bench-2_telecom.json
index 0371242e1ef28be51ed37461c45171b5f6b938db..05002e54c35c11c6e2530af6d100378b4038ab6c 100644
--- a/data/benchmarks/tau-bench-2_telecom.json
+++ b/data/benchmarks/tau-bench-2_telecom.json
@@ -13,7 +13,7 @@
       "name": "gemini-3-pro-preview",
       "developer": "Google",
       "scores": {
-        "tau-bench-2/telecom": 0.6852
+        "tau-bench-2/telecom": 0.73
       }
     },
     {
@@ -21,7 +21,7 @@
       "name": "gpt-5.2-2025-12-11",
       "developer": "OpenAI",
       "scores": {
-        "tau-bench-2/telecom": 0.5354
+        "tau-bench-2/telecom": 0.55
       }
     }
   ]
diff --git a/data/benchmarks/terminal-bench-2.0.json b/data/benchmarks/terminal-bench-2.0.json
index a8e801f280cc4af65aa221436665986581643fe9..3f1515b599ae57812585a3e55eaf803056a58325 100644
--- a/data/benchmarks/terminal-bench-2.0.json
+++ b/data/benchmarks/terminal-bench-2.0.json
@@ -13,7 +13,7 @@
       "name": "Claude Haiku 4.5",
       "developer": "Anthropic",
       "scores": {
-        "terminal-bench-2.0": 35.5
+        "terminal-bench-2.0": 13.9
       }
     },
     {
@@ -21,7 +21,7 @@
       "name": "Claude Opus 4.1",
       "developer": "Anthropic",
       "scores": {
-        "terminal-bench-2.0": 38.0
+        "terminal-bench-2.0": 36.9
       }
     },
     {
@@ -29,7 +29,7 @@
       "name": "Claude Opus 4.5",
       "developer": "Anthropic",
       "scores": {
-        "terminal-bench-2.0": 59.1
+        "terminal-bench-2.0": 51.9
       }
     },
     {
@@ -37,7 +37,7 @@
       "name": "Claude Opus 4.6",
       "developer": "Anthropic",
       "scores": {
-        "terminal-bench-2.0": 66.9
+        "terminal-bench-2.0": 74.7
       }
     },
     {
@@ -45,7 +45,7 @@
       "name": "Claude Sonnet 4.5",
       "developer": "Anthropic",
       "scores": {
-        "terminal-bench-2.0": 40.1
+        "terminal-bench-2.0": 42.6
       }
     },
     {
@@ -61,7 +61,7 @@
       "name": "Gemini 2.5 Flash",
       "developer": "Google",
       "scores": {
-        "terminal-bench-2.0": 17.1
+        "terminal-bench-2.0": 15.4
       }
     },
     {
@@ -69,7 +69,7 @@
       "name": "Gemini 2.5 Pro",
       "developer": "Google",
       "scores": {
-        "terminal-bench-2.0": 19.6
+        "terminal-bench-2.0": 16.4
       }
     },
     {
@@ -93,7 +93,7 @@
       "name": "Gemini 3.1 Pro",
       "developer": "Google",
       "scores": {
-        "terminal-bench-2.0": 78.4
+        "terminal-bench-2.0": 74.8
       }
     },
     {
@@ -125,7 +125,7 @@
       "name": "Kimi K2 Instruct",
       "developer": "Moonshot AI",
       "scores": {
-        "terminal-bench-2.0": 26.7
+        "terminal-bench-2.0": 27.8
       }
     },
     {
@@ -149,7 +149,7 @@
       "name": "Multiple",
       "developer": "Multiple",
       "scores": {
-        "terminal-bench-2.0": 58.4
+        "terminal-bench-2.0": 72.4
       }
     },
     {
@@ -165,7 +165,7 @@
       "name": "GPT-5-Codex",
       "developer": "OpenAI",
       "scores": {
-        "terminal-bench-2.0": 41.3
+        "terminal-bench-2.0": 43.4
       }
     },
     {
@@ -173,7 +173,7 @@
       "name": "GPT-5-Mini",
       "developer": "OpenAI",
       "scores": {
-        "terminal-bench-2.0": 22.2
+        "terminal-bench-2.0": 34.8
       }
     },
     {
@@ -181,7 +181,7 @@
       "name": "GPT-5-Nano",
       "developer": "OpenAI",
       "scores": {
-        "terminal-bench-2.0": 7.9
+        "terminal-bench-2.0": 7.0
       }
     },
     {
@@ -197,7 +197,7 @@
       "name": "GPT-5.1-Codex",
       "developer": "OpenAI",
       "scores": {
-        "terminal-bench-2.0": 36.9
+        "terminal-bench-2.0": 53.5
       }
     },
     {
@@ -221,7 +221,7 @@
       "name": "GPT-5.2",
       "developer": "OpenAI",
       "scores": {
-        "terminal-bench-2.0": 54.0
+        "terminal-bench-2.0": 60.7
       }
     },
     {
@@ -237,7 +237,7 @@
       "name": "GPT-5.3-Codex",
       "developer": "OpenAI",
       "scores": {
-        "terminal-bench-2.0": 77.3
+        "terminal-bench-2.0": 74.6
       }
     },
     {
@@ -253,7 +253,7 @@
       "name": "GPT-OSS-20B",
       "developer": "OpenAI",
       "scores": {
-        "terminal-bench-2.0": 3.4
+        "terminal-bench-2.0": 3.1
       }
     },
     {
@@ -269,7 +269,7 @@
       "name": "Grok Code Fast 1",
       "developer": "xAI",
       "scores": {
-        "terminal-bench-2.0": 14.2
+        "terminal-bench-2.0": 25.8
       }
     },
     {
diff --git a/data/developers/adriszmar.json b/data/developers/adriszmar.json
index 1f1d39916960942963a9c3c265196aea3657be38..acb90d745752909d8f96f323acb9caa9b19061ae 100644
--- a/data/developers/adriszmar.json
+++ b/data/developers/adriszmar.json
@@ -7,12 +7,12 @@
       "developer": "adriszmar",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "hfopenllm_v2/IFEval": 0.1746,
-        "hfopenllm_v2/BBH": 0.3126,
-        "hfopenllm_v2/MATH Level 5": 0.0,
-        "hfopenllm_v2/GPQA": 0.245,
-        "hfopenllm_v2/MUSR": 0.4096,
-        "hfopenllm_v2/MMLU-PRO": 0.1087
+        "hfopenllm_v2/IFEval": 0.1685,
+        "hfopenllm_v2/BBH": 0.3124,
+        "hfopenllm_v2/MATH Level 5": 0.0015,
+        "hfopenllm_v2/GPQA": 0.2492,
+        "hfopenllm_v2/MUSR": 0.3963,
+        "hfopenllm_v2/MMLU-PRO": 0.1066
       }
     }
   ]
diff --git a/data/developers/ai2.json b/data/developers/ai2.json
index 4934c11b7806e647da8c3821dcfccba2566bb947..6ae2e91a5d501e1d313c59819f3bee806d5615b0 100644
--- a/data/developers/ai2.json
+++ b/data/developers/ai2.json
@@ -43,9 +43,9 @@
       "developer": "AI2",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "reward-bench/Score": 0.7008,
-        "reward-bench/Chat": 0.9385,
-        "reward-bench/Chat Hard": 0.3882,
+        "reward-bench/Score": 0.6924,
+        "reward-bench/Chat": 0.9441,
+        "reward-bench/Chat Hard": 0.3575,
         "reward-bench/Safety": 0.7757
       }
     },
diff --git a/data/developers/allenai.json b/data/developers/allenai.json
index 26883d607b7a5071bd9da08389772de32edfe871..733bf4fc5c0900a8884a7abb1f0b0f474d01c62a 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": 0.9021,
+        "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/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/Chat": 0.9665,
-        "reward-bench/Chat Hard": 0.8355,
-        "reward-bench/Reasoning": 0.8969,
-        "reward-bench/Prior Sets (0.5 weight)": 0.0
+        "reward-bench/Ties": 0.8835
       }
     },
     {
@@ -120,12 +120,12 @@
       "developer": "allenai",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "hfopenllm_v2/IFEval": 0.8379,
-        "hfopenllm_v2/BBH": 0.6157,
-        "hfopenllm_v2/MATH Level 5": 0.3829,
+        "hfopenllm_v2/IFEval": 0.8291,
+        "hfopenllm_v2/BBH": 0.6164,
+        "hfopenllm_v2/MATH Level 5": 0.4502,
         "hfopenllm_v2/GPQA": 0.3733,
-        "hfopenllm_v2/MUSR": 0.4988,
-        "hfopenllm_v2/MMLU-PRO": 0.4656
+        "hfopenllm_v2/MUSR": 0.4948,
+        "hfopenllm_v2/MMLU-PRO": 0.4645
       }
     },
     {
@@ -181,12 +181,12 @@
       "developer": "allenai",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "hfopenllm_v2/IFEval": 0.8267,
-        "hfopenllm_v2/BBH": 0.405,
-        "hfopenllm_v2/MATH Level 5": 0.1964,
-        "hfopenllm_v2/GPQA": 0.2987,
+        "hfopenllm_v2/IFEval": 0.8255,
+        "hfopenllm_v2/BBH": 0.4061,
+        "hfopenllm_v2/MATH Level 5": 0.2115,
+        "hfopenllm_v2/GPQA": 0.297,
         "hfopenllm_v2/MUSR": 0.4175,
-        "hfopenllm_v2/MMLU-PRO": 0.2827
+        "hfopenllm_v2/MMLU-PRO": 0.2821
       }
     },
     {
@@ -228,17 +228,17 @@
       "developer": "allenai",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "reward-bench/Score": 0.8369,
+        "reward-bench/Score": 0.6871,
+        "reward-bench/Chat": 0.9469,
+        "reward-bench/Chat Hard": 0.7588,
+        "reward-bench/Safety": 0.8644,
+        "reward-bench/Reasoning": 0.7715,
+        "reward-bench/Prior Sets (0.5 weight)": 0.0,
         "reward-bench/Factuality": 0.7642,
         "reward-bench/Precise IF": 0.4,
         "reward-bench/Math": 0.6175,
-        "reward-bench/Safety": 0.8703,
         "reward-bench/Focus": 0.8485,
-        "reward-bench/Ties": 0.6281,
-        "reward-bench/Chat": 0.9469,
-        "reward-bench/Chat Hard": 0.7588,
-        "reward-bench/Reasoning": 0.7715,
-        "reward-bench/Prior Sets (0.5 weight)": 0.0
+        "reward-bench/Ties": 0.6281
       }
     },
     {
diff --git a/data/developers/amd.json b/data/developers/amd.json
index f58c5a6931b8f7bef3756ba18944919a5d99e792..ec85a4364a761e30f1999f359d0d247d8857e139 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": 0.1918,
-        "hfopenllm_v2/BBH": 0.2969,
-        "hfopenllm_v2/MATH Level 5": 0.0076,
-        "hfopenllm_v2/GPQA": 0.2584,
-        "hfopenllm_v2/MUSR": 0.3846,
+        "hfopenllm_v2/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/MMLU-PRO": 0.1169
       }
     }
diff --git a/data/developers/anthropic.json b/data/developers/anthropic.json
index c1b51c55828f681c4d430c9fc7c3821e0c017451..21c2bc0153b15a2859b6559b8628567638664450 100644
--- a/data/developers/anthropic.json
+++ b/data/developers/anthropic.json
@@ -436,16 +436,16 @@
         "helm_mmlu/Virology": 0.578,
         "helm_mmlu/World Religions": 0.901,
         "helm_mmlu/Mean win rate": 0.014,
-        "reward-bench/Score": 0.5744,
-        "reward-bench/Chat": 0.9469,
-        "reward-bench/Chat Hard": 0.6031,
-        "reward-bench/Safety": 0.8378,
-        "reward-bench/Reasoning": 0.7868,
+        "reward-bench/Score": 0.8008,
         "reward-bench/Factuality": 0.5389,
         "reward-bench/Precise IF": 0.3312,
         "reward-bench/Math": 0.5137,
+        "reward-bench/Safety": 0.8662,
         "reward-bench/Focus": 0.6646,
-        "reward-bench/Ties": 0.5601
+        "reward-bench/Ties": 0.5601,
+        "reward-bench/Chat": 0.9469,
+        "reward-bench/Chat Hard": 0.6031,
+        "reward-bench/Reasoning": 0.7868
       }
     },
     {
@@ -525,7 +525,7 @@
       "developer": "Anthropic",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "terminal-bench-2.0/terminal-bench-2.0": 35.5
+        "terminal-bench-2.0/terminal-bench-2.0": 13.9
       }
     },
     {
@@ -650,10 +650,10 @@
       "developer": "Anthropic",
       "evaluator_relationship": null,
       "benchmark_scores": {
+        "appworld_test_normal/appworld/test_normal": 0.66,
         "browsecompplus/browsecompplus": 0.49,
-        "appworld_test_normal/appworld/test_normal": 0.64,
-        "swe-bench/swe-bench": 0.8072,
-        "tau-bench-2_airline/tau-bench-2/airline": 0.66,
+        "swe-bench/swe-bench": 0.65,
+        "tau-bench-2_airline/tau-bench-2/airline": 0.72,
         "tau-bench-2_retail/tau-bench-2/retail": 0.85,
         "tau-bench-2_telecom/tau-bench-2/telecom": 0.84
       }
@@ -664,7 +664,7 @@
       "developer": "Anthropic",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "terminal-bench-2.0/terminal-bench-2.0": 38.0
+        "terminal-bench-2.0/terminal-bench-2.0": 36.9
       }
     },
     {
@@ -673,7 +673,7 @@
       "developer": "Anthropic",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "terminal-bench-2.0/terminal-bench-2.0": 59.1
+        "terminal-bench-2.0/terminal-bench-2.0": 51.9
       }
     },
     {
@@ -682,7 +682,7 @@
       "developer": "Anthropic",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "terminal-bench-2.0/terminal-bench-2.0": 66.9
+        "terminal-bench-2.0/terminal-bench-2.0": 74.7
       }
     },
     {
@@ -756,7 +756,7 @@
       "developer": "Anthropic",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "terminal-bench-2.0/terminal-bench-2.0": 40.1
+        "terminal-bench-2.0/terminal-bench-2.0": 42.6
       }
     },
     {
diff --git a/data/developers/arcee-ai.json b/data/developers/arcee-ai.json
index fb3c26af6dfe804ff7a40fb7fe0b6065ba67af15..a67ed73a3aff7f3d10c24e6ce76a817fd626a3c8 100644
--- a/data/developers/arcee-ai.json
+++ b/data/developers/arcee-ai.json
@@ -49,12 +49,12 @@
       "developer": "arcee-ai",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "hfopenllm_v2/IFEval": 0.5621,
-        "hfopenllm_v2/BBH": 0.5489,
-        "hfopenllm_v2/MATH Level 5": 0.2953,
-        "hfopenllm_v2/GPQA": 0.307,
-        "hfopenllm_v2/MUSR": 0.4021,
-        "hfopenllm_v2/MMLU-PRO": 0.3822
+        "hfopenllm_v2/IFEval": 0.5718,
+        "hfopenllm_v2/BBH": 0.5481,
+        "hfopenllm_v2/MATH Level 5": 0.114,
+        "hfopenllm_v2/GPQA": 0.3062,
+        "hfopenllm_v2/MUSR": 0.4008,
+        "hfopenllm_v2/MMLU-PRO": 0.3813
       }
     },
     {
diff --git a/data/developers/atanddev.json b/data/developers/atanddev.json
index d269c1fbba37e9ea4df30635a880656764997806..42530fda0188ea30162bbff58f1010442b0394c9 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": 0.4511,
-        "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
+        "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
       }
     }
   ]
diff --git a/data/developers/boltmonkey.json b/data/developers/boltmonkey.json
index d93c347b80733b690b666d77f058a8e36708eee2..93a1093c0cbb01b9a84ae22cf6063fc50d8793cb 100644
--- a/data/developers/boltmonkey.json
+++ b/data/developers/boltmonkey.json
@@ -21,12 +21,12 @@
       "developer": "BoltMonkey",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "hfopenllm_v2/IFEval": 0.459,
-        "hfopenllm_v2/BBH": 0.5185,
-        "hfopenllm_v2/MATH Level 5": 0.0937,
-        "hfopenllm_v2/GPQA": 0.2743,
-        "hfopenllm_v2/MUSR": 0.4083,
-        "hfopenllm_v2/MMLU-PRO": 0.3631
+        "hfopenllm_v2/IFEval": 0.7999,
+        "hfopenllm_v2/BBH": 0.5152,
+        "hfopenllm_v2/MATH Level 5": 0.1193,
+        "hfopenllm_v2/GPQA": 0.281,
+        "hfopenllm_v2/MUSR": 0.4019,
+        "hfopenllm_v2/MMLU-PRO": 0.3733
       }
     },
     {
diff --git a/data/developers/cognitivecomputations.json b/data/developers/cognitivecomputations.json
index 292d5e513d244c8ebb441a809017ff16919c9354..27ef3ede420acfeab83ed5bb754062e32374c41a 100644
--- a/data/developers/cognitivecomputations.json
+++ b/data/developers/cognitivecomputations.json
@@ -77,12 +77,12 @@
       "developer": "cognitivecomputations",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "hfopenllm_v2/IFEval": 0.3613,
-        "hfopenllm_v2/BBH": 0.6123,
-        "hfopenllm_v2/MATH Level 5": 0.1239,
-        "hfopenllm_v2/GPQA": 0.328,
-        "hfopenllm_v2/MUSR": 0.4112,
-        "hfopenllm_v2/MMLU-PRO": 0.4494
+        "hfopenllm_v2/IFEval": 0.4124,
+        "hfopenllm_v2/BBH": 0.6383,
+        "hfopenllm_v2/MATH Level 5": 0.182,
+        "hfopenllm_v2/GPQA": 0.3289,
+        "hfopenllm_v2/MUSR": 0.4349,
+        "hfopenllm_v2/MMLU-PRO": 0.4525
       }
     },
     {
diff --git a/data/developers/columbia-nlp.json b/data/developers/columbia-nlp.json
index b04d1f97bca6939c03a53d86cd396214edf82f72..11f5fed45eb39522787aef4e964f3d3e28d320c0 100644
--- a/data/developers/columbia-nlp.json
+++ b/data/developers/columbia-nlp.json
@@ -7,12 +7,12 @@
       "developer": "Columbia-NLP",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "hfopenllm_v2/IFEval": 0.3278,
-        "hfopenllm_v2/BBH": 0.392,
-        "hfopenllm_v2/MATH Level 5": 0.0431,
-        "hfopenllm_v2/GPQA": 0.2492,
-        "hfopenllm_v2/MUSR": 0.412,
-        "hfopenllm_v2/MMLU-PRO": 0.1666
+        "hfopenllm_v2/IFEval": 0.3102,
+        "hfopenllm_v2/BBH": 0.3881,
+        "hfopenllm_v2/MATH Level 5": 0.0536,
+        "hfopenllm_v2/GPQA": 0.2534,
+        "hfopenllm_v2/MUSR": 0.4081,
+        "hfopenllm_v2/MMLU-PRO": 0.1665
       }
     },
     {
diff --git a/data/developers/cpayne1303.json b/data/developers/cpayne1303.json
index 6d735bd94a67b9fc86d407e5a74d4ec119a21a01..878ab50b2c306395a2d661382c84d0660b0f0d51 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": 0.1916,
-        "hfopenllm_v2/BBH": 0.2977,
-        "hfopenllm_v2/MATH Level 5": 0.0,
+        "hfopenllm_v2/IFEval": 0.1949,
+        "hfopenllm_v2/BBH": 0.2965,
+        "hfopenllm_v2/MATH Level 5": 0.0045,
         "hfopenllm_v2/GPQA": 0.2685,
-        "hfopenllm_v2/MUSR": 0.3872,
-        "hfopenllm_v2/MMLU-PRO": 0.1132
+        "hfopenllm_v2/MUSR": 0.3885,
+        "hfopenllm_v2/MMLU-PRO": 0.1111
       }
     },
     {
diff --git a/data/developers/daemontatox.json b/data/developers/daemontatox.json
index 3de1c87bc255ec29e11a7fcd9434ebc4d17ff27a..b8e6a28a7fbf1f38ce6fe03abcdad2859f985a0e 100644
--- a/data/developers/daemontatox.json
+++ b/data/developers/daemontatox.json
@@ -119,12 +119,12 @@
       "developer": "Daemontatox",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "hfopenllm_v2/IFEval": 0.777,
-        "hfopenllm_v2/BBH": 0.5187,
-        "hfopenllm_v2/MATH Level 5": 0.2198,
-        "hfopenllm_v2/GPQA": 0.2936,
-        "hfopenllm_v2/MUSR": 0.3911,
-        "hfopenllm_v2/MMLU-PRO": 0.3738
+        "hfopenllm_v2/IFEval": 0.5064,
+        "hfopenllm_v2/BBH": 0.5112,
+        "hfopenllm_v2/MATH Level 5": 0.1631,
+        "hfopenllm_v2/GPQA": 0.3163,
+        "hfopenllm_v2/MUSR": 0.3973,
+        "hfopenllm_v2/MMLU-PRO": 0.3802
       }
     },
     {
@@ -231,12 +231,12 @@
       "developer": "Daemontatox",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "hfopenllm_v2/IFEval": 0.4855,
-        "hfopenllm_v2/BBH": 0.6627,
-        "hfopenllm_v2/MATH Level 5": 0.4841,
-        "hfopenllm_v2/GPQA": 0.3096,
-        "hfopenllm_v2/MUSR": 0.4256,
-        "hfopenllm_v2/MMLU-PRO": 0.5542
+        "hfopenllm_v2/IFEval": 0.3745,
+        "hfopenllm_v2/BBH": 0.6668,
+        "hfopenllm_v2/MATH Level 5": 0.4758,
+        "hfopenllm_v2/GPQA": 0.3943,
+        "hfopenllm_v2/MUSR": 0.4858,
+        "hfopenllm_v2/MMLU-PRO": 0.5593
       }
     },
     {
diff --git a/data/developers/deepmount00.json b/data/developers/deepmount00.json
index 5505c28134c7ac10ef3a27978dd2745253c793a1..e898074e4a61782e05002f7b47eb2ee0411313aa 100644
--- a/data/developers/deepmount00.json
+++ b/data/developers/deepmount00.json
@@ -63,12 +63,12 @@
       "developer": "DeepMount00",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "hfopenllm_v2/IFEval": 0.7917,
-        "hfopenllm_v2/BBH": 0.5109,
-        "hfopenllm_v2/MATH Level 5": 0.1088,
-        "hfopenllm_v2/GPQA": 0.2878,
-        "hfopenllm_v2/MUSR": 0.4136,
-        "hfopenllm_v2/MMLU-PRO": 0.3876
+        "hfopenllm_v2/IFEval": 0.5365,
+        "hfopenllm_v2/BBH": 0.517,
+        "hfopenllm_v2/MATH Level 5": 0.1707,
+        "hfopenllm_v2/GPQA": 0.3062,
+        "hfopenllm_v2/MUSR": 0.4487,
+        "hfopenllm_v2/MMLU-PRO": 0.396
       }
     },
     {
diff --git a/data/developers/doppelreflex.json b/data/developers/doppelreflex.json
index 4e478be7761570eec41b8a497db82c0ab081c8b0..0b78fc1cbec001d1df6b60b1fab265b2eab6799e 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": 0.451,
-        "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
+        "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
       }
     },
     {
diff --git a/data/developers/epistemeai.json b/data/developers/epistemeai.json
index 11b25cd31eead1ba78e7fde536703493137e208b..ae59684b2ae8edda61f6033386c80ae35c1570fc 100644
--- a/data/developers/epistemeai.json
+++ b/data/developers/epistemeai.json
@@ -231,12 +231,12 @@
       "developer": "EpistemeAI",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "hfopenllm_v2/IFEval": 0.7207,
-        "hfopenllm_v2/BBH": 0.461,
-        "hfopenllm_v2/MATH Level 5": 0.1314,
-        "hfopenllm_v2/GPQA": 0.2701,
-        "hfopenllm_v2/MUSR": 0.3432,
-        "hfopenllm_v2/MMLU-PRO": 0.3354
+        "hfopenllm_v2/IFEval": 0.7305,
+        "hfopenllm_v2/BBH": 0.4649,
+        "hfopenllm_v2/MATH Level 5": 0.1397,
+        "hfopenllm_v2/GPQA": 0.2659,
+        "hfopenllm_v2/MUSR": 0.3209,
+        "hfopenllm_v2/MMLU-PRO": 0.348
       }
     },
     {
diff --git a/data/developers/etherll.json b/data/developers/etherll.json
index 2be2455f8558b72fcbd342c72cc671c443f3155e..6a72dd37a279f4d76a8244a057714c910854bcd2 100644
--- a/data/developers/etherll.json
+++ b/data/developers/etherll.json
@@ -35,12 +35,12 @@
       "developer": "Etherll",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "hfopenllm_v2/IFEval": 0.4672,
-        "hfopenllm_v2/BBH": 0.5013,
-        "hfopenllm_v2/MATH Level 5": 0.0279,
-        "hfopenllm_v2/GPQA": 0.2861,
-        "hfopenllm_v2/MUSR": 0.386,
-        "hfopenllm_v2/MMLU-PRO": 0.3482
+        "hfopenllm_v2/IFEval": 0.6106,
+        "hfopenllm_v2/BBH": 0.5347,
+        "hfopenllm_v2/MATH Level 5": 0.1548,
+        "hfopenllm_v2/GPQA": 0.3146,
+        "hfopenllm_v2/MUSR": 0.3991,
+        "hfopenllm_v2/MMLU-PRO": 0.3752
       }
     },
     {
diff --git a/data/developers/fblgit.json b/data/developers/fblgit.json
index 6fc1e61b7aa2564e949656f946971c56834a0ca1..c9c68512a8d17a7002851c775ec2736dba6e4b4f 100644
--- a/data/developers/fblgit.json
+++ b/data/developers/fblgit.json
@@ -91,12 +91,12 @@
       "developer": "fblgit",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "hfopenllm_v2/IFEval": 0.5181,
-        "hfopenllm_v2/BBH": 0.7033,
-        "hfopenllm_v2/MATH Level 5": 0.4947,
-        "hfopenllm_v2/GPQA": 0.3826,
-        "hfopenllm_v2/MUSR": 0.5008,
-        "hfopenllm_v2/MMLU-PRO": 0.5915
+        "hfopenllm_v2/IFEval": 0.4503,
+        "hfopenllm_v2/BBH": 0.7035,
+        "hfopenllm_v2/MATH Level 5": 0.3943,
+        "hfopenllm_v2/GPQA": 0.401,
+        "hfopenllm_v2/MUSR": 0.5021,
+        "hfopenllm_v2/MMLU-PRO": 0.5911
       }
     },
     {
diff --git a/data/developers/goekdeniz-guelmez.json b/data/developers/goekdeniz-guelmez.json
index e3a743ff451afc2206e344fc708fd30240018483..c6e66fe9b3a75e2d49b70b9c90b10752326b37c4 100644
--- a/data/developers/goekdeniz-guelmez.json
+++ b/data/developers/goekdeniz-guelmez.json
@@ -49,12 +49,12 @@
       "developer": "Goekdeniz-Guelmez",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "hfopenllm_v2/IFEval": 0.7598,
-        "hfopenllm_v2/BBH": 0.5107,
-        "hfopenllm_v2/MATH Level 5": 0.4237,
-        "hfopenllm_v2/GPQA": 0.2768,
-        "hfopenllm_v2/MUSR": 0.4539,
-        "hfopenllm_v2/MMLU-PRO": 0.4012
+        "hfopenllm_v2/IFEval": 0.7628,
+        "hfopenllm_v2/BBH": 0.5098,
+        "hfopenllm_v2/MATH Level 5": 0.0,
+        "hfopenllm_v2/GPQA": 0.2802,
+        "hfopenllm_v2/MUSR": 0.4579,
+        "hfopenllm_v2/MMLU-PRO": 0.4033
       }
     },
     {
diff --git a/data/developers/google.json b/data/developers/google.json
index ae9dc7717f1b79909d67dfe1364f96967d93b736..81f1df0599e79d5fa5b9eb113ec92dededc4447e 100644
--- a/data/developers/google.json
+++ b/data/developers/google.json
@@ -139,6 +139,7 @@
       "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,
@@ -146,7 +147,6 @@
         "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": 17.1
+        "terminal-bench-2.0/terminal-bench-2.0": 15.4
       }
     },
     {
@@ -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": 19.6
+        "terminal-bench-2.0/terminal-bench-2.0": 16.4
       }
     },
     {
@@ -879,7 +879,7 @@
       "developer": "Google",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "appworld_test_normal/appworld/test_normal": 0.13,
+        "appworld_test_normal/appworld/test_normal": 0.36,
         "browsecompplus/browsecompplus": 0.48,
         "global-mmlu-lite/Global MMLU Lite": 0.9453,
         "global-mmlu-lite/Culturally Sensitive": 0.9397,
@@ -901,9 +901,9 @@
         "global-mmlu-lite/Chinese": 0.9475,
         "global-mmlu-lite/Burmese": 0.9425,
         "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": 0.6852
+        "tau-bench-2_airline/tau-bench-2/airline": 0.68,
+        "tau-bench-2_retail/tau-bench-2/retail": 0.82,
+        "tau-bench-2_telecom/tau-bench-2/telecom": 0.73
       }
     },
     {
@@ -912,7 +912,7 @@
       "developer": "Google",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "terminal-bench-2.0/terminal-bench-2.0": 78.4
+        "terminal-bench-2.0/terminal-bench-2.0": 74.8
       }
     },
     {
diff --git a/data/developers/gunulhona.json b/data/developers/gunulhona.json
index 1eba4dc6aed35ea93d90c3c8c2e1a2676805ffa0..3d63c85d80df83c6632e31f815d8dc78510d19a0 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": 0.4441,
-        "hfopenllm_v2/BBH": 0.4863,
+        "hfopenllm_v2/IFEval": 0.288,
+        "hfopenllm_v2/BBH": 0.5154,
         "hfopenllm_v2/MATH Level 5": 0.0,
-        "hfopenllm_v2/GPQA": 0.307,
-        "hfopenllm_v2/MUSR": 0.3986,
-        "hfopenllm_v2/MMLU-PRO": 0.3098
+        "hfopenllm_v2/GPQA": 0.3247,
+        "hfopenllm_v2/MUSR": 0.408,
+        "hfopenllm_v2/MMLU-PRO": 0.3817
       }
     }
   ]
diff --git a/data/developers/hendrydong.json b/data/developers/hendrydong.json
index 56e05071d3b06a1289763aa84d052b49b755b3aa..66d1cb6cae0c438dba7144b9a92c7891857c219e 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": 0.7847,
+        "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/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/Chat": 0.9832,
-        "reward-bench/Chat Hard": 0.5789,
-        "reward-bench/Reasoning": 0.7434,
-        "reward-bench/Prior Sets (0.5 weight)": 0.7508
+        "reward-bench/Ties": 0.5988
       }
     }
   ]
diff --git a/data/developers/huggingfacetb.json b/data/developers/huggingfacetb.json
index 60e6e856fd10ebf29a5d127dd18301cd9edf10dd..bed31781473fb30427be579aab45ef01bf5054ce 100644
--- a/data/developers/huggingfacetb.json
+++ b/data/developers/huggingfacetb.json
@@ -161,12 +161,12 @@
       "developer": "HuggingFaceTB",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "hfopenllm_v2/IFEval": 0.3842,
-        "hfopenllm_v2/BBH": 0.3144,
-        "hfopenllm_v2/MATH Level 5": 0.0151,
-        "hfopenllm_v2/GPQA": 0.255,
-        "hfopenllm_v2/MUSR": 0.3461,
-        "hfopenllm_v2/MMLU-PRO": 0.1117
+        "hfopenllm_v2/IFEval": 0.083,
+        "hfopenllm_v2/BBH": 0.3053,
+        "hfopenllm_v2/MATH Level 5": 0.0083,
+        "hfopenllm_v2/GPQA": 0.2651,
+        "hfopenllm_v2/MUSR": 0.3423,
+        "hfopenllm_v2/MMLU-PRO": 0.1126
       }
     }
   ]
diff --git a/data/developers/infly.json b/data/developers/infly.json
index fe3f0dc6f7a4b2c08dd2895544fd05de4f16df3c..d497bf1e2632542284e99f21127cba81c8ed1b97 100644
--- a/data/developers/infly.json
+++ b/data/developers/infly.json
@@ -7,16 +7,16 @@
       "developer": "infly",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "reward-bench/Score": 0.7648,
-        "reward-bench/Chat": 0.9665,
-        "reward-bench/Chat Hard": 0.9101,
-        "reward-bench/Safety": 0.9644,
-        "reward-bench/Reasoning": 0.9912,
+        "reward-bench/Score": 0.9511,
         "reward-bench/Factuality": 0.7411,
         "reward-bench/Precise IF": 0.4188,
         "reward-bench/Math": 0.6995,
+        "reward-bench/Safety": 0.9365,
         "reward-bench/Focus": 0.903,
-        "reward-bench/Ties": 0.8622
+        "reward-bench/Ties": 0.8622,
+        "reward-bench/Chat": 0.9665,
+        "reward-bench/Chat Hard": 0.9101,
+        "reward-bench/Reasoning": 0.9912
       }
     }
   ]
diff --git a/data/developers/internlm.json b/data/developers/internlm.json
index ba5efe87a4d9e153aadeeeaadd0b465b5955bdd6..035007101b6dacaf9414107420239eb159a0ec86 100644
--- a/data/developers/internlm.json
+++ b/data/developers/internlm.json
@@ -21,16 +21,16 @@
       "developer": "internlm",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "reward-bench/Score": 0.3902,
-        "reward-bench/Chat": 0.9358,
-        "reward-bench/Chat Hard": 0.6623,
-        "reward-bench/Safety": 0.4711,
-        "reward-bench/Reasoning": 0.8724,
+        "reward-bench/Score": 0.8217,
         "reward-bench/Factuality": 0.2758,
         "reward-bench/Precise IF": 0.3625,
         "reward-bench/Math": 0.4426,
+        "reward-bench/Safety": 0.8162,
         "reward-bench/Focus": 0.596,
-        "reward-bench/Ties": 0.1934
+        "reward-bench/Ties": 0.1934,
+        "reward-bench/Chat": 0.9358,
+        "reward-bench/Chat Hard": 0.6623,
+        "reward-bench/Reasoning": 0.8724
       }
     },
     {
@@ -39,16 +39,16 @@
       "developer": "internlm",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "reward-bench/Score": 0.9016,
+        "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/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/Chat": 0.9888,
-        "reward-bench/Chat Hard": 0.7654,
-        "reward-bench/Reasoning": 0.9576
+        "reward-bench/Ties": 0.5483
       }
     },
     {
diff --git a/data/developers/isaak-carter.json b/data/developers/isaak-carter.json
index 690871bc9bb32834a871ee3cfe82d0488b7c6bad..5e4243cedab9b62fa1fd1f8e9be8ea7f6c708259 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": 0.2477,
-        "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
+        "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
       }
     }
   ]
diff --git a/data/developers/jaspionjader.json b/data/developers/jaspionjader.json
index 053d128582b4aa02040ae51cd0577288669f17e5..9d9d1e268e56a9945ae657deca0493de6a22ce3d 100644
--- a/data/developers/jaspionjader.json
+++ b/data/developers/jaspionjader.json
@@ -1477,12 +1477,12 @@
       "developer": "jaspionjader",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "hfopenllm_v2/IFEval": 0.4345,
-        "hfopenllm_v2/BBH": 0.5419,
-        "hfopenllm_v2/MATH Level 5": 0.1292,
-        "hfopenllm_v2/GPQA": 0.3087,
+        "hfopenllm_v2/IFEval": 0.4418,
+        "hfopenllm_v2/BBH": 0.5406,
+        "hfopenllm_v2/MATH Level 5": 0.1352,
+        "hfopenllm_v2/GPQA": 0.3062,
         "hfopenllm_v2/MUSR": 0.4277,
-        "hfopenllm_v2/MMLU-PRO": 0.3854
+        "hfopenllm_v2/MMLU-PRO": 0.386
       }
     },
     {
diff --git a/data/developers/kavonalds.json b/data/developers/kavonalds.json
index c5a641658de284c1f8e0579f706e8c77674e2dfa..3c38b58473bebadc89fb67cf205ea04b79c73205 100644
--- a/data/developers/kavonalds.json
+++ b/data/developers/kavonalds.json
@@ -7,12 +7,12 @@
       "developer": "kavonalds",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "hfopenllm_v2/IFEval": 0.2701,
-        "hfopenllm_v2/BBH": 0.5566,
+        "hfopenllm_v2/IFEval": 0.3283,
+        "hfopenllm_v2/BBH": 0.6651,
         "hfopenllm_v2/MATH Level 5": 0.068,
-        "hfopenllm_v2/GPQA": 0.2802,
-        "hfopenllm_v2/MUSR": 0.3682,
-        "hfopenllm_v2/MMLU-PRO": 0.1449
+        "hfopenllm_v2/GPQA": 0.2609,
+        "hfopenllm_v2/MUSR": 0.3393,
+        "hfopenllm_v2/MMLU-PRO": 0.1314
       }
     },
     {
diff --git a/data/developers/lxzgordon.json b/data/developers/lxzgordon.json
index e4ace3cc8f7193c8c711403c980535ee73fdd6d3..7f802cf733857054e01537f3ecf745a3fdb38a05 100644
--- a/data/developers/lxzgordon.json
+++ b/data/developers/lxzgordon.json
@@ -20,16 +20,16 @@
       "developer": "LxzGordon",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "reward-bench/Score": 0.9294,
+        "reward-bench/Score": 0.7394,
+        "reward-bench/Chat": 0.9553,
+        "reward-bench/Chat Hard": 0.8816,
+        "reward-bench/Safety": 0.9178,
+        "reward-bench/Reasoning": 0.9698,
         "reward-bench/Factuality": 0.6884,
         "reward-bench/Precise IF": 0.45,
         "reward-bench/Math": 0.6393,
-        "reward-bench/Safety": 0.9108,
         "reward-bench/Focus": 0.9758,
-        "reward-bench/Ties": 0.7653,
-        "reward-bench/Chat": 0.9553,
-        "reward-bench/Chat Hard": 0.8816,
-        "reward-bench/Reasoning": 0.9698
+        "reward-bench/Ties": 0.7653
       }
     }
   ]
diff --git a/data/developers/magpie-align.json b/data/developers/magpie-align.json
index 155a416e715db19186e6af681f6736ea9ed101d1..0dc0a43e89bb456a61006caa30051add55effb08 100644
--- a/data/developers/magpie-align.json
+++ b/data/developers/magpie-align.json
@@ -35,12 +35,12 @@
       "developer": "Magpie-Align",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "hfopenllm_v2/IFEval": 0.4118,
-        "hfopenllm_v2/BBH": 0.4811,
-        "hfopenllm_v2/MATH Level 5": 0.034,
-        "hfopenllm_v2/GPQA": 0.2752,
-        "hfopenllm_v2/MUSR": 0.3047,
-        "hfopenllm_v2/MMLU-PRO": 0.3006
+        "hfopenllm_v2/IFEval": 0.4027,
+        "hfopenllm_v2/BBH": 0.4789,
+        "hfopenllm_v2/MATH Level 5": 0.0461,
+        "hfopenllm_v2/GPQA": 0.2768,
+        "hfopenllm_v2/MUSR": 0.3087,
+        "hfopenllm_v2/MMLU-PRO": 0.3001
       }
     },
     {
diff --git a/data/developers/meta-llama.json b/data/developers/meta-llama.json
index a28b7c096e670398e8b74d7b30002bc56044221b..76d923e16aab37465ed7dda94d7be71e39f4b29e 100644
--- a/data/developers/meta-llama.json
+++ b/data/developers/meta-llama.json
@@ -265,12 +265,12 @@
       "developer": "meta-llama",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "hfopenllm_v2/IFEval": 0.4782,
-        "hfopenllm_v2/BBH": 0.491,
-        "hfopenllm_v2/MATH Level 5": 0.0914,
-        "hfopenllm_v2/GPQA": 0.2928,
-        "hfopenllm_v2/MUSR": 0.3805,
-        "hfopenllm_v2/MMLU-PRO": 0.3591,
+        "hfopenllm_v2/IFEval": 0.7408,
+        "hfopenllm_v2/BBH": 0.4989,
+        "hfopenllm_v2/MATH Level 5": 0.0869,
+        "hfopenllm_v2/GPQA": 0.2592,
+        "hfopenllm_v2/MUSR": 0.3568,
+        "hfopenllm_v2/MMLU-PRO": 0.3664,
         "reward-bench/Score": 0.645,
         "reward-bench/Chat": 0.8547,
         "reward-bench/Chat Hard": 0.4156,
diff --git a/data/developers/mistralai.json b/data/developers/mistralai.json
index 57d196d824fe3b2d3e0a8303970991b9f16872ee..168bb98ff1b313fc7d40f024df899fec3a02671f 100644
--- a/data/developers/mistralai.json
+++ b/data/developers/mistralai.json
@@ -513,12 +513,12 @@
       "developer": "mistralai",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "hfopenllm_v2/IFEval": 0.6283,
-        "hfopenllm_v2/BBH": 0.583,
-        "hfopenllm_v2/MATH Level 5": 0.2039,
-        "hfopenllm_v2/GPQA": 0.3331,
-        "hfopenllm_v2/MUSR": 0.4063,
-        "hfopenllm_v2/MMLU-PRO": 0.4099
+        "hfopenllm_v2/IFEval": 0.667,
+        "hfopenllm_v2/BBH": 0.5213,
+        "hfopenllm_v2/MATH Level 5": 0.1435,
+        "hfopenllm_v2/GPQA": 0.3238,
+        "hfopenllm_v2/MUSR": 0.3632,
+        "hfopenllm_v2/MMLU-PRO": 0.396
       }
     },
     {
diff --git a/data/developers/mlabonne.json b/data/developers/mlabonne.json
index 2620a8c4e8931697abdcd44e4a4aae7c1e430da5..be86bd7fe732025f133b06dc7c412aa5e56b7119 100644
--- a/data/developers/mlabonne.json
+++ b/data/developers/mlabonne.json
@@ -161,12 +161,12 @@
       "developer": "mlabonne",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "hfopenllm_v2/IFEval": 0.7561,
-        "hfopenllm_v2/BBH": 0.5111,
-        "hfopenllm_v2/MATH Level 5": 0.0906,
-        "hfopenllm_v2/GPQA": 0.3062,
-        "hfopenllm_v2/MUSR": 0.4019,
-        "hfopenllm_v2/MMLU-PRO": 0.3841
+        "hfopenllm_v2/IFEval": 0.4162,
+        "hfopenllm_v2/BBH": 0.5124,
+        "hfopenllm_v2/MATH Level 5": 0.0853,
+        "hfopenllm_v2/GPQA": 0.3029,
+        "hfopenllm_v2/MUSR": 0.415,
+        "hfopenllm_v2/MMLU-PRO": 0.3802
       }
     },
     {
diff --git a/data/developers/moonshot_ai.json b/data/developers/moonshot_ai.json
index d83f11402fcca0c39c33d09eed495f2aefd69384..746185ce773a539bd025922ab856fdcf2f8a1d9f 100644
--- a/data/developers/moonshot_ai.json
+++ b/data/developers/moonshot_ai.json
@@ -7,7 +7,7 @@
       "developer": "Moonshot AI",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "terminal-bench-2.0/terminal-bench-2.0": 26.7
+        "terminal-bench-2.0/terminal-bench-2.0": 27.8
       }
     },
     {
diff --git a/data/developers/multiple.json b/data/developers/multiple.json
index 3ca416f37a8a2d37629452327cce332c02e2b948..34cdb844d495e12fd3a3820204fbda313306e211 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": 58.4
+        "terminal-bench-2.0/terminal-bench-2.0": 72.4
       }
     }
   ]
diff --git a/data/developers/ncsoft.json b/data/developers/ncsoft.json
index 78886a7e33419ae72417f31ea13b0a41a2a3ced1..5cc19c52d2bf4d85f74e73a3056f8da048c42869 100644
--- a/data/developers/ncsoft.json
+++ b/data/developers/ncsoft.json
@@ -20,16 +20,16 @@
       "developer": "NCSOFT",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "reward-bench/Score": 0.8942,
+        "reward-bench/Score": 0.648,
+        "reward-bench/Chat": 0.9721,
+        "reward-bench/Chat Hard": 0.818,
+        "reward-bench/Safety": 0.7222,
+        "reward-bench/Reasoning": 0.9192,
         "reward-bench/Factuality": 0.6084,
         "reward-bench/Precise IF": 0.4,
         "reward-bench/Math": 0.5191,
-        "reward-bench/Safety": 0.8676,
         "reward-bench/Focus": 0.9596,
-        "reward-bench/Ties": 0.6786,
-        "reward-bench/Chat": 0.9721,
-        "reward-bench/Chat Hard": 0.818,
-        "reward-bench/Reasoning": 0.9192
+        "reward-bench/Ties": 0.6786
       }
     },
     {
diff --git a/data/developers/nexusflow.json b/data/developers/nexusflow.json
index 49fe739e7104f59b148ecb24e067de8a0cb500b5..2f78cab8780e463261ce35ef251c295eb3f3fd0f 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": 0.4553,
-        "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/Score": 0.8133,
         "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/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
       }
     }
   ]
diff --git a/data/developers/ontocord.json b/data/developers/ontocord.json
index add41dbe183800ebed90c916e0b704c974dd50e7..c16f4cbacdda3485b721f459b079923a6793a670 100644
--- a/data/developers/ontocord.json
+++ b/data/developers/ontocord.json
@@ -273,12 +273,12 @@
       "developer": "ontocord",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "hfopenllm_v2/IFEval": 0.1162,
-        "hfopenllm_v2/BBH": 0.3184,
-        "hfopenllm_v2/MATH Level 5": 0.0076,
-        "hfopenllm_v2/GPQA": 0.2634,
-        "hfopenllm_v2/MUSR": 0.3447,
-        "hfopenllm_v2/MMLU-PRO": 0.1124
+        "hfopenllm_v2/IFEval": 0.1128,
+        "hfopenllm_v2/BBH": 0.3171,
+        "hfopenllm_v2/MATH Level 5": 0.0113,
+        "hfopenllm_v2/GPQA": 0.2685,
+        "hfopenllm_v2/MUSR": 0.346,
+        "hfopenllm_v2/MMLU-PRO": 0.1129
       }
     },
     {
diff --git a/data/developers/openai.json b/data/developers/openai.json
index ede5404bc51db07d8e63c7bbcb6be1b005184ac0..778495ca5d9933e50afc2a386628c3370e3c9523 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,
-        "ace/Overall Score": 0.515,
-        "ace/Food Score": 0.65,
-        "ace/Gaming Score": 0.578
+        "apex-agents/Corporate Lawyer Mean Score": 0.443
       }
     },
     {
@@ -772,16 +772,16 @@
         "helm_mmlu/Virology": 0.578,
         "helm_mmlu/World Religions": 0.883,
         "helm_mmlu/Mean win rate": 0.52,
-        "reward-bench/Score": 0.8673,
+        "reward-bench/Score": 0.6493,
+        "reward-bench/Chat": 0.9609,
+        "reward-bench/Chat Hard": 0.761,
+        "reward-bench/Safety": 0.8619,
+        "reward-bench/Reasoning": 0.8661,
         "reward-bench/Factuality": 0.5684,
         "reward-bench/Precise IF": 0.3312,
         "reward-bench/Math": 0.623,
-        "reward-bench/Safety": 0.8811,
         "reward-bench/Focus": 0.7293,
-        "reward-bench/Ties": 0.7819,
-        "reward-bench/Chat": 0.9609,
-        "reward-bench/Chat Hard": 0.761,
-        "reward-bench/Reasoning": 0.8661
+        "reward-bench/Ties": 0.7819
       }
     },
     {
@@ -859,16 +859,16 @@
         "helm_mmlu/Virology": 0.536,
         "helm_mmlu/World Religions": 0.86,
         "helm_mmlu/Mean win rate": 0.774,
-        "reward-bench/Score": 0.8007,
+        "reward-bench/Score": 0.5796,
+        "reward-bench/Chat": 0.9497,
+        "reward-bench/Chat Hard": 0.6075,
+        "reward-bench/Safety": 0.7667,
+        "reward-bench/Reasoning": 0.8374,
         "reward-bench/Factuality": 0.4105,
         "reward-bench/Precise IF": 0.3438,
         "reward-bench/Math": 0.5191,
-        "reward-bench/Safety": 0.8081,
         "reward-bench/Focus": 0.7414,
-        "reward-bench/Ties": 0.6962,
-        "reward-bench/Chat": 0.9497,
-        "reward-bench/Chat Hard": 0.6075,
-        "reward-bench/Reasoning": 0.8374
+        "reward-bench/Ties": 0.6962
       }
     },
     {
@@ -922,7 +922,7 @@
       "developer": "OpenAI",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "terminal-bench-2.0/terminal-bench-2.0": 41.3
+        "terminal-bench-2.0/terminal-bench-2.0": 43.4
       }
     },
     {
@@ -931,7 +931,7 @@
       "developer": "OpenAI",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "terminal-bench-2.0/terminal-bench-2.0": 22.2
+        "terminal-bench-2.0/terminal-bench-2.0": 34.8
       }
     },
     {
@@ -954,7 +954,7 @@
       "developer": "OpenAI",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "terminal-bench-2.0/terminal-bench-2.0": 7.9
+        "terminal-bench-2.0/terminal-bench-2.0": 7.0
       }
     },
     {
@@ -986,7 +986,7 @@
       "developer": "OpenAI",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "terminal-bench-2.0/terminal-bench-2.0": 36.9
+        "terminal-bench-2.0/terminal-bench-2.0": 53.5
       }
     },
     {
@@ -1013,7 +1013,7 @@
       "developer": "OpenAI",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "terminal-bench-2.0/terminal-bench-2.0": 54.0
+        "terminal-bench-2.0/terminal-bench-2.0": 60.7
       }
     },
     {
@@ -1022,15 +1022,15 @@
       "developer": "OpenAI",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "appworld_test_normal/appworld/test_normal": 0.0,
-        "browsecompplus/browsecompplus": 0.48,
+        "appworld_test_normal/appworld/test_normal": 0.071,
+        "browsecompplus/browsecompplus": 0.46,
         "livecodebenchpro/Hard Problems": 0.1594,
         "livecodebenchpro/Medium Problems": 0.5211,
         "livecodebenchpro/Easy Problems": 0.9014,
-        "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
+        "swe-bench/swe-bench": 0.57,
+        "tau-bench-2_airline/tau-bench-2/airline": 0.6,
+        "tau-bench-2_retail/tau-bench-2/retail": 0.73,
+        "tau-bench-2_telecom/tau-bench-2/telecom": 0.55
       }
     },
     {
@@ -1048,7 +1048,7 @@
       "developer": "OpenAI",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "terminal-bench-2.0/terminal-bench-2.0": 77.3
+        "terminal-bench-2.0/terminal-bench-2.0": 74.6
       }
     },
     {
@@ -1130,7 +1130,7 @@
         "livecodebenchpro/Hard Problems": 0.0,
         "livecodebenchpro/Medium Problems": 0.056338028169014086,
         "livecodebenchpro/Easy Problems": 0.5070422535211268,
-        "terminal-bench-2.0/terminal-bench-2.0": 3.4
+        "terminal-bench-2.0/terminal-bench-2.0": 3.1
       }
     },
     {
diff --git a/data/developers/openassistant.json b/data/developers/openassistant.json
index 95e3fbf7702e838e1924ccdd51ef3a7ea27c9d5c..94a84f4efb74c56aff95d97f1dc674cfa0445541 100644
--- a/data/developers/openassistant.json
+++ b/data/developers/openassistant.json
@@ -59,17 +59,17 @@
       "developer": "OpenAssistant",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "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/Score": 0.6126,
         "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/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
       }
     }
   ]
diff --git a/data/developers/openbmb.json b/data/developers/openbmb.json
index b9795ed819d46987af7a443e489394fa08308cdd..d8dae84054074ce01b5c47fc58b69a148fdc99c0 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": 0.5806,
-        "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/Score": 0.8159,
         "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/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
       }
     },
     {
diff --git a/data/developers/pku-alignment.json b/data/developers/pku-alignment.json
index 4cebe3d4c55c06b2bbbd44b7bb6fe487a030b922..b42d9be156feba13e7cdbffbd62351a64e28c1fb 100644
--- a/data/developers/pku-alignment.json
+++ b/data/developers/pku-alignment.json
@@ -7,17 +7,17 @@
       "developer": "PKU-Alignment",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "reward-bench/Score": 0.3332,
-        "reward-bench/Chat": 0.6173,
-        "reward-bench/Chat Hard": 0.4232,
-        "reward-bench/Safety": 0.7589,
-        "reward-bench/Reasoning": 0.5482,
-        "reward-bench/Prior Sets (0.5 weight)": 0.57,
+        "reward-bench/Score": 0.5798,
         "reward-bench/Factuality": 0.3263,
         "reward-bench/Precise IF": 0.2313,
         "reward-bench/Math": 0.3989,
+        "reward-bench/Safety": 0.7351,
         "reward-bench/Focus": 0.2939,
-        "reward-bench/Ties": -0.01
+        "reward-bench/Ties": -0.01,
+        "reward-bench/Chat": 0.6173,
+        "reward-bench/Chat Hard": 0.4232,
+        "reward-bench/Reasoning": 0.5482,
+        "reward-bench/Prior Sets (0.5 weight)": 0.57
       }
     },
     {
diff --git a/data/developers/prithivmlmods.json b/data/developers/prithivmlmods.json
index 88e743a4279f310dec935aed3968189a78be084e..f14f3864a910968b11c756eb8300bd4bd3eea36e 100644
--- a/data/developers/prithivmlmods.json
+++ b/data/developers/prithivmlmods.json
@@ -63,12 +63,12 @@
       "developer": "prithivMLmods",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "hfopenllm_v2/IFEval": 0.6052,
-        "hfopenllm_v2/BBH": 0.6317,
-        "hfopenllm_v2/MATH Level 5": 0.4789,
-        "hfopenllm_v2/GPQA": 0.3742,
-        "hfopenllm_v2/MUSR": 0.486,
-        "hfopenllm_v2/MMLU-PRO": 0.5302
+        "hfopenllm_v2/IFEval": 0.6064,
+        "hfopenllm_v2/BBH": 0.6296,
+        "hfopenllm_v2/MATH Level 5": 0.3708,
+        "hfopenllm_v2/GPQA": 0.3733,
+        "hfopenllm_v2/MUSR": 0.4873,
+        "hfopenllm_v2/MMLU-PRO": 0.5307
       }
     },
     {
diff --git a/data/developers/qingy2019.json b/data/developers/qingy2019.json
index b11a9d79a541432fdd0c8e33c56cfaa201540388..3885f54f7f780ebe87cee5b8aacc1c1136f4441f 100644
--- a/data/developers/qingy2019.json
+++ b/data/developers/qingy2019.json
@@ -49,12 +49,12 @@
       "developer": "qingy2019",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "hfopenllm_v2/IFEval": 0.6005,
-        "hfopenllm_v2/BBH": 0.6356,
-        "hfopenllm_v2/MATH Level 5": 0.2764,
-        "hfopenllm_v2/GPQA": 0.3691,
+        "hfopenllm_v2/IFEval": 0.6066,
+        "hfopenllm_v2/BBH": 0.635,
+        "hfopenllm_v2/MATH Level 5": 0.3716,
+        "hfopenllm_v2/GPQA": 0.3725,
         "hfopenllm_v2/MUSR": 0.4757,
-        "hfopenllm_v2/MMLU-PRO": 0.5339
+        "hfopenllm_v2/MMLU-PRO": 0.5331
       }
     },
     {
diff --git a/data/developers/ray2333.json b/data/developers/ray2333.json
index 51f9b51d9ebb192a98a4a9a46633e05cf73f77b6..709d24161c8237750555868d00eabe667376cddb 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": 0.8464,
+        "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/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/Chat": 0.9832,
-        "reward-bench/Chat Hard": 0.6842,
-        "reward-bench/Reasoning": 0.9133,
-        "reward-bench/Prior Sets (0.5 weight)": 0.7209
+        "reward-bench/Ties": 0.5743
       }
     },
     {
@@ -98,16 +98,16 @@
       "developer": "Ray2333",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "reward-bench/Score": 0.9154,
+        "reward-bench/Score": 0.6766,
+        "reward-bench/Chat": 0.9553,
+        "reward-bench/Chat Hard": 0.8618,
+        "reward-bench/Safety": 0.9222,
+        "reward-bench/Reasoning": 0.9362,
         "reward-bench/Factuality": 0.6274,
         "reward-bench/Precise IF": 0.35,
         "reward-bench/Math": 0.5847,
-        "reward-bench/Safety": 0.9081,
         "reward-bench/Focus": 0.8929,
-        "reward-bench/Ties": 0.6824,
-        "reward-bench/Chat": 0.9553,
-        "reward-bench/Chat Hard": 0.8618,
-        "reward-bench/Reasoning": 0.9362
+        "reward-bench/Ties": 0.6824
       }
     },
     {
@@ -116,17 +116,17 @@
       "developer": "Ray2333",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "reward-bench/Score": 0.8542,
+        "reward-bench/Score": 0.6089,
+        "reward-bench/Chat": 0.986,
+        "reward-bench/Chat Hard": 0.6776,
+        "reward-bench/Safety": 0.7867,
+        "reward-bench/Reasoning": 0.9229,
+        "reward-bench/Prior Sets (0.5 weight)": 0.7309,
         "reward-bench/Factuality": 0.6189,
         "reward-bench/Precise IF": 0.3875,
         "reward-bench/Math": 0.5792,
-        "reward-bench/Safety": 0.8919,
         "reward-bench/Focus": 0.6828,
-        "reward-bench/Ties": 0.5981,
-        "reward-bench/Chat": 0.986,
-        "reward-bench/Chat Hard": 0.6776,
-        "reward-bench/Reasoning": 0.9229,
-        "reward-bench/Prior Sets (0.5 weight)": 0.7309
+        "reward-bench/Ties": 0.5981
       }
     },
     {
diff --git a/data/developers/recoilme.json b/data/developers/recoilme.json
index 50baa7f16a67b3ee26a355a9f5b41de814bc7e52..a767d74249450554babea0e0fb1705321ef571fe 100644
--- a/data/developers/recoilme.json
+++ b/data/developers/recoilme.json
@@ -7,12 +7,12 @@
       "developer": "recoilme",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "hfopenllm_v2/IFEval": 0.2854,
-        "hfopenllm_v2/BBH": 0.5984,
-        "hfopenllm_v2/MATH Level 5": 0.1005,
-        "hfopenllm_v2/GPQA": 0.3297,
-        "hfopenllm_v2/MUSR": 0.4607,
-        "hfopenllm_v2/MMLU-PRO": 0.4162
+        "hfopenllm_v2/IFEval": 0.7649,
+        "hfopenllm_v2/BBH": 0.5974,
+        "hfopenllm_v2/MATH Level 5": 0.0174,
+        "hfopenllm_v2/GPQA": 0.3305,
+        "hfopenllm_v2/MUSR": 0.4245,
+        "hfopenllm_v2/MMLU-PRO": 0.4207
       }
     },
     {
@@ -35,12 +35,12 @@
       "developer": "recoilme",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "hfopenllm_v2/IFEval": 0.2747,
-        "hfopenllm_v2/BBH": 0.6031,
-        "hfopenllm_v2/MATH Level 5": 0.0831,
-        "hfopenllm_v2/GPQA": 0.3305,
-        "hfopenllm_v2/MUSR": 0.4686,
-        "hfopenllm_v2/MMLU-PRO": 0.4122
+        "hfopenllm_v2/IFEval": 0.7592,
+        "hfopenllm_v2/BBH": 0.6026,
+        "hfopenllm_v2/MATH Level 5": 0.0529,
+        "hfopenllm_v2/GPQA": 0.3289,
+        "hfopenllm_v2/MUSR": 0.4099,
+        "hfopenllm_v2/MMLU-PRO": 0.4163
       }
     },
     {
@@ -49,12 +49,12 @@
       "developer": "recoilme",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "hfopenllm_v2/IFEval": 0.7439,
-        "hfopenllm_v2/BBH": 0.5993,
-        "hfopenllm_v2/MATH Level 5": 0.0876,
-        "hfopenllm_v2/GPQA": 0.3238,
-        "hfopenllm_v2/MUSR": 0.4204,
-        "hfopenllm_v2/MMLU-PRO": 0.4072
+        "hfopenllm_v2/IFEval": 0.5761,
+        "hfopenllm_v2/BBH": 0.602,
+        "hfopenllm_v2/MATH Level 5": 0.1888,
+        "hfopenllm_v2/GPQA": 0.3372,
+        "hfopenllm_v2/MUSR": 0.4632,
+        "hfopenllm_v2/MMLU-PRO": 0.4039
       }
     },
     {
diff --git a/data/developers/replete-ai.json b/data/developers/replete-ai.json
index dbb06f00736a7fcddf76b24a5c7673e098ecab57..0f038b31b0c0cf28a02b6c25fb4fd9bd374c118c 100644
--- a/data/developers/replete-ai.json
+++ b/data/developers/replete-ai.json
@@ -91,12 +91,12 @@
       "developer": "Replete-AI",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "hfopenllm_v2/IFEval": 0.0932,
-        "hfopenllm_v2/BBH": 0.2977,
+        "hfopenllm_v2/IFEval": 0.0905,
+        "hfopenllm_v2/BBH": 0.2985,
         "hfopenllm_v2/MATH Level 5": 0.0,
-        "hfopenllm_v2/GPQA": 0.2475,
-        "hfopenllm_v2/MUSR": 0.3941,
-        "hfopenllm_v2/MMLU-PRO": 0.1157
+        "hfopenllm_v2/GPQA": 0.2534,
+        "hfopenllm_v2/MUSR": 0.3848,
+        "hfopenllm_v2/MMLU-PRO": 0.1158
       }
     },
     {
diff --git a/data/developers/riaz.json b/data/developers/riaz.json
index d54f5bbaf70d322fa875b56275f987dd3ae70f34..342d5654379425c9866753c909eb0413c18e5c77 100644
--- a/data/developers/riaz.json
+++ b/data/developers/riaz.json
@@ -7,12 +7,12 @@
       "developer": "riaz",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "hfopenllm_v2/IFEval": 0.4373,
-        "hfopenllm_v2/BBH": 0.4586,
-        "hfopenllm_v2/MATH Level 5": 0.0514,
-        "hfopenllm_v2/GPQA": 0.2752,
-        "hfopenllm_v2/MUSR": 0.3763,
-        "hfopenllm_v2/MMLU-PRO": 0.2964
+        "hfopenllm_v2/IFEval": 0.4137,
+        "hfopenllm_v2/BBH": 0.4565,
+        "hfopenllm_v2/MATH Level 5": 0.0453,
+        "hfopenllm_v2/GPQA": 0.276,
+        "hfopenllm_v2/MUSR": 0.3776,
+        "hfopenllm_v2/MMLU-PRO": 0.2978
       }
     }
   ]
diff --git a/data/developers/rombodawg.json b/data/developers/rombodawg.json
index e7b347a91d5be7f4c52661e255a50c99caa3a3fd..a241fbd73dcecc7fc768ef47719ff98c1bcb64ab 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": 0.2566,
-        "hfopenllm_v2/BBH": 0.39,
-        "hfopenllm_v2/MATH Level 5": 0.1208,
-        "hfopenllm_v2/GPQA": 0.2626,
+        "hfopenllm_v2/IFEval": 0.2595,
+        "hfopenllm_v2/BBH": 0.3884,
+        "hfopenllm_v2/MATH Level 5": 0.0914,
+        "hfopenllm_v2/GPQA": 0.2743,
         "hfopenllm_v2/MUSR": 0.3991,
-        "hfopenllm_v2/MMLU-PRO": 0.2741
+        "hfopenllm_v2/MMLU-PRO": 0.2719
       }
     },
     {
diff --git a/data/developers/sao10k.json b/data/developers/sao10k.json
index 6569058a39b468de833ea3ab9419e073af211e5a..e66900f1906266fdf37e55995d3b04130f5b6fd2 100644
--- a/data/developers/sao10k.json
+++ b/data/developers/sao10k.json
@@ -35,12 +35,12 @@
       "developer": "Sao10K",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "hfopenllm_v2/IFEval": 0.7281,
-        "hfopenllm_v2/BBH": 0.6503,
-        "hfopenllm_v2/MATH Level 5": 0.2243,
+        "hfopenllm_v2/IFEval": 0.7384,
+        "hfopenllm_v2/BBH": 0.6471,
+        "hfopenllm_v2/MATH Level 5": 0.2137,
         "hfopenllm_v2/GPQA": 0.3314,
-        "hfopenllm_v2/MUSR": 0.4196,
-        "hfopenllm_v2/MMLU-PRO": 0.5096
+        "hfopenllm_v2/MUSR": 0.4209,
+        "hfopenllm_v2/MMLU-PRO": 0.5104
       }
     },
     {
diff --git a/data/developers/shikaichen.json b/data/developers/shikaichen.json
index 6162cba6dec7eaed27af88272ffb98342af2522b..6502ef5b0e02cc85862537458f25816eb0826b7d 100644
--- a/data/developers/shikaichen.json
+++ b/data/developers/shikaichen.json
@@ -7,16 +7,16 @@
       "developer": "ShikaiChen",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "reward-bench/Score": 0.9499,
+        "reward-bench/Score": 0.7249,
+        "reward-bench/Chat": 0.9637,
+        "reward-bench/Chat Hard": 0.9079,
+        "reward-bench/Safety": 0.9222,
+        "reward-bench/Reasoning": 0.9903,
         "reward-bench/Factuality": 0.7558,
         "reward-bench/Precise IF": 0.35,
         "reward-bench/Math": 0.6448,
-        "reward-bench/Safety": 0.9378,
         "reward-bench/Focus": 0.9131,
-        "reward-bench/Ties": 0.7633,
-        "reward-bench/Chat": 0.9637,
-        "reward-bench/Chat Hard": 0.9079,
-        "reward-bench/Reasoning": 0.9903
+        "reward-bench/Ties": 0.7633
       }
     }
   ]
diff --git a/data/developers/skywork.json b/data/developers/skywork.json
index a1886dbde5ab2f08ceeb175a3c92e5b11655f24d..b75ac4fa3e86dd1c341887c14306e39e694944d2 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": 0.7531,
-        "reward-bench/Chat": 0.9609,
-        "reward-bench/Chat Hard": 0.8991,
-        "reward-bench/Safety": 0.9689,
-        "reward-bench/Reasoning": 0.9807,
+        "reward-bench/Score": 0.9426,
         "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/Ties": 0.8182,
+        "reward-bench/Chat": 0.9609,
+        "reward-bench/Chat Hard": 0.8991,
+        "reward-bench/Reasoning": 0.9807
       }
     },
     {
diff --git a/data/developers/tanliboy.json b/data/developers/tanliboy.json
index daa17945601d8528cbfc7c883e4dc4315ea363fc..7b17e651b33310ae087a6456408950e1456ff623 100644
--- a/data/developers/tanliboy.json
+++ b/data/developers/tanliboy.json
@@ -7,12 +7,12 @@
       "developer": "tanliboy",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "hfopenllm_v2/IFEval": 0.4501,
-        "hfopenllm_v2/BBH": 0.5472,
-        "hfopenllm_v2/MATH Level 5": 0.0944,
-        "hfopenllm_v2/GPQA": 0.3138,
-        "hfopenllm_v2/MUSR": 0.4017,
-        "hfopenllm_v2/MMLU-PRO": 0.3792
+        "hfopenllm_v2/IFEval": 0.1829,
+        "hfopenllm_v2/BBH": 0.5488,
+        "hfopenllm_v2/MATH Level 5": 0.0,
+        "hfopenllm_v2/GPQA": 0.3104,
+        "hfopenllm_v2/MUSR": 0.4056,
+        "hfopenllm_v2/MMLU-PRO": 0.3805
       }
     },
     {
diff --git a/data/developers/valiantlabs.json b/data/developers/valiantlabs.json
index fea79922ada6f8587a14d0c683f2c0090d2ca061..a0fc2b3d81b7ddfe31ae4c63f4f370e45c708501 100644
--- a/data/developers/valiantlabs.json
+++ b/data/developers/valiantlabs.json
@@ -105,12 +105,12 @@
       "developer": "ValiantLabs",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "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
+        "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
       }
     },
     {
diff --git a/data/developers/weqweasdas.json b/data/developers/weqweasdas.json
index 36aa4e34297ffab30b15be8c96f1b385a32071bf..e11faa49d0109edbe3a144d975a897042bc51bca 100644
--- a/data/developers/weqweasdas.json
+++ b/data/developers/weqweasdas.json
@@ -7,17 +7,17 @@
       "developer": "weqweasdas",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "reward-bench/Score": 0.2498,
-        "reward-bench/Chat": 0.8184,
-        "reward-bench/Chat Hard": 0.3728,
-        "reward-bench/Safety": 0.24,
-        "reward-bench/Reasoning": 0.3281,
-        "reward-bench/Prior Sets (0.5 weight)": 0.6564,
+        "reward-bench/Score": 0.5027,
         "reward-bench/Factuality": 0.3642,
         "reward-bench/Precise IF": 0.275,
         "reward-bench/Math": 0.3497,
+        "reward-bench/Safety": 0.4149,
         "reward-bench/Focus": 0.2384,
-        "reward-bench/Ties": 0.0315
+        "reward-bench/Ties": 0.0315,
+        "reward-bench/Chat": 0.8184,
+        "reward-bench/Chat Hard": 0.3728,
+        "reward-bench/Reasoning": 0.3281,
+        "reward-bench/Prior Sets (0.5 weight)": 0.6564
       }
     },
     {
@@ -45,17 +45,17 @@
       "developer": "weqweasdas",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "reward-bench/Score": 0.4826,
-        "reward-bench/Chat": 0.9693,
-        "reward-bench/Chat Hard": 0.4978,
-        "reward-bench/Safety": 0.4822,
-        "reward-bench/Reasoning": 0.7362,
-        "reward-bench/Prior Sets (0.5 weight)": 0.7069,
+        "reward-bench/Score": 0.6967,
         "reward-bench/Factuality": 0.4926,
         "reward-bench/Precise IF": 0.3937,
         "reward-bench/Math": 0.6066,
+        "reward-bench/Safety": 0.5784,
         "reward-bench/Focus": 0.497,
-        "reward-bench/Ties": 0.4232
+        "reward-bench/Ties": 0.4232,
+        "reward-bench/Chat": 0.9693,
+        "reward-bench/Chat Hard": 0.4978,
+        "reward-bench/Reasoning": 0.7362,
+        "reward-bench/Prior Sets (0.5 weight)": 0.7069
       }
     },
     {
diff --git a/data/developers/xai.json b/data/developers/xai.json
index d0ba30a6d3c372a4bdb6c48d3c0cb90677ed30d5..4539ab8505af399ecb6f06dee4d4f2618de3e3bc 100644
--- a/data/developers/xai.json
+++ b/data/developers/xai.json
@@ -120,7 +120,7 @@
       "developer": "xAI",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "terminal-bench-2.0/terminal-bench-2.0": 14.2
+        "terminal-bench-2.0/terminal-bench-2.0": 25.8
       }
     }
   ]
diff --git a/data/developers/yam-peleg.json b/data/developers/yam-peleg.json
index 3161f95274f1998cddb90c53a59dce4097dbe0fd..f415128b8e93253c12ae15436b68cf36d5f248bf 100644
--- a/data/developers/yam-peleg.json
+++ b/data/developers/yam-peleg.json
@@ -35,12 +35,12 @@
       "developer": "yam-peleg",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "hfopenllm_v2/IFEval": 0.1856,
-        "hfopenllm_v2/BBH": 0.4149,
-        "hfopenllm_v2/MATH Level 5": 0.0234,
-        "hfopenllm_v2/GPQA": 0.276,
-        "hfopenllm_v2/MUSR": 0.3765,
-        "hfopenllm_v2/MMLU-PRO": 0.2573
+        "hfopenllm_v2/IFEval": 0.177,
+        "hfopenllm_v2/BBH": 0.3411,
+        "hfopenllm_v2/MATH Level 5": 0.031,
+        "hfopenllm_v2/GPQA": 0.2534,
+        "hfopenllm_v2/MUSR": 0.374,
+        "hfopenllm_v2/MMLU-PRO": 0.2529
       }
     }
   ]
diff --git a/data/models.json b/data/models.json
index b08337869e0315ca25ad74e1e682be0126b52503..a5af0007574aa89e984bf7d8a4b2911e04bfd788 100644
--- a/data/models.json
+++ b/data/models.json
@@ -1005,12 +1005,12 @@
     "developer": "adriszmar",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "hfopenllm_v2/IFEval": 0.1746,
-      "hfopenllm_v2/BBH": 0.3126,
-      "hfopenllm_v2/MATH Level 5": 0.0,
-      "hfopenllm_v2/GPQA": 0.245,
-      "hfopenllm_v2/MUSR": 0.4096,
-      "hfopenllm_v2/MMLU-PRO": 0.1087
+      "hfopenllm_v2/IFEval": 0.1685,
+      "hfopenllm_v2/BBH": 0.3124,
+      "hfopenllm_v2/MATH Level 5": 0.0015,
+      "hfopenllm_v2/GPQA": 0.2492,
+      "hfopenllm_v2/MUSR": 0.3963,
+      "hfopenllm_v2/MMLU-PRO": 0.1066
     }
   },
   {
@@ -1391,9 +1391,9 @@
     "developer": "AI2",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "reward-bench/Score": 0.7008,
-      "reward-bench/Chat": 0.9385,
-      "reward-bench/Chat Hard": 0.3882,
+      "reward-bench/Score": 0.6924,
+      "reward-bench/Chat": 0.9441,
+      "reward-bench/Chat Hard": 0.3575,
       "reward-bench/Safety": 0.7757
     }
   },
@@ -2390,17 +2390,17 @@
     "developer": "allenai",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "reward-bench/Score": 0.9021,
+      "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/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/Chat": 0.9665,
-      "reward-bench/Chat Hard": 0.8355,
-      "reward-bench/Reasoning": 0.8969,
-      "reward-bench/Prior Sets (0.5 weight)": 0.0
+      "reward-bench/Ties": 0.8835
     }
   },
   {
@@ -2447,12 +2447,12 @@
     "developer": "allenai",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "hfopenllm_v2/IFEval": 0.8379,
-      "hfopenllm_v2/BBH": 0.6157,
-      "hfopenllm_v2/MATH Level 5": 0.3829,
+      "hfopenllm_v2/IFEval": 0.8291,
+      "hfopenllm_v2/BBH": 0.6164,
+      "hfopenllm_v2/MATH Level 5": 0.4502,
       "hfopenllm_v2/GPQA": 0.3733,
-      "hfopenllm_v2/MUSR": 0.4988,
-      "hfopenllm_v2/MMLU-PRO": 0.4656
+      "hfopenllm_v2/MUSR": 0.4948,
+      "hfopenllm_v2/MMLU-PRO": 0.4645
     }
   },
   {
@@ -2508,12 +2508,12 @@
     "developer": "allenai",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "hfopenllm_v2/IFEval": 0.8267,
-      "hfopenllm_v2/BBH": 0.405,
-      "hfopenllm_v2/MATH Level 5": 0.1964,
-      "hfopenllm_v2/GPQA": 0.2987,
+      "hfopenllm_v2/IFEval": 0.8255,
+      "hfopenllm_v2/BBH": 0.4061,
+      "hfopenllm_v2/MATH Level 5": 0.2115,
+      "hfopenllm_v2/GPQA": 0.297,
       "hfopenllm_v2/MUSR": 0.4175,
-      "hfopenllm_v2/MMLU-PRO": 0.2827
+      "hfopenllm_v2/MMLU-PRO": 0.2821
     }
   },
   {
@@ -2555,17 +2555,17 @@
     "developer": "allenai",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "reward-bench/Score": 0.8369,
+      "reward-bench/Score": 0.6871,
+      "reward-bench/Chat": 0.9469,
+      "reward-bench/Chat Hard": 0.7588,
+      "reward-bench/Safety": 0.8644,
+      "reward-bench/Reasoning": 0.7715,
+      "reward-bench/Prior Sets (0.5 weight)": 0.0,
       "reward-bench/Factuality": 0.7642,
       "reward-bench/Precise IF": 0.4,
       "reward-bench/Math": 0.6175,
-      "reward-bench/Safety": 0.8703,
       "reward-bench/Focus": 0.8485,
-      "reward-bench/Ties": 0.6281,
-      "reward-bench/Chat": 0.9469,
-      "reward-bench/Chat Hard": 0.7588,
-      "reward-bench/Reasoning": 0.7715,
-      "reward-bench/Prior Sets (0.5 weight)": 0.0
+      "reward-bench/Ties": 0.6281
     }
   },
   {
@@ -6556,11 +6556,11 @@
     "developer": "amd",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "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/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/MMLU-PRO": 0.1169
     }
   },
@@ -7232,16 +7232,16 @@
       "helm_mmlu/Virology": 0.578,
       "helm_mmlu/World Religions": 0.901,
       "helm_mmlu/Mean win rate": 0.014,
-      "reward-bench/Score": 0.5744,
-      "reward-bench/Chat": 0.9469,
-      "reward-bench/Chat Hard": 0.6031,
-      "reward-bench/Safety": 0.8378,
-      "reward-bench/Reasoning": 0.7868,
+      "reward-bench/Score": 0.8008,
       "reward-bench/Factuality": 0.5389,
       "reward-bench/Precise IF": 0.3312,
       "reward-bench/Math": 0.5137,
+      "reward-bench/Safety": 0.8662,
       "reward-bench/Focus": 0.6646,
-      "reward-bench/Ties": 0.5601
+      "reward-bench/Ties": 0.5601,
+      "reward-bench/Chat": 0.9469,
+      "reward-bench/Chat Hard": 0.6031,
+      "reward-bench/Reasoning": 0.7868
     }
   },
   {
@@ -7321,7 +7321,7 @@
     "developer": "Anthropic",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "terminal-bench-2.0/terminal-bench-2.0": 35.5
+      "terminal-bench-2.0/terminal-bench-2.0": 13.9
     }
   },
   {
@@ -7446,10 +7446,10 @@
     "developer": "Anthropic",
     "evaluator_relationship": null,
     "benchmark_scores": {
+      "appworld_test_normal/appworld/test_normal": 0.66,
       "browsecompplus/browsecompplus": 0.49,
-      "appworld_test_normal/appworld/test_normal": 0.64,
-      "swe-bench/swe-bench": 0.8072,
-      "tau-bench-2_airline/tau-bench-2/airline": 0.66,
+      "swe-bench/swe-bench": 0.65,
+      "tau-bench-2_airline/tau-bench-2/airline": 0.72,
       "tau-bench-2_retail/tau-bench-2/retail": 0.85,
       "tau-bench-2_telecom/tau-bench-2/telecom": 0.84
     }
@@ -7460,7 +7460,7 @@
     "developer": "Anthropic",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "terminal-bench-2.0/terminal-bench-2.0": 38.0
+      "terminal-bench-2.0/terminal-bench-2.0": 36.9
     }
   },
   {
@@ -7469,7 +7469,7 @@
     "developer": "Anthropic",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "terminal-bench-2.0/terminal-bench-2.0": 59.1
+      "terminal-bench-2.0/terminal-bench-2.0": 51.9
     }
   },
   {
@@ -7478,7 +7478,7 @@
     "developer": "Anthropic",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "terminal-bench-2.0/terminal-bench-2.0": 66.9
+      "terminal-bench-2.0/terminal-bench-2.0": 74.7
     }
   },
   {
@@ -7552,7 +7552,7 @@
     "developer": "Anthropic",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "terminal-bench-2.0/terminal-bench-2.0": 40.1
+      "terminal-bench-2.0/terminal-bench-2.0": 42.6
     }
   },
   {
@@ -7730,12 +7730,12 @@
     "developer": "arcee-ai",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "hfopenllm_v2/IFEval": 0.5621,
-      "hfopenllm_v2/BBH": 0.5489,
-      "hfopenllm_v2/MATH Level 5": 0.2953,
-      "hfopenllm_v2/GPQA": 0.307,
-      "hfopenllm_v2/MUSR": 0.4021,
-      "hfopenllm_v2/MMLU-PRO": 0.3822
+      "hfopenllm_v2/IFEval": 0.5718,
+      "hfopenllm_v2/BBH": 0.5481,
+      "hfopenllm_v2/MATH Level 5": 0.114,
+      "hfopenllm_v2/GPQA": 0.3062,
+      "hfopenllm_v2/MUSR": 0.4008,
+      "hfopenllm_v2/MMLU-PRO": 0.3813
     }
   },
   {
@@ -8091,12 +8091,12 @@
     "developer": "AtAndDev",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "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
+      "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
     }
   },
   {
@@ -9843,12 +9843,12 @@
     "developer": "BoltMonkey",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "hfopenllm_v2/IFEval": 0.459,
-      "hfopenllm_v2/BBH": 0.5185,
-      "hfopenllm_v2/MATH Level 5": 0.0937,
-      "hfopenllm_v2/GPQA": 0.2743,
-      "hfopenllm_v2/MUSR": 0.4083,
-      "hfopenllm_v2/MMLU-PRO": 0.3631
+      "hfopenllm_v2/IFEval": 0.7999,
+      "hfopenllm_v2/BBH": 0.5152,
+      "hfopenllm_v2/MATH Level 5": 0.1193,
+      "hfopenllm_v2/GPQA": 0.281,
+      "hfopenllm_v2/MUSR": 0.4019,
+      "hfopenllm_v2/MMLU-PRO": 0.3733
     }
   },
   {
@@ -12127,12 +12127,12 @@
     "developer": "cognitivecomputations",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "hfopenllm_v2/IFEval": 0.3613,
-      "hfopenllm_v2/BBH": 0.6123,
-      "hfopenllm_v2/MATH Level 5": 0.1239,
-      "hfopenllm_v2/GPQA": 0.328,
-      "hfopenllm_v2/MUSR": 0.4112,
-      "hfopenllm_v2/MMLU-PRO": 0.4494
+      "hfopenllm_v2/IFEval": 0.4124,
+      "hfopenllm_v2/BBH": 0.6383,
+      "hfopenllm_v2/MATH Level 5": 0.182,
+      "hfopenllm_v2/GPQA": 0.3289,
+      "hfopenllm_v2/MUSR": 0.4349,
+      "hfopenllm_v2/MMLU-PRO": 0.4525
     }
   },
   {
@@ -12852,12 +12852,12 @@
     "developer": "Columbia-NLP",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "hfopenllm_v2/IFEval": 0.3278,
-      "hfopenllm_v2/BBH": 0.392,
-      "hfopenllm_v2/MATH Level 5": 0.0431,
-      "hfopenllm_v2/GPQA": 0.2492,
-      "hfopenllm_v2/MUSR": 0.412,
-      "hfopenllm_v2/MMLU-PRO": 0.1666
+      "hfopenllm_v2/IFEval": 0.3102,
+      "hfopenllm_v2/BBH": 0.3881,
+      "hfopenllm_v2/MATH Level 5": 0.0536,
+      "hfopenllm_v2/GPQA": 0.2534,
+      "hfopenllm_v2/MUSR": 0.4081,
+      "hfopenllm_v2/MMLU-PRO": 0.1665
     }
   },
   {
@@ -13400,12 +13400,12 @@
     "developer": "cpayne1303",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "hfopenllm_v2/IFEval": 0.1916,
-      "hfopenllm_v2/BBH": 0.2977,
-      "hfopenllm_v2/MATH Level 5": 0.0,
+      "hfopenllm_v2/IFEval": 0.1949,
+      "hfopenllm_v2/BBH": 0.2965,
+      "hfopenllm_v2/MATH Level 5": 0.0045,
       "hfopenllm_v2/GPQA": 0.2685,
-      "hfopenllm_v2/MUSR": 0.3872,
-      "hfopenllm_v2/MMLU-PRO": 0.1132
+      "hfopenllm_v2/MUSR": 0.3885,
+      "hfopenllm_v2/MMLU-PRO": 0.1111
     }
   },
   {
@@ -14226,12 +14226,12 @@
     "developer": "Daemontatox",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "hfopenllm_v2/IFEval": 0.777,
-      "hfopenllm_v2/BBH": 0.5187,
-      "hfopenllm_v2/MATH Level 5": 0.2198,
-      "hfopenllm_v2/GPQA": 0.2936,
-      "hfopenllm_v2/MUSR": 0.3911,
-      "hfopenllm_v2/MMLU-PRO": 0.3738
+      "hfopenllm_v2/IFEval": 0.5064,
+      "hfopenllm_v2/BBH": 0.5112,
+      "hfopenllm_v2/MATH Level 5": 0.1631,
+      "hfopenllm_v2/GPQA": 0.3163,
+      "hfopenllm_v2/MUSR": 0.3973,
+      "hfopenllm_v2/MMLU-PRO": 0.3802
     }
   },
   {
@@ -14338,12 +14338,12 @@
     "developer": "Daemontatox",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "hfopenllm_v2/IFEval": 0.4855,
-      "hfopenllm_v2/BBH": 0.6627,
-      "hfopenllm_v2/MATH Level 5": 0.4841,
-      "hfopenllm_v2/GPQA": 0.3096,
-      "hfopenllm_v2/MUSR": 0.4256,
-      "hfopenllm_v2/MMLU-PRO": 0.5542
+      "hfopenllm_v2/IFEval": 0.3745,
+      "hfopenllm_v2/BBH": 0.6668,
+      "hfopenllm_v2/MATH Level 5": 0.4758,
+      "hfopenllm_v2/GPQA": 0.3943,
+      "hfopenllm_v2/MUSR": 0.4858,
+      "hfopenllm_v2/MMLU-PRO": 0.5593
     }
   },
   {
@@ -15729,12 +15729,12 @@
     "developer": "DeepMount00",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "hfopenllm_v2/IFEval": 0.7917,
-      "hfopenllm_v2/BBH": 0.5109,
-      "hfopenllm_v2/MATH Level 5": 0.1088,
-      "hfopenllm_v2/GPQA": 0.2878,
-      "hfopenllm_v2/MUSR": 0.4136,
-      "hfopenllm_v2/MMLU-PRO": 0.3876
+      "hfopenllm_v2/IFEval": 0.5365,
+      "hfopenllm_v2/BBH": 0.517,
+      "hfopenllm_v2/MATH Level 5": 0.1707,
+      "hfopenllm_v2/GPQA": 0.3062,
+      "hfopenllm_v2/MUSR": 0.4487,
+      "hfopenllm_v2/MMLU-PRO": 0.396
     }
   },
   {
@@ -17020,12 +17020,12 @@
     "developer": "DoppelReflEx",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "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
+      "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
     }
   },
   {
@@ -20340,12 +20340,12 @@
     "developer": "EpistemeAI",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "hfopenllm_v2/IFEval": 0.7207,
-      "hfopenllm_v2/BBH": 0.461,
-      "hfopenllm_v2/MATH Level 5": 0.1314,
-      "hfopenllm_v2/GPQA": 0.2701,
-      "hfopenllm_v2/MUSR": 0.3432,
-      "hfopenllm_v2/MMLU-PRO": 0.3354
+      "hfopenllm_v2/IFEval": 0.7305,
+      "hfopenllm_v2/BBH": 0.4649,
+      "hfopenllm_v2/MATH Level 5": 0.1397,
+      "hfopenllm_v2/GPQA": 0.2659,
+      "hfopenllm_v2/MUSR": 0.3209,
+      "hfopenllm_v2/MMLU-PRO": 0.348
     }
   },
   {
@@ -21040,12 +21040,12 @@
     "developer": "Etherll",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "hfopenllm_v2/IFEval": 0.4672,
-      "hfopenllm_v2/BBH": 0.5013,
-      "hfopenllm_v2/MATH Level 5": 0.0279,
-      "hfopenllm_v2/GPQA": 0.2861,
-      "hfopenllm_v2/MUSR": 0.386,
-      "hfopenllm_v2/MMLU-PRO": 0.3482
+      "hfopenllm_v2/IFEval": 0.6106,
+      "hfopenllm_v2/BBH": 0.5347,
+      "hfopenllm_v2/MATH Level 5": 0.1548,
+      "hfopenllm_v2/GPQA": 0.3146,
+      "hfopenllm_v2/MUSR": 0.3991,
+      "hfopenllm_v2/MMLU-PRO": 0.3752
     }
   },
   {
@@ -21500,12 +21500,12 @@
     "developer": "fblgit",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "hfopenllm_v2/IFEval": 0.5181,
-      "hfopenllm_v2/BBH": 0.7033,
-      "hfopenllm_v2/MATH Level 5": 0.4947,
-      "hfopenllm_v2/GPQA": 0.3826,
-      "hfopenllm_v2/MUSR": 0.5008,
-      "hfopenllm_v2/MMLU-PRO": 0.5915
+      "hfopenllm_v2/IFEval": 0.4503,
+      "hfopenllm_v2/BBH": 0.7035,
+      "hfopenllm_v2/MATH Level 5": 0.3943,
+      "hfopenllm_v2/GPQA": 0.401,
+      "hfopenllm_v2/MUSR": 0.5021,
+      "hfopenllm_v2/MMLU-PRO": 0.5911
     }
   },
   {
@@ -23289,12 +23289,12 @@
     "developer": "Goekdeniz-Guelmez",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "hfopenllm_v2/IFEval": 0.7598,
-      "hfopenllm_v2/BBH": 0.5107,
-      "hfopenllm_v2/MATH Level 5": 0.4237,
-      "hfopenllm_v2/GPQA": 0.2768,
-      "hfopenllm_v2/MUSR": 0.4539,
-      "hfopenllm_v2/MMLU-PRO": 0.4012
+      "hfopenllm_v2/IFEval": 0.7628,
+      "hfopenllm_v2/BBH": 0.5098,
+      "hfopenllm_v2/MATH Level 5": 0.0,
+      "hfopenllm_v2/GPQA": 0.2802,
+      "hfopenllm_v2/MUSR": 0.4579,
+      "hfopenllm_v2/MMLU-PRO": 0.4033
     }
   },
   {
@@ -23519,6 +23519,7 @@
     "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,
@@ -23526,7 +23527,6 @@
       "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
     }
@@ -24103,7 +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": 17.1
+      "terminal-bench-2.0/terminal-bench-2.0": 15.4
     }
   },
   {
@@ -24203,7 +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": 19.6
+      "terminal-bench-2.0/terminal-bench-2.0": 16.4
     }
   },
   {
@@ -24259,7 +24259,7 @@
     "developer": "Google",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "appworld_test_normal/appworld/test_normal": 0.13,
+      "appworld_test_normal/appworld/test_normal": 0.36,
       "browsecompplus/browsecompplus": 0.48,
       "global-mmlu-lite/Global MMLU Lite": 0.9453,
       "global-mmlu-lite/Culturally Sensitive": 0.9397,
@@ -24281,9 +24281,9 @@
       "global-mmlu-lite/Chinese": 0.9475,
       "global-mmlu-lite/Burmese": 0.9425,
       "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": 0.6852
+      "tau-bench-2_airline/tau-bench-2/airline": 0.68,
+      "tau-bench-2_retail/tau-bench-2/retail": 0.82,
+      "tau-bench-2_telecom/tau-bench-2/telecom": 0.73
     }
   },
   {
@@ -24292,7 +24292,7 @@
     "developer": "Google",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "terminal-bench-2.0/terminal-bench-2.0": 78.4
+      "terminal-bench-2.0/terminal-bench-2.0": 74.8
     }
   },
   {
@@ -25558,12 +25558,12 @@
     "developer": "Gunulhona",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "hfopenllm_v2/IFEval": 0.4441,
-      "hfopenllm_v2/BBH": 0.4863,
+      "hfopenllm_v2/IFEval": 0.288,
+      "hfopenllm_v2/BBH": 0.5154,
       "hfopenllm_v2/MATH Level 5": 0.0,
-      "hfopenllm_v2/GPQA": 0.307,
-      "hfopenllm_v2/MUSR": 0.3986,
-      "hfopenllm_v2/MMLU-PRO": 0.3098
+      "hfopenllm_v2/GPQA": 0.3247,
+      "hfopenllm_v2/MUSR": 0.408,
+      "hfopenllm_v2/MMLU-PRO": 0.3817
     }
   },
   {
@@ -25894,17 +25894,17 @@
     "developer": "hendrydong",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "reward-bench/Score": 0.7847,
+      "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/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/Chat": 0.9832,
-      "reward-bench/Chat Hard": 0.5789,
-      "reward-bench/Reasoning": 0.7434,
-      "reward-bench/Prior Sets (0.5 weight)": 0.7508
+      "reward-bench/Ties": 0.5988
     }
   },
   {
@@ -26814,12 +26814,12 @@
     "developer": "HuggingFaceTB",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "hfopenllm_v2/IFEval": 0.3842,
-      "hfopenllm_v2/BBH": 0.3144,
-      "hfopenllm_v2/MATH Level 5": 0.0151,
-      "hfopenllm_v2/GPQA": 0.255,
-      "hfopenllm_v2/MUSR": 0.3461,
-      "hfopenllm_v2/MMLU-PRO": 0.1117
+      "hfopenllm_v2/IFEval": 0.083,
+      "hfopenllm_v2/BBH": 0.3053,
+      "hfopenllm_v2/MATH Level 5": 0.0083,
+      "hfopenllm_v2/GPQA": 0.2651,
+      "hfopenllm_v2/MUSR": 0.3423,
+      "hfopenllm_v2/MMLU-PRO": 0.1126
     }
   },
   {
@@ -28507,16 +28507,16 @@
     "developer": "infly",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "reward-bench/Score": 0.7648,
-      "reward-bench/Chat": 0.9665,
-      "reward-bench/Chat Hard": 0.9101,
-      "reward-bench/Safety": 0.9644,
-      "reward-bench/Reasoning": 0.9912,
+      "reward-bench/Score": 0.9511,
       "reward-bench/Factuality": 0.7411,
       "reward-bench/Precise IF": 0.4188,
       "reward-bench/Math": 0.6995,
+      "reward-bench/Safety": 0.9365,
       "reward-bench/Focus": 0.903,
-      "reward-bench/Ties": 0.8622
+      "reward-bench/Ties": 0.8622,
+      "reward-bench/Chat": 0.9665,
+      "reward-bench/Chat Hard": 0.9101,
+      "reward-bench/Reasoning": 0.9912
     }
   },
   {
@@ -28651,16 +28651,16 @@
     "developer": "internlm",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "reward-bench/Score": 0.3902,
-      "reward-bench/Chat": 0.9358,
-      "reward-bench/Chat Hard": 0.6623,
-      "reward-bench/Safety": 0.4711,
-      "reward-bench/Reasoning": 0.8724,
+      "reward-bench/Score": 0.8217,
       "reward-bench/Factuality": 0.2758,
       "reward-bench/Precise IF": 0.3625,
       "reward-bench/Math": 0.4426,
+      "reward-bench/Safety": 0.8162,
       "reward-bench/Focus": 0.596,
-      "reward-bench/Ties": 0.1934
+      "reward-bench/Ties": 0.1934,
+      "reward-bench/Chat": 0.9358,
+      "reward-bench/Chat Hard": 0.6623,
+      "reward-bench/Reasoning": 0.8724
     }
   },
   {
@@ -28669,16 +28669,16 @@
     "developer": "internlm",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "reward-bench/Score": 0.9016,
+      "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/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/Chat": 0.9888,
-      "reward-bench/Chat Hard": 0.7654,
-      "reward-bench/Reasoning": 0.9576
+      "reward-bench/Ties": 0.5483
     }
   },
   {
@@ -28985,12 +28985,12 @@
     "developer": "Isaak-Carter",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "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
+      "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
     }
   },
   {
@@ -30623,12 +30623,12 @@
     "developer": "jaspionjader",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "hfopenllm_v2/IFEval": 0.4345,
-      "hfopenllm_v2/BBH": 0.5419,
-      "hfopenllm_v2/MATH Level 5": 0.1292,
-      "hfopenllm_v2/GPQA": 0.3087,
+      "hfopenllm_v2/IFEval": 0.4418,
+      "hfopenllm_v2/BBH": 0.5406,
+      "hfopenllm_v2/MATH Level 5": 0.1352,
+      "hfopenllm_v2/GPQA": 0.3062,
       "hfopenllm_v2/MUSR": 0.4277,
-      "hfopenllm_v2/MMLU-PRO": 0.3854
+      "hfopenllm_v2/MMLU-PRO": 0.386
     }
   },
   {
@@ -35901,12 +35901,12 @@
     "developer": "kavonalds",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "hfopenllm_v2/IFEval": 0.2701,
-      "hfopenllm_v2/BBH": 0.5566,
+      "hfopenllm_v2/IFEval": 0.3283,
+      "hfopenllm_v2/BBH": 0.6651,
       "hfopenllm_v2/MATH Level 5": 0.068,
-      "hfopenllm_v2/GPQA": 0.2802,
-      "hfopenllm_v2/MUSR": 0.3682,
-      "hfopenllm_v2/MMLU-PRO": 0.1449
+      "hfopenllm_v2/GPQA": 0.2609,
+      "hfopenllm_v2/MUSR": 0.3393,
+      "hfopenllm_v2/MMLU-PRO": 0.1314
     }
   },
   {
@@ -39569,16 +39569,16 @@
     "developer": "LxzGordon",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "reward-bench/Score": 0.9294,
+      "reward-bench/Score": 0.7394,
+      "reward-bench/Chat": 0.9553,
+      "reward-bench/Chat Hard": 0.8816,
+      "reward-bench/Safety": 0.9178,
+      "reward-bench/Reasoning": 0.9698,
       "reward-bench/Factuality": 0.6884,
       "reward-bench/Precise IF": 0.45,
       "reward-bench/Math": 0.6393,
-      "reward-bench/Safety": 0.9108,
       "reward-bench/Focus": 0.9758,
-      "reward-bench/Ties": 0.7653,
-      "reward-bench/Chat": 0.9553,
-      "reward-bench/Chat Hard": 0.8816,
-      "reward-bench/Reasoning": 0.9698
+      "reward-bench/Ties": 0.7653
     }
   },
   {
@@ -39741,12 +39741,12 @@
     "developer": "Magpie-Align",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "hfopenllm_v2/IFEval": 0.4118,
-      "hfopenllm_v2/BBH": 0.4811,
-      "hfopenllm_v2/MATH Level 5": 0.034,
-      "hfopenllm_v2/GPQA": 0.2752,
-      "hfopenllm_v2/MUSR": 0.3047,
-      "hfopenllm_v2/MMLU-PRO": 0.3006
+      "hfopenllm_v2/IFEval": 0.4027,
+      "hfopenllm_v2/BBH": 0.4789,
+      "hfopenllm_v2/MATH Level 5": 0.0461,
+      "hfopenllm_v2/GPQA": 0.2768,
+      "hfopenllm_v2/MUSR": 0.3087,
+      "hfopenllm_v2/MMLU-PRO": 0.3001
     }
   },
   {
@@ -42056,12 +42056,12 @@
     "developer": "meta-llama",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "hfopenllm_v2/IFEval": 0.4782,
-      "hfopenllm_v2/BBH": 0.491,
-      "hfopenllm_v2/MATH Level 5": 0.0914,
-      "hfopenllm_v2/GPQA": 0.2928,
-      "hfopenllm_v2/MUSR": 0.3805,
-      "hfopenllm_v2/MMLU-PRO": 0.3591,
+      "hfopenllm_v2/IFEval": 0.7408,
+      "hfopenllm_v2/BBH": 0.4989,
+      "hfopenllm_v2/MATH Level 5": 0.0869,
+      "hfopenllm_v2/GPQA": 0.2592,
+      "hfopenllm_v2/MUSR": 0.3568,
+      "hfopenllm_v2/MMLU-PRO": 0.3664,
       "reward-bench/Score": 0.645,
       "reward-bench/Chat": 0.8547,
       "reward-bench/Chat Hard": 0.4156,
@@ -44247,12 +44247,12 @@
     "developer": "mistralai",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "hfopenllm_v2/IFEval": 0.6283,
-      "hfopenllm_v2/BBH": 0.583,
-      "hfopenllm_v2/MATH Level 5": 0.2039,
-      "hfopenllm_v2/GPQA": 0.3331,
-      "hfopenllm_v2/MUSR": 0.4063,
-      "hfopenllm_v2/MMLU-PRO": 0.4099
+      "hfopenllm_v2/IFEval": 0.667,
+      "hfopenllm_v2/BBH": 0.5213,
+      "hfopenllm_v2/MATH Level 5": 0.1435,
+      "hfopenllm_v2/GPQA": 0.3238,
+      "hfopenllm_v2/MUSR": 0.3632,
+      "hfopenllm_v2/MMLU-PRO": 0.396
     }
   },
   {
@@ -44758,12 +44758,12 @@
     "developer": "mlabonne",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "hfopenllm_v2/IFEval": 0.7561,
-      "hfopenllm_v2/BBH": 0.5111,
-      "hfopenllm_v2/MATH Level 5": 0.0906,
-      "hfopenllm_v2/GPQA": 0.3062,
-      "hfopenllm_v2/MUSR": 0.4019,
-      "hfopenllm_v2/MMLU-PRO": 0.3841
+      "hfopenllm_v2/IFEval": 0.4162,
+      "hfopenllm_v2/BBH": 0.5124,
+      "hfopenllm_v2/MATH Level 5": 0.0853,
+      "hfopenllm_v2/GPQA": 0.3029,
+      "hfopenllm_v2/MUSR": 0.415,
+      "hfopenllm_v2/MMLU-PRO": 0.3802
     }
   },
   {
@@ -44996,7 +44996,7 @@
     "developer": "Moonshot AI",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "terminal-bench-2.0/terminal-bench-2.0": 26.7
+      "terminal-bench-2.0/terminal-bench-2.0": 27.8
     }
   },
   {
@@ -45317,7 +45317,7 @@
     "developer": "Multiple",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "terminal-bench-2.0/terminal-bench-2.0": 58.4
+      "terminal-bench-2.0/terminal-bench-2.0": 72.4
     }
   },
   {
@@ -46416,16 +46416,16 @@
     "developer": "NCSOFT",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "reward-bench/Score": 0.8942,
+      "reward-bench/Score": 0.648,
+      "reward-bench/Chat": 0.9721,
+      "reward-bench/Chat Hard": 0.818,
+      "reward-bench/Safety": 0.7222,
+      "reward-bench/Reasoning": 0.9192,
       "reward-bench/Factuality": 0.6084,
       "reward-bench/Precise IF": 0.4,
       "reward-bench/Math": 0.5191,
-      "reward-bench/Safety": 0.8676,
       "reward-bench/Focus": 0.9596,
-      "reward-bench/Ties": 0.6786,
-      "reward-bench/Chat": 0.9721,
-      "reward-bench/Chat Hard": 0.818,
-      "reward-bench/Reasoning": 0.9192
+      "reward-bench/Ties": 0.6786
     }
   },
   {
@@ -48142,17 +48142,17 @@
     "developer": "Nexusflow",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "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/Score": 0.8133,
       "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/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
     }
   },
   {
@@ -50393,12 +50393,12 @@
     "developer": "ontocord",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "hfopenllm_v2/IFEval": 0.1162,
-      "hfopenllm_v2/BBH": 0.3184,
-      "hfopenllm_v2/MATH Level 5": 0.0076,
-      "hfopenllm_v2/GPQA": 0.2634,
-      "hfopenllm_v2/MUSR": 0.3447,
-      "hfopenllm_v2/MMLU-PRO": 0.1124
+      "hfopenllm_v2/IFEval": 0.1128,
+      "hfopenllm_v2/BBH": 0.3171,
+      "hfopenllm_v2/MATH Level 5": 0.0113,
+      "hfopenllm_v2/GPQA": 0.2685,
+      "hfopenllm_v2/MUSR": 0.346,
+      "hfopenllm_v2/MMLU-PRO": 0.1129
     }
   },
   {
@@ -51011,16 +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,
-      "ace/Overall Score": 0.515,
-      "ace/Food Score": 0.65,
-      "ace/Gaming Score": 0.578
+      "apex-agents/Corporate Lawyer Mean Score": 0.443
     }
   },
   {
@@ -51620,16 +51620,16 @@
       "helm_mmlu/Virology": 0.578,
       "helm_mmlu/World Religions": 0.883,
       "helm_mmlu/Mean win rate": 0.52,
-      "reward-bench/Score": 0.8673,
+      "reward-bench/Score": 0.6493,
+      "reward-bench/Chat": 0.9609,
+      "reward-bench/Chat Hard": 0.761,
+      "reward-bench/Safety": 0.8619,
+      "reward-bench/Reasoning": 0.8661,
       "reward-bench/Factuality": 0.5684,
       "reward-bench/Precise IF": 0.3312,
       "reward-bench/Math": 0.623,
-      "reward-bench/Safety": 0.8811,
       "reward-bench/Focus": 0.7293,
-      "reward-bench/Ties": 0.7819,
-      "reward-bench/Chat": 0.9609,
-      "reward-bench/Chat Hard": 0.761,
-      "reward-bench/Reasoning": 0.8661
+      "reward-bench/Ties": 0.7819
     }
   },
   {
@@ -51707,16 +51707,16 @@
       "helm_mmlu/Virology": 0.536,
       "helm_mmlu/World Religions": 0.86,
       "helm_mmlu/Mean win rate": 0.774,
-      "reward-bench/Score": 0.8007,
+      "reward-bench/Score": 0.5796,
+      "reward-bench/Chat": 0.9497,
+      "reward-bench/Chat Hard": 0.6075,
+      "reward-bench/Safety": 0.7667,
+      "reward-bench/Reasoning": 0.8374,
       "reward-bench/Factuality": 0.4105,
       "reward-bench/Precise IF": 0.3438,
       "reward-bench/Math": 0.5191,
-      "reward-bench/Safety": 0.8081,
       "reward-bench/Focus": 0.7414,
-      "reward-bench/Ties": 0.6962,
-      "reward-bench/Chat": 0.9497,
-      "reward-bench/Chat Hard": 0.6075,
-      "reward-bench/Reasoning": 0.8374
+      "reward-bench/Ties": 0.6962
     }
   },
   {
@@ -51770,7 +51770,7 @@
     "developer": "OpenAI",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "terminal-bench-2.0/terminal-bench-2.0": 41.3
+      "terminal-bench-2.0/terminal-bench-2.0": 43.4
     }
   },
   {
@@ -51779,7 +51779,7 @@
     "developer": "OpenAI",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "terminal-bench-2.0/terminal-bench-2.0": 22.2
+      "terminal-bench-2.0/terminal-bench-2.0": 34.8
     }
   },
   {
@@ -51802,7 +51802,7 @@
     "developer": "OpenAI",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "terminal-bench-2.0/terminal-bench-2.0": 7.9
+      "terminal-bench-2.0/terminal-bench-2.0": 7.0
     }
   },
   {
@@ -51834,7 +51834,7 @@
     "developer": "OpenAI",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "terminal-bench-2.0/terminal-bench-2.0": 36.9
+      "terminal-bench-2.0/terminal-bench-2.0": 53.5
     }
   },
   {
@@ -51861,7 +51861,7 @@
     "developer": "OpenAI",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "terminal-bench-2.0/terminal-bench-2.0": 54.0
+      "terminal-bench-2.0/terminal-bench-2.0": 60.7
     }
   },
   {
@@ -51870,15 +51870,15 @@
     "developer": "OpenAI",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "appworld_test_normal/appworld/test_normal": 0.0,
-      "browsecompplus/browsecompplus": 0.48,
+      "appworld_test_normal/appworld/test_normal": 0.071,
+      "browsecompplus/browsecompplus": 0.46,
       "livecodebenchpro/Hard Problems": 0.1594,
       "livecodebenchpro/Medium Problems": 0.5211,
       "livecodebenchpro/Easy Problems": 0.9014,
-      "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
+      "swe-bench/swe-bench": 0.57,
+      "tau-bench-2_airline/tau-bench-2/airline": 0.6,
+      "tau-bench-2_retail/tau-bench-2/retail": 0.73,
+      "tau-bench-2_telecom/tau-bench-2/telecom": 0.55
     }
   },
   {
@@ -51896,7 +51896,7 @@
     "developer": "OpenAI",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "terminal-bench-2.0/terminal-bench-2.0": 77.3
+      "terminal-bench-2.0/terminal-bench-2.0": 74.6
     }
   },
   {
@@ -51978,7 +51978,7 @@
       "livecodebenchpro/Hard Problems": 0.0,
       "livecodebenchpro/Medium Problems": 0.056338028169014086,
       "livecodebenchpro/Easy Problems": 0.5070422535211268,
-      "terminal-bench-2.0/terminal-bench-2.0": 3.4
+      "terminal-bench-2.0/terminal-bench-2.0": 3.1
     }
   },
   {
@@ -52279,17 +52279,17 @@
     "developer": "OpenAssistant",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "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/Score": 0.6126,
       "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/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
     }
   },
   {
@@ -52312,17 +52312,17 @@
     "developer": "openbmb",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "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/Score": 0.8159,
       "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/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
     }
   },
   {
@@ -53830,17 +53830,17 @@
     "developer": "PKU-Alignment",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "reward-bench/Score": 0.3332,
-      "reward-bench/Chat": 0.6173,
-      "reward-bench/Chat Hard": 0.4232,
-      "reward-bench/Safety": 0.7589,
-      "reward-bench/Reasoning": 0.5482,
-      "reward-bench/Prior Sets (0.5 weight)": 0.57,
+      "reward-bench/Score": 0.5798,
       "reward-bench/Factuality": 0.3263,
       "reward-bench/Precise IF": 0.2313,
       "reward-bench/Math": 0.3989,
+      "reward-bench/Safety": 0.7351,
       "reward-bench/Focus": 0.2939,
-      "reward-bench/Ties": -0.01
+      "reward-bench/Ties": -0.01,
+      "reward-bench/Chat": 0.6173,
+      "reward-bench/Chat Hard": 0.4232,
+      "reward-bench/Reasoning": 0.5482,
+      "reward-bench/Prior Sets (0.5 weight)": 0.57
     }
   },
   {
@@ -54983,12 +54983,12 @@
     "developer": "prithivMLmods",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "hfopenllm_v2/IFEval": 0.6052,
-      "hfopenllm_v2/BBH": 0.6317,
-      "hfopenllm_v2/MATH Level 5": 0.4789,
-      "hfopenllm_v2/GPQA": 0.3742,
-      "hfopenllm_v2/MUSR": 0.486,
-      "hfopenllm_v2/MMLU-PRO": 0.5302
+      "hfopenllm_v2/IFEval": 0.6064,
+      "hfopenllm_v2/BBH": 0.6296,
+      "hfopenllm_v2/MATH Level 5": 0.3708,
+      "hfopenllm_v2/GPQA": 0.3733,
+      "hfopenllm_v2/MUSR": 0.4873,
+      "hfopenllm_v2/MMLU-PRO": 0.5307
     }
   },
   {
@@ -56605,12 +56605,12 @@
     "developer": "qingy2019",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "hfopenllm_v2/IFEval": 0.6005,
-      "hfopenllm_v2/BBH": 0.6356,
-      "hfopenllm_v2/MATH Level 5": 0.2764,
-      "hfopenllm_v2/GPQA": 0.3691,
+      "hfopenllm_v2/IFEval": 0.6066,
+      "hfopenllm_v2/BBH": 0.635,
+      "hfopenllm_v2/MATH Level 5": 0.3716,
+      "hfopenllm_v2/GPQA": 0.3725,
       "hfopenllm_v2/MUSR": 0.4757,
-      "hfopenllm_v2/MMLU-PRO": 0.5339
+      "hfopenllm_v2/MMLU-PRO": 0.5331
     }
   },
   {
@@ -59400,17 +59400,17 @@
     "developer": "Ray2333",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "reward-bench/Score": 0.8464,
+      "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/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/Chat": 0.9832,
-      "reward-bench/Chat Hard": 0.6842,
-      "reward-bench/Reasoning": 0.9133,
-      "reward-bench/Prior Sets (0.5 weight)": 0.7209
+      "reward-bench/Ties": 0.5743
     }
   },
   {
@@ -59419,16 +59419,16 @@
     "developer": "Ray2333",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "reward-bench/Score": 0.9154,
+      "reward-bench/Score": 0.6766,
+      "reward-bench/Chat": 0.9553,
+      "reward-bench/Chat Hard": 0.8618,
+      "reward-bench/Safety": 0.9222,
+      "reward-bench/Reasoning": 0.9362,
       "reward-bench/Factuality": 0.6274,
       "reward-bench/Precise IF": 0.35,
       "reward-bench/Math": 0.5847,
-      "reward-bench/Safety": 0.9081,
       "reward-bench/Focus": 0.8929,
-      "reward-bench/Ties": 0.6824,
-      "reward-bench/Chat": 0.9553,
-      "reward-bench/Chat Hard": 0.8618,
-      "reward-bench/Reasoning": 0.9362
+      "reward-bench/Ties": 0.6824
     }
   },
   {
@@ -59437,17 +59437,17 @@
     "developer": "Ray2333",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "reward-bench/Score": 0.8542,
+      "reward-bench/Score": 0.6089,
+      "reward-bench/Chat": 0.986,
+      "reward-bench/Chat Hard": 0.6776,
+      "reward-bench/Safety": 0.7867,
+      "reward-bench/Reasoning": 0.9229,
+      "reward-bench/Prior Sets (0.5 weight)": 0.7309,
       "reward-bench/Factuality": 0.6189,
       "reward-bench/Precise IF": 0.3875,
       "reward-bench/Math": 0.5792,
-      "reward-bench/Safety": 0.8919,
       "reward-bench/Focus": 0.6828,
-      "reward-bench/Ties": 0.5981,
-      "reward-bench/Chat": 0.986,
-      "reward-bench/Chat Hard": 0.6776,
-      "reward-bench/Reasoning": 0.9229,
-      "reward-bench/Prior Sets (0.5 weight)": 0.7309
+      "reward-bench/Ties": 0.5981
     }
   },
   {
@@ -59511,12 +59511,12 @@
     "developer": "recoilme",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "hfopenllm_v2/IFEval": 0.2854,
-      "hfopenllm_v2/BBH": 0.5984,
-      "hfopenllm_v2/MATH Level 5": 0.1005,
-      "hfopenllm_v2/GPQA": 0.3297,
-      "hfopenllm_v2/MUSR": 0.4607,
-      "hfopenllm_v2/MMLU-PRO": 0.4162
+      "hfopenllm_v2/IFEval": 0.7649,
+      "hfopenllm_v2/BBH": 0.5974,
+      "hfopenllm_v2/MATH Level 5": 0.0174,
+      "hfopenllm_v2/GPQA": 0.3305,
+      "hfopenllm_v2/MUSR": 0.4245,
+      "hfopenllm_v2/MMLU-PRO": 0.4207
     }
   },
   {
@@ -59539,12 +59539,12 @@
     "developer": "recoilme",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "hfopenllm_v2/IFEval": 0.2747,
-      "hfopenllm_v2/BBH": 0.6031,
-      "hfopenllm_v2/MATH Level 5": 0.0831,
-      "hfopenllm_v2/GPQA": 0.3305,
-      "hfopenllm_v2/MUSR": 0.4686,
-      "hfopenllm_v2/MMLU-PRO": 0.4122
+      "hfopenllm_v2/IFEval": 0.7592,
+      "hfopenllm_v2/BBH": 0.6026,
+      "hfopenllm_v2/MATH Level 5": 0.0529,
+      "hfopenllm_v2/GPQA": 0.3289,
+      "hfopenllm_v2/MUSR": 0.4099,
+      "hfopenllm_v2/MMLU-PRO": 0.4163
     }
   },
   {
@@ -59553,12 +59553,12 @@
     "developer": "recoilme",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "hfopenllm_v2/IFEval": 0.7439,
-      "hfopenllm_v2/BBH": 0.5993,
-      "hfopenllm_v2/MATH Level 5": 0.0876,
-      "hfopenllm_v2/GPQA": 0.3238,
-      "hfopenllm_v2/MUSR": 0.4204,
-      "hfopenllm_v2/MMLU-PRO": 0.4072
+      "hfopenllm_v2/IFEval": 0.5761,
+      "hfopenllm_v2/BBH": 0.602,
+      "hfopenllm_v2/MATH Level 5": 0.1888,
+      "hfopenllm_v2/GPQA": 0.3372,
+      "hfopenllm_v2/MUSR": 0.4632,
+      "hfopenllm_v2/MMLU-PRO": 0.4039
     }
   },
   {
@@ -59721,12 +59721,12 @@
     "developer": "Replete-AI",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "hfopenllm_v2/IFEval": 0.0932,
-      "hfopenllm_v2/BBH": 0.2977,
+      "hfopenllm_v2/IFEval": 0.0905,
+      "hfopenllm_v2/BBH": 0.2985,
       "hfopenllm_v2/MATH Level 5": 0.0,
-      "hfopenllm_v2/GPQA": 0.2475,
-      "hfopenllm_v2/MUSR": 0.3941,
-      "hfopenllm_v2/MMLU-PRO": 0.1157
+      "hfopenllm_v2/GPQA": 0.2534,
+      "hfopenllm_v2/MUSR": 0.3848,
+      "hfopenllm_v2/MMLU-PRO": 0.1158
     }
   },
   {
@@ -59861,12 +59861,12 @@
     "developer": "riaz",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "hfopenllm_v2/IFEval": 0.4373,
-      "hfopenllm_v2/BBH": 0.4586,
-      "hfopenllm_v2/MATH Level 5": 0.0514,
-      "hfopenllm_v2/GPQA": 0.2752,
-      "hfopenllm_v2/MUSR": 0.3763,
-      "hfopenllm_v2/MMLU-PRO": 0.2964
+      "hfopenllm_v2/IFEval": 0.4137,
+      "hfopenllm_v2/BBH": 0.4565,
+      "hfopenllm_v2/MATH Level 5": 0.0453,
+      "hfopenllm_v2/GPQA": 0.276,
+      "hfopenllm_v2/MUSR": 0.3776,
+      "hfopenllm_v2/MMLU-PRO": 0.2978
     }
   },
   {
@@ -60158,12 +60158,12 @@
     "developer": "rombodawg",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "hfopenllm_v2/IFEval": 0.2566,
-      "hfopenllm_v2/BBH": 0.39,
-      "hfopenllm_v2/MATH Level 5": 0.1208,
-      "hfopenllm_v2/GPQA": 0.2626,
+      "hfopenllm_v2/IFEval": 0.2595,
+      "hfopenllm_v2/BBH": 0.3884,
+      "hfopenllm_v2/MATH Level 5": 0.0914,
+      "hfopenllm_v2/GPQA": 0.2743,
       "hfopenllm_v2/MUSR": 0.3991,
-      "hfopenllm_v2/MMLU-PRO": 0.2741
+      "hfopenllm_v2/MMLU-PRO": 0.2719
     }
   },
   {
@@ -61835,12 +61835,12 @@
     "developer": "Sao10K",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "hfopenllm_v2/IFEval": 0.7281,
-      "hfopenllm_v2/BBH": 0.6503,
-      "hfopenllm_v2/MATH Level 5": 0.2243,
+      "hfopenllm_v2/IFEval": 0.7384,
+      "hfopenllm_v2/BBH": 0.6471,
+      "hfopenllm_v2/MATH Level 5": 0.2137,
       "hfopenllm_v2/GPQA": 0.3314,
-      "hfopenllm_v2/MUSR": 0.4196,
-      "hfopenllm_v2/MMLU-PRO": 0.5096
+      "hfopenllm_v2/MUSR": 0.4209,
+      "hfopenllm_v2/MMLU-PRO": 0.5104
     }
   },
   {
@@ -62581,16 +62581,16 @@
     "developer": "ShikaiChen",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "reward-bench/Score": 0.9499,
+      "reward-bench/Score": 0.7249,
+      "reward-bench/Chat": 0.9637,
+      "reward-bench/Chat Hard": 0.9079,
+      "reward-bench/Safety": 0.9222,
+      "reward-bench/Reasoning": 0.9903,
       "reward-bench/Factuality": 0.7558,
       "reward-bench/Precise IF": 0.35,
       "reward-bench/Math": 0.6448,
-      "reward-bench/Safety": 0.9378,
       "reward-bench/Focus": 0.9131,
-      "reward-bench/Ties": 0.7633,
-      "reward-bench/Chat": 0.9637,
-      "reward-bench/Chat Hard": 0.9079,
-      "reward-bench/Reasoning": 0.9903
+      "reward-bench/Ties": 0.7633
     }
   },
   {
@@ -63307,16 +63307,16 @@
       "hfopenllm_v2/GPQA": 0.344,
       "hfopenllm_v2/MUSR": 0.4231,
       "hfopenllm_v2/MMLU-PRO": 0.4103,
-      "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/Score": 0.9426,
       "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/Ties": 0.8182,
+      "reward-bench/Chat": 0.9609,
+      "reward-bench/Chat Hard": 0.8991,
+      "reward-bench/Reasoning": 0.9807
     }
   },
   {
@@ -66784,12 +66784,12 @@
     "developer": "tanliboy",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "hfopenllm_v2/IFEval": 0.4501,
-      "hfopenllm_v2/BBH": 0.5472,
-      "hfopenllm_v2/MATH Level 5": 0.0944,
-      "hfopenllm_v2/GPQA": 0.3138,
-      "hfopenllm_v2/MUSR": 0.4017,
-      "hfopenllm_v2/MMLU-PRO": 0.3792
+      "hfopenllm_v2/IFEval": 0.1829,
+      "hfopenllm_v2/BBH": 0.5488,
+      "hfopenllm_v2/MATH Level 5": 0.0,
+      "hfopenllm_v2/GPQA": 0.3104,
+      "hfopenllm_v2/MUSR": 0.4056,
+      "hfopenllm_v2/MMLU-PRO": 0.3805
     }
   },
   {
@@ -71056,12 +71056,12 @@
     "developer": "ValiantLabs",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "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
+      "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
     }
   },
   {
@@ -71686,17 +71686,17 @@
     "developer": "weqweasdas",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "reward-bench/Score": 0.2498,
-      "reward-bench/Chat": 0.8184,
-      "reward-bench/Chat Hard": 0.3728,
-      "reward-bench/Safety": 0.24,
-      "reward-bench/Reasoning": 0.3281,
-      "reward-bench/Prior Sets (0.5 weight)": 0.6564,
+      "reward-bench/Score": 0.5027,
       "reward-bench/Factuality": 0.3642,
       "reward-bench/Precise IF": 0.275,
       "reward-bench/Math": 0.3497,
+      "reward-bench/Safety": 0.4149,
       "reward-bench/Focus": 0.2384,
-      "reward-bench/Ties": 0.0315
+      "reward-bench/Ties": 0.0315,
+      "reward-bench/Chat": 0.8184,
+      "reward-bench/Chat Hard": 0.3728,
+      "reward-bench/Reasoning": 0.3281,
+      "reward-bench/Prior Sets (0.5 weight)": 0.6564
     }
   },
   {
@@ -71724,17 +71724,17 @@
     "developer": "weqweasdas",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "reward-bench/Score": 0.4826,
-      "reward-bench/Chat": 0.9693,
-      "reward-bench/Chat Hard": 0.4978,
-      "reward-bench/Safety": 0.4822,
-      "reward-bench/Reasoning": 0.7362,
-      "reward-bench/Prior Sets (0.5 weight)": 0.7069,
+      "reward-bench/Score": 0.6967,
       "reward-bench/Factuality": 0.4926,
       "reward-bench/Precise IF": 0.3937,
       "reward-bench/Math": 0.6066,
+      "reward-bench/Safety": 0.5784,
       "reward-bench/Focus": 0.497,
-      "reward-bench/Ties": 0.4232
+      "reward-bench/Ties": 0.4232,
+      "reward-bench/Chat": 0.9693,
+      "reward-bench/Chat Hard": 0.4978,
+      "reward-bench/Reasoning": 0.7362,
+      "reward-bench/Prior Sets (0.5 weight)": 0.7069
     }
   },
   {
@@ -72436,7 +72436,7 @@
     "developer": "xAI",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "terminal-bench-2.0/terminal-bench-2.0": 14.2
+      "terminal-bench-2.0/terminal-bench-2.0": 25.8
     }
   },
   {
@@ -73047,12 +73047,12 @@
     "developer": "yam-peleg",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "hfopenllm_v2/IFEval": 0.1856,
-      "hfopenllm_v2/BBH": 0.4149,
-      "hfopenllm_v2/MATH Level 5": 0.0234,
-      "hfopenllm_v2/GPQA": 0.276,
-      "hfopenllm_v2/MUSR": 0.3765,
-      "hfopenllm_v2/MMLU-PRO": 0.2573
+      "hfopenllm_v2/IFEval": 0.177,
+      "hfopenllm_v2/BBH": 0.3411,
+      "hfopenllm_v2/MATH Level 5": 0.031,
+      "hfopenllm_v2/GPQA": 0.2534,
+      "hfopenllm_v2/MUSR": 0.374,
+      "hfopenllm_v2/MMLU-PRO": 0.2529
     }
   },
   {
diff --git a/data/models/adriszmar_qaimath-qwen2.5-7b-ties.json b/data/models/adriszmar_qaimath-qwen2.5-7b-ties.json
index 776a7c662b5afb276bf059bb90896cee5cd968ec..a8a69697e53329e56da6b7741229b84b4f2eeb85 100644
--- a/data/models/adriszmar_qaimath-qwen2.5-7b-ties.json
+++ b/data/models/adriszmar_qaimath-qwen2.5-7b-ties.json
@@ -5,7 +5,7 @@
     "developer": "adriszmar",
     "inference_platform": "unknown",
     "additional_details": {
-      "precision": "bfloat16",
+      "precision": "float16",
       "architecture": "Qwen2ForCausalLM",
       "params_billions": "7.616"
     }
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1685
+            "score": 0.1746
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3124
+            "score": 0.3126
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0015
+            "score": 0.0
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2492
+            "score": 0.245
           }
         },
         {
@@ -116,7 +116,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3963
+            "score": 0.4096
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1066
+            "score": 0.1087
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1746
+            "score": 0.1685
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3126
+            "score": 0.3124
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0
+            "score": 0.0015
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.245
+            "score": 0.2492
           }
         },
         {
@@ -246,7 +246,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4096
+            "score": 0.3963
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1087
+            "score": 0.1066
           }
         }
       ],
diff --git a/data/models/ai2_tulu-2-7b-rm-v0-nectar-binarized-3.8m-check....json b/data/models/ai2_tulu-2-7b-rm-v0-nectar-binarized-3.8m-check....json
index e1ac41e4bb97f41e9784803c588108ddfee89905..e9d556b28d7550c1e76a8e996c98b852c7622823 100644
--- a/data/models/ai2_tulu-2-7b-rm-v0-nectar-binarized-3.8m-check....json
+++ b/data/models/ai2_tulu-2-7b-rm-v0-nectar-binarized-3.8m-check....json
@@ -38,7 +38,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7058
+            "score": 0.6905
           },
           "source_data": {
             "dataset_name": "RewardBench",
@@ -56,7 +56,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9525
+            "score": 0.9441
           },
           "source_data": {
             "dataset_name": "RewardBench",
@@ -74,7 +74,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3947
+            "score": 0.3596
           },
           "source_data": {
             "dataset_name": "RewardBench",
@@ -92,7 +92,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7703
+            "score": 0.7676
           },
           "source_data": {
             "dataset_name": "RewardBench",
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6895
+            "score": 0.6808
           },
           "source_data": {
             "dataset_name": "RewardBench",
@@ -152,7 +152,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9385
+            "score": 0.9302
           },
           "source_data": {
             "dataset_name": "RewardBench",
@@ -170,7 +170,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3706
+            "score": 0.3596
           },
           "source_data": {
             "dataset_name": "RewardBench",
@@ -188,7 +188,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7595
+            "score": 0.7527
           },
           "source_data": {
             "dataset_name": "RewardBench",
@@ -230,7 +230,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7019
+            "score": 0.6895
           },
           "source_data": {
             "dataset_name": "RewardBench",
@@ -248,7 +248,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9497
+            "score": 0.9385
           },
           "source_data": {
             "dataset_name": "RewardBench",
@@ -266,7 +266,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.375
+            "score": 0.3706
           },
           "source_data": {
             "dataset_name": "RewardBench",
@@ -284,7 +284,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7811
+            "score": 0.7595
           },
           "source_data": {
             "dataset_name": "RewardBench",
@@ -326,7 +326,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6905
+            "score": 0.7004
           },
           "source_data": {
             "dataset_name": "RewardBench",
@@ -344,7 +344,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9441
+            "score": 0.9413
           },
           "source_data": {
             "dataset_name": "RewardBench",
@@ -362,7 +362,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3596
+            "score": 0.3882
           },
           "source_data": {
             "dataset_name": "RewardBench",
@@ -380,7 +380,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7676
+            "score": 0.7716
           },
           "source_data": {
             "dataset_name": "RewardBench",
@@ -422,7 +422,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6808
+            "score": 0.7019
           },
           "source_data": {
             "dataset_name": "RewardBench",
@@ -440,7 +440,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9302
+            "score": 0.9497
           },
           "source_data": {
             "dataset_name": "RewardBench",
@@ -458,7 +458,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3596
+            "score": 0.375
           },
           "source_data": {
             "dataset_name": "RewardBench",
@@ -476,7 +476,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7527
+            "score": 0.7811
           },
           "source_data": {
             "dataset_name": "RewardBench",
@@ -518,7 +518,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6924
+            "score": 0.7058
           },
           "source_data": {
             "dataset_name": "RewardBench",
@@ -536,7 +536,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9441
+            "score": 0.9525
           },
           "source_data": {
             "dataset_name": "RewardBench",
@@ -554,7 +554,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3575
+            "score": 0.3947
           },
           "source_data": {
             "dataset_name": "RewardBench",
@@ -572,7 +572,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7757
+            "score": 0.7703
           },
           "source_data": {
             "dataset_name": "RewardBench",
@@ -614,7 +614,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6945
+            "score": 0.7008
           },
           "source_data": {
             "dataset_name": "RewardBench",
@@ -650,7 +650,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3706
+            "score": 0.3882
           },
           "source_data": {
             "dataset_name": "RewardBench",
@@ -668,7 +668,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7743
+            "score": 0.7757
           },
           "source_data": {
             "dataset_name": "RewardBench",
@@ -710,7 +710,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7004
+            "score": 0.6945
           },
           "source_data": {
             "dataset_name": "RewardBench",
@@ -728,7 +728,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9413
+            "score": 0.9385
           },
           "source_data": {
             "dataset_name": "RewardBench",
@@ -746,7 +746,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3882
+            "score": 0.3706
           },
           "source_data": {
             "dataset_name": "RewardBench",
@@ -764,7 +764,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7716
+            "score": 0.7743
           },
           "source_data": {
             "dataset_name": "RewardBench",
@@ -806,7 +806,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7008
+            "score": 0.6924
           },
           "source_data": {
             "dataset_name": "RewardBench",
@@ -824,7 +824,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9385
+            "score": 0.9441
           },
           "source_data": {
             "dataset_name": "RewardBench",
@@ -842,7 +842,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3882
+            "score": 0.3575
           },
           "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 f598d15a400b5ed438e43880c6cab3a3248e3641..78f6ba994c4cff4ccaf572ddc5297bedb19efb9b 100644
--- a/data/models/alibaba_qwen-3-coder-480b.json
+++ b/data/models/alibaba_qwen-3-coder-480b.json
@@ -4,13 +4,13 @@
     "id": "alibaba/qwen-3-coder-480b",
     "developer": "Alibaba",
     "additional_details": {
-      "agent_name": "OpenHands",
-      "agent_organization": "OpenHands"
+      "agent_name": "Dakou Agent",
+      "agent_organization": "iflow"
     }
   },
   "evaluations": [
     {
-      "evaluation_id": "terminal-bench-2.0/openhands__qwen-3-coder-480b/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/dakou-agent__qwen-3-coder-480b/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -34,7 +34,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-11-02",
+          "evaluation_timestamp": "2025-12-28",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -43,7 +43,7 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 25.4,
+            "score": 27.2,
             "uncertainty": {
               "standard_error": {
                 "value": 2.6
@@ -53,7 +53,7 @@
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"OpenHands\" -m \"Qwen 3 Coder 480B\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Dakou Agent\" -m \"Qwen 3 Coder 480B\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -70,7 +70,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"OpenHands\" -m \"Qwen 3 Coder 480B\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Dakou Agent\" -m \"Qwen 3 Coder 480B\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -84,7 +84,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/dakou-agent__qwen-3-coder-480b/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/openhands__qwen-3-coder-480b/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -108,7 +108,7 @@
               "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,
@@ -117,7 +117,7 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 27.2,
+            "score": 25.4,
             "uncertainty": {
               "standard_error": {
                 "value": 2.6
@@ -127,7 +127,7 @@
           },
           "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": [
                   {
@@ -144,7 +144,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Dakou Agent\" -m \"Qwen 3 Coder 480B\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"OpenHands\" -m \"Qwen 3 Coder 480B\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
diff --git a/data/models/allenai_llama-3.1-70b-instruct-rm-rb2.json b/data/models/allenai_llama-3.1-70b-instruct-rm-rb2.json
index 6b82bed55df1bdb62067f41e1f2f588c7fd5e772..3edb4e861c9c885f1d8b857f90568f09968d9fbc 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-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",
@@ -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": 0.7606
-          },
-          "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"
           }
         }
       ],
@@ -159,10 +141,10 @@
       "generation_config": null
     },
     {
-      "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",
@@ -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": 0.9021
+            "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"
           }
         }
       ],
diff --git a/data/models/allenai_llama-3.1-tulu-3-70b.json b/data/models/allenai_llama-3.1-tulu-3-70b.json
index 1db7ede127ee803b7ffd5960ed83ddaa8fe5c58c..dedd220cd13dda3e92225bd87465795dab977b4c 100644
--- a/data/models/allenai_llama-3.1-tulu-3-70b.json
+++ b/data/models/allenai_llama-3.1-tulu-3-70b.json
@@ -5,7 +5,7 @@
     "developer": "allenai",
     "inference_platform": "unknown",
     "additional_details": {
-      "precision": "bfloat16",
+      "precision": "float16",
       "architecture": "LlamaForCausalLM",
       "params_billions": "70.554"
     }
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.8291
+            "score": 0.8379
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6164
+            "score": 0.6157
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4502
+            "score": 0.3829
           }
         },
         {
@@ -116,7 +116,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4948
+            "score": 0.4988
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4645
+            "score": 0.4656
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.8379
+            "score": 0.8291
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6157
+            "score": 0.6164
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3829
+            "score": 0.4502
           }
         },
         {
@@ -246,7 +246,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4988
+            "score": 0.4948
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4656
+            "score": 0.4645
           }
         }
       ],
diff --git a/data/models/allenai_llama-3.1-tulu-3-8b-rl-rm-rb2.json b/data/models/allenai_llama-3.1-tulu-3-8b-rl-rm-rb2.json
index c04edea77c13058100e53f5dc2eead6fb95e8fc2..407df5e17676737402cd08d14ff8185dc4fb9a2a 100644
--- a/data/models/allenai_llama-3.1-tulu-3-8b-rl-rm-rb2.json
+++ b/data/models/allenai_llama-3.1-tulu-3-8b-rl-rm-rb2.json
@@ -9,10 +9,10 @@
   },
   "evaluations": [
     {
-      "evaluation_id": "reward-bench-2/allenai_Llama-3.1-Tulu-3-8B-RL-RM-RB2/1766412838.146816",
+      "evaluation_id": "reward-bench/allenai_Llama-3.1-Tulu-3-8B-RL-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": 0.6871
-          },
-          "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": 0.7642
+            "score": 0.8369
           },
           "source_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": 0.4
+            "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": "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": 0.7588
           },
           "source_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": 0.8644
+            "score": 0.8703
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Focus",
+          "evaluation_name": "Reasoning",
           "metric_config": {
-            "evaluation_description": "Focus score - measures response focus",
+            "evaluation_description": "Reasoning accuracy - includes code and math subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.8485
+            "score": 0.7715
           },
           "source_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": 0.6281
+            "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-RL-RM-RB2/1766412838.146816",
+      "evaluation_id": "reward-bench-2/allenai_Llama-3.1-Tulu-3-8B-RL-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": 0.8369
+            "score": 0.6871
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Chat",
+          "evaluation_name": "Factuality",
           "metric_config": {
-            "evaluation_description": "Chat accuracy - includes easy chat subsets",
+            "evaluation_description": "Factuality score - measures factual accuracy",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9469
+            "score": 0.7642
           },
           "source_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": 0.7588
+            "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": "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": 0.8703
+            "score": 0.8644
           },
           "source_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": 0.7715
+            "score": 0.8485
           },
           "source_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": 0.6281
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         }
       ],
diff --git a/data/models/allenai_llama-3.1-tulu-3-8b.json b/data/models/allenai_llama-3.1-tulu-3-8b.json
index 53350f20b1f74556a0af6a9aa87ed77d181deaec..7de1c9431728784c04f1c32781631febc2ed7e32 100644
--- a/data/models/allenai_llama-3.1-tulu-3-8b.json
+++ b/data/models/allenai_llama-3.1-tulu-3-8b.json
@@ -5,7 +5,7 @@
     "developer": "allenai",
     "inference_platform": "unknown",
     "additional_details": {
-      "precision": "float16",
+      "precision": "bfloat16",
       "architecture": "LlamaForCausalLM",
       "params_billions": "8.03"
     }
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.8255
+            "score": 0.8267
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4061
+            "score": 0.405
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2115
+            "score": 0.1964
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.297
+            "score": 0.2987
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2821
+            "score": 0.2827
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.8267
+            "score": 0.8255
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.405
+            "score": 0.4061
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1964
+            "score": 0.2115
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2987
+            "score": 0.297
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2827
+            "score": 0.2821
           }
         }
       ],
diff --git a/data/models/amd_amd-llama-135m.json b/data/models/amd_amd-llama-135m.json
index a445333e3dd0495a4c3e2fddf3e92a96b288f85c..dfdcf8e7a431ddc8bdf51b6aa797b81cf0f89c9e 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": "float16",
+      "precision": "bfloat16",
       "architecture": "LlamaForCausalLM",
-      "params_billions": "0.135"
+      "params_billions": "0.134"
     }
   },
   "evaluations": [
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1842
+            "score": 0.1918
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2974
+            "score": 0.2969
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0053
+            "score": 0.0076
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2525
+            "score": 0.2584
           }
         },
         {
@@ -116,7 +116,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.378
+            "score": 0.3846
           }
         },
         {
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1918
+            "score": 0.1842
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2969
+            "score": 0.2974
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0076
+            "score": 0.0053
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2584
+            "score": 0.2525
           }
         },
         {
@@ -246,7 +246,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3846
+            "score": 0.378
           }
         },
         {
diff --git a/data/models/anthropic_claude-3-5-haiku-20241022.json b/data/models/anthropic_claude-3-5-haiku-20241022.json
index 97ab32cadbb5e110dfa409cbea1ee9b8c38d6850..9edb0c7484cd3b1eab61fa90716227281f955253 100644
--- a/data/models/anthropic_claude-3-5-haiku-20241022.json
+++ b/data/models/anthropic_claude-3-5-haiku-20241022.json
@@ -10,8 +10,8 @@
   },
   "evaluations": [
     {
-      "evaluation_id": "global-mmlu-lite/anthropic_claude-3-5-haiku-20241022/1773936496.366405",
-      "retrieved_timestamp": "1773936496.366405",
+      "evaluation_id": "global-mmlu-lite/anthropic_claude-3-5-haiku-20241022/1773936583.743359",
+      "retrieved_timestamp": "1773936583.743359",
       "source_metadata": {
         "source_name": "Global MMLU Lite Leaderboard",
         "source_type": "documentation",
@@ -525,8 +525,8 @@
       "generation_config": null
     },
     {
-      "evaluation_id": "global-mmlu-lite/anthropic_claude-3-5-haiku-20241022/1773936583.743359",
-      "retrieved_timestamp": "1773936583.743359",
+      "evaluation_id": "global-mmlu-lite/anthropic_claude-3-5-haiku-20241022/1773936496.366405",
+      "retrieved_timestamp": "1773936496.366405",
       "source_metadata": {
         "source_name": "Global MMLU Lite Leaderboard",
         "source_type": "documentation",
diff --git a/data/models/anthropic_claude-3-opus-20240229.json b/data/models/anthropic_claude-3-opus-20240229.json
index 8f8b70dd804fcbb225ceb8111209d93e20e8bd0b..150503f1a5f91571d10a33f8965d4bd84f3ccf46 100644
--- a/data/models/anthropic_claude-3-opus-20240229.json
+++ b/data/models/anthropic_claude-3-opus-20240229.json
@@ -1903,10 +1903,10 @@
       }
     },
     {
-      "evaluation_id": "reward-bench/Anthropic_claude-3-opus-20240229/1766412838.146816",
+      "evaluation_id": "reward-bench-2/anthropic_claude-3-opus-20240229/1766412838.146816",
       "retrieved_timestamp": "1766412838.146816",
       "source_metadata": {
-        "source_name": "RewardBench",
+        "source_name": "RewardBench 2",
         "source_type": "documentation",
         "source_organization_name": "Allen Institute for AI",
         "source_organization_url": "https://allenai.org",
@@ -1925,128 +1925,104 @@
         {
           "evaluation_name": "Score",
           "metric_config": {
-            "evaluation_description": "Overall RewardBench Score",
+            "evaluation_description": "Overall RewardBench 2 Score (mean of all metrics)",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.8008
+            "score": 0.5744
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Chat",
+          "evaluation_name": "Factuality",
           "metric_config": {
-            "evaluation_description": "Chat accuracy - includes easy chat subsets",
+            "evaluation_description": "Factuality score - measures factual accuracy",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9469
+            "score": 0.5389
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Chat Hard",
+          "evaluation_name": "Precise IF",
           "metric_config": {
-            "evaluation_description": "Chat Hard accuracy - includes hard chat subsets",
+            "evaluation_description": "Precise Instruction Following score",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6031
+            "score": 0.3312
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Safety",
+          "evaluation_name": "Math",
           "metric_config": {
-            "evaluation_description": "Safety accuracy - includes safety subsets",
+            "evaluation_description": "Math score - measures mathematical reasoning",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.8662
+            "score": 0.5137
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Reasoning",
+          "evaluation_name": "Safety",
           "metric_config": {
-            "evaluation_description": "Reasoning accuracy - includes code and math subsets",
+            "evaluation_description": "Safety score - measures safety awareness",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7868
+            "score": 0.8378
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
-        }
-      ],
-      "detailed_evaluation_results": null,
-      "generation_config": null
-    },
-    {
-      "evaluation_id": "reward-bench-2/anthropic_claude-3-opus-20240229/1766412838.146816",
-      "retrieved_timestamp": "1766412838.146816",
-      "source_metadata": {
-        "source_name": "RewardBench 2",
-        "source_type": "documentation",
-        "source_organization_name": "Allen Institute for AI",
-        "source_organization_url": "https://allenai.org",
-        "evaluator_relationship": "third_party"
-      },
-      "eval_library": {
-        "name": "rewardbench",
-        "version": "0.1.3",
-        "additional_details": {
-          "subsets": "Chat, Chat Hard, Safety, Reasoning",
-          "hf_space": "allenai/reward-bench"
-        }
-      },
-      "benchmark": "reward-bench",
-      "evaluation_results": [
+        },
         {
-          "evaluation_name": "Score",
+          "evaluation_name": "Focus",
           "metric_config": {
-            "evaluation_description": "Overall RewardBench 2 Score (mean of all metrics)",
+            "evaluation_description": "Focus score - measures response focus",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5744
+            "score": 0.6646
           },
           "source_data": {
             "dataset_name": "RewardBench 2",
@@ -2055,111 +2031,135 @@
           }
         },
         {
-          "evaluation_name": "Factuality",
+          "evaluation_name": "Ties",
           "metric_config": {
-            "evaluation_description": "Factuality score - measures factual accuracy",
+            "evaluation_description": "Ties score - ability to identify tie cases",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5389
+            "score": 0.5601
           },
           "source_data": {
             "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
             "hf_repo": "allenai/reward-bench-2-results"
           }
-        },
+        }
+      ],
+      "detailed_evaluation_results": null,
+      "generation_config": null
+    },
+    {
+      "evaluation_id": "reward-bench/Anthropic_claude-3-opus-20240229/1766412838.146816",
+      "retrieved_timestamp": "1766412838.146816",
+      "source_metadata": {
+        "source_name": "RewardBench",
+        "source_type": "documentation",
+        "source_organization_name": "Allen Institute for AI",
+        "source_organization_url": "https://allenai.org",
+        "evaluator_relationship": "third_party"
+      },
+      "eval_library": {
+        "name": "rewardbench",
+        "version": "0.1.3",
+        "additional_details": {
+          "subsets": "Chat, Chat Hard, Safety, Reasoning",
+          "hf_space": "allenai/reward-bench"
+        }
+      },
+      "benchmark": "reward-bench",
+      "evaluation_results": [
         {
-          "evaluation_name": "Precise IF",
+          "evaluation_name": "Score",
           "metric_config": {
-            "evaluation_description": "Precise Instruction Following score",
+            "evaluation_description": "Overall RewardBench Score",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3312
+            "score": 0.8008
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Math",
+          "evaluation_name": "Chat",
           "metric_config": {
-            "evaluation_description": "Math score - measures mathematical reasoning",
+            "evaluation_description": "Chat accuracy - includes easy chat subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5137
+            "score": 0.9469
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Safety",
+          "evaluation_name": "Chat Hard",
           "metric_config": {
-            "evaluation_description": "Safety score - measures safety awareness",
+            "evaluation_description": "Chat Hard accuracy - includes hard chat subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.8378
+            "score": 0.6031
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Focus",
+          "evaluation_name": "Safety",
           "metric_config": {
-            "evaluation_description": "Focus score - measures response focus",
+            "evaluation_description": "Safety accuracy - includes safety subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6646
+            "score": 0.8662
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Ties",
+          "evaluation_name": "Reasoning",
           "metric_config": {
-            "evaluation_description": "Ties score - ability to identify tie cases",
+            "evaluation_description": "Reasoning accuracy - includes code and math subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5601
+            "score": 0.7868
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         }
       ],
diff --git a/data/models/anthropic_claude-haiku-4.5.json b/data/models/anthropic_claude-haiku-4.5.json
index 0030689870b1d61c70e99ee0cdff0afc1d0e9bf2..e7b7ed8c329f7f81d319b4442fafacedb7ba1133 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": "Terminus 2",
-      "agent_organization": "Terminal Bench"
+      "agent_name": "Mini-SWE-Agent",
+      "agent_organization": "Princeton"
     }
   },
   "evaluations": [
     {
-      "evaluation_id": "terminal-bench-2.0/terminus-2__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",
@@ -34,7 +34,7 @@
               "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,
@@ -43,17 +43,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 28.3,
+            "score": 29.8,
             "uncertainty": {
               "standard_error": {
-                "value": 2.9
+                "value": 2.5
               },
               "num_samples": 435
             }
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -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": [
                   {
@@ -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 \"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": [
               {
@@ -84,7 +84,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/claude-code__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",
@@ -108,7 +108,7 @@
               "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,
@@ -117,17 +117,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 27.5,
+            "score": 28.3,
             "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 \"Terminus 2\" -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 \"Claude Code\" -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": [
               {
@@ -158,7 +158,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/mini-swe-agent__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",
@@ -182,7 +182,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-11-03",
+          "evaluation_timestamp": "2025-12-11",
           "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": 29.8,
+            "score": 35.5,
             "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 \"Goose\" -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 \"Mini-SWE-Agent\" -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": [
               {
@@ -232,7 +232,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/openhands__claude-haiku-4.5/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/claude-code__claude-haiku-4.5/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -256,7 +256,7 @@
               "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,
@@ -265,17 +265,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 13.9,
+            "score": 27.5,
             "uncertainty": {
               "standard_error": {
-                "value": 2.7
+                "value": 2.8
               },
               "num_samples": 435
             }
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"OpenHands\" -m \"Claude Haiku 4.5\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Claude Code\" -m \"Claude Haiku 4.5\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -292,7 +292,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"OpenHands\" -m \"Claude Haiku 4.5\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Claude Code\" -m \"Claude Haiku 4.5\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -306,7 +306,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/goose__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",
@@ -330,7 +330,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-12-11",
+          "evaluation_timestamp": "2025-11-02",
           "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": 35.5,
+            "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 \"Goose\" -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": [
                   {
@@ -366,7 +366,7 @@
       "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 \"OpenHands\" -m \"Claude Haiku 4.5\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
diff --git a/data/models/anthropic_claude-opus-4-5.json b/data/models/anthropic_claude-opus-4-5.json
index 0cd69b8f1e682224797162bd821dc65c4792b021..ec98797a0bada43df823aeb8285704dc256b7f56 100644
--- a/data/models/anthropic_claude-opus-4-5.json
+++ b/data/models/anthropic_claude-opus-4-5.json
@@ -10,7 +10,7 @@
   },
   "evaluations": [
     {
-      "evaluation_id": "browsecompplus/litellm-tool-calling-with-shortlisting__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",
@@ -23,34 +23,34 @@
         "name": "exgentic",
         "version": "0.1.0"
       },
-      "benchmark": "browsecompplus",
+      "benchmark": "appworld_test_normal",
       "evaluation_results": [
         {
-          "evaluation_name": "browsecompplus",
+          "evaluation_name": "appworld/test_normal",
           "source_data": {
-            "dataset_name": "browsecompplus",
+            "dataset_name": "appworld/test_normal",
             "source_type": "url",
             "url": [
               "https://github.com/Exgentic/exgentic"
             ]
           },
           "metric_config": {
-            "evaluation_description": "BrowseCompPlus benchmark evaluation",
+            "evaluation_description": "AppWorld benchmark evaluation (test_normal subset)",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.49,
+            "score": 0.64,
             "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": "3.43",
+              "total_run_cost": "343.32",
+              "average_steps": "20.06",
+              "percent_finished": "0.82"
             }
           },
           "generation_config": {
@@ -78,7 +78,7 @@
       }
     },
     {
-      "evaluation_id": "appworld/test_normal/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",
@@ -110,23 +110,23 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.61,
+            "score": 0.7,
             "uncertainty": {
               "num_samples": 100
             },
             "details": {
-              "average_agent_cost": "11.32",
-              "total_run_cost": "1132.47",
-              "average_steps": "21.99",
-              "percent_finished": "0.83"
+              "average_agent_cost": "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"
                 }
               }
             }
@@ -138,15 +138,15 @@
         "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/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",
@@ -159,42 +159,42 @@
         "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": 0.5294,
+            "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": "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"
                 }
               }
             }
@@ -206,8 +206,8 @@
         "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"
             }
           }
         }
@@ -282,7 +282,7 @@
       }
     },
     {
-      "evaluation_id": "appworld/test_normal/claude-code-cli__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",
@@ -295,34 +295,34 @@
         "name": "exgentic",
         "version": "0.1.0"
       },
-      "benchmark": "appworld_test_normal",
+      "benchmark": "browsecompplus",
       "evaluation_results": [
         {
-          "evaluation_name": "appworld/test_normal",
+          "evaluation_name": "browsecompplus",
           "source_data": {
-            "dataset_name": "appworld/test_normal",
+            "dataset_name": "browsecompplus",
             "source_type": "url",
             "url": [
               "https://github.com/Exgentic/exgentic"
             ]
           },
           "metric_config": {
-            "evaluation_description": "AppWorld benchmark evaluation (test_normal subset)",
+            "evaluation_description": "BrowseCompPlus benchmark evaluation",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.66,
+            "score": 0.5294,
             "uncertainty": {
-              "num_samples": 100
+              "num_samples": 51
             },
             "details": {
-              "average_agent_cost": "13.08",
-              "total_run_cost": "1308.38",
-              "average_steps": "49.69",
-              "percent_finished": "0.74"
+              "average_agent_cost": "11.66",
+              "total_run_cost": "594.68",
+              "average_steps": "31.04",
+              "percent_finished": "0.8431"
             }
           },
           "generation_config": {
@@ -349,6 +349,74 @@
         }
       }
     },
+    {
+      "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",
+        "source_type": "evaluation_run",
+        "source_organization_name": "Exgentic",
+        "source_organization_url": "https://github.com/Exgentic",
+        "evaluator_relationship": "third_party"
+      },
+      "eval_library": {
+        "name": "exgentic",
+        "version": "0.1.0"
+      },
+      "benchmark": "browsecompplus",
+      "evaluation_results": [
+        {
+          "evaluation_name": "browsecompplus",
+          "source_data": {
+            "dataset_name": "browsecompplus",
+            "source_type": "url",
+            "url": [
+              "https://github.com/Exgentic/exgentic"
+            ]
+          },
+          "metric_config": {
+            "evaluation_description": "BrowseCompPlus benchmark evaluation",
+            "lower_is_better": false,
+            "score_type": "continuous",
+            "min_score": 0.0,
+            "max_score": 1.0
+          },
+          "score_details": {
+            "score": 0.49,
+            "uncertainty": {
+              "num_samples": 100
+            },
+            "details": {
+              "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": "LiteLLM Tool Calling",
+                  "agent_framework": "tool_calling"
+                }
+              }
+            }
+          }
+        }
+      ],
+      "detailed_evaluation_results": null,
+      "generation_config": {
+        "generation_args": {
+          "agentic_eval_config": {
+            "additional_details": {
+              "agent_name": "LiteLLM Tool Calling",
+              "agent_framework": "tool_calling"
+            }
+          }
+        }
+      }
+    },
     {
       "evaluation_id": "appworld/test_normal/openai-solo__anthropic_claude-opus-4-5/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
@@ -486,7 +554,7 @@
       }
     },
     {
-      "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",
@@ -518,23 +586,23 @@
             "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"
                 }
               }
             }
@@ -546,15 +614,15 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "SmolAgents Code",
-              "agent_framework": "smolagents_code"
+              "agent_name": "Claude Code CLI",
+              "agent_framework": "claude_code"
             }
           }
         }
       }
     },
     {
-      "evaluation_id": "browsecompplus/litellm-tool-calling__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",
@@ -601,8 +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"
                 }
               }
             }
@@ -614,15 +682,15 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "LiteLLM Tool Calling",
-              "agent_framework": "tool_calling"
+              "agent_name": "LiteLLM Tool Calling with Shortlisting",
+              "agent_framework": "tool_calling_with_shortlisting"
             }
           }
         }
       }
     },
     {
-      "evaluation_id": "appworld/test_normal/litellm-tool-calling-with-shortlisting__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",
@@ -635,42 +703,42 @@
         "name": "exgentic",
         "version": "0.1.0"
       },
-      "benchmark": "appworld_test_normal",
+      "benchmark": "swe-bench",
       "evaluation_results": [
         {
-          "evaluation_name": "appworld/test_normal",
+          "evaluation_name": "swe-bench",
           "source_data": {
-            "dataset_name": "appworld/test_normal",
+            "dataset_name": "swe-bench",
             "source_type": "url",
             "url": [
               "https://github.com/Exgentic/exgentic"
             ]
           },
           "metric_config": {
-            "evaluation_description": "AppWorld benchmark evaluation (test_normal 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": 0.64,
+            "score": 0.8072,
             "uncertainty": {
-              "num_samples": 100
+              "num_samples": 83
             },
             "details": {
-              "average_agent_cost": "3.43",
-              "total_run_cost": "343.32",
-              "average_steps": "20.06",
-              "percent_finished": "0.82"
+              "average_agent_cost": "2.96",
+              "total_run_cost": "245.78",
+              "average_steps": "34.1",
+              "percent_finished": "1.0"
             }
           },
           "generation_config": {
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "LiteLLM Tool Calling with Shortlisting",
-                  "agent_framework": "tool_calling_with_shortlisting"
+                  "agent_name": "OpenAI Solo",
+                  "agent_framework": "openai_solo"
                 }
               }
             }
@@ -682,15 +750,15 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "LiteLLM Tool Calling with Shortlisting",
-              "agent_framework": "tool_calling_with_shortlisting"
+              "agent_name": "OpenAI Solo",
+              "agent_framework": "openai_solo"
             }
           }
         }
       }
     },
     {
-      "evaluation_id": "swe-bench/litellm-tool-calling-with-shortlisting__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",
@@ -737,8 +805,8 @@
             "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"
                 }
               }
             }
@@ -750,15 +818,15 @@
         "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": "swe-bench/smolagents-code__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",
@@ -790,14 +858,14 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.65,
+            "score": 0.7423,
             "uncertainty": {
-              "num_samples": 100
+              "num_samples": 97
             },
             "details": {
-              "average_agent_cost": "4.85",
-              "total_run_cost": "485.22",
-              "average_steps": "39.13",
+              "average_agent_cost": "5.6",
+              "total_run_cost": "543.62",
+              "average_steps": "31.76",
               "percent_finished": "1.0"
             }
           },
@@ -805,8 +873,8 @@
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "SmolAgents Code",
-                  "agent_framework": "smolagents_code"
+                  "agent_name": "Claude Code CLI",
+                  "agent_framework": "claude_code"
                 }
               }
             }
@@ -818,15 +886,15 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "SmolAgents Code",
-              "agent_framework": "smolagents_code"
+              "agent_name": "Claude Code CLI",
+              "agent_framework": "claude_code"
             }
           }
         }
       }
     },
     {
-      "evaluation_id": "swe-bench/litellm-tool-calling__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",
@@ -873,8 +941,8 @@
             "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"
                 }
               }
             }
@@ -886,15 +954,15 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "LiteLLM Tool Calling",
-              "agent_framework": "tool_calling"
+              "agent_name": "LiteLLM Tool Calling with Shortlisting",
+              "agent_framework": "tool_calling_with_shortlisting"
             }
           }
         }
       }
     },
     {
-      "evaluation_id": "swe-bench/claude-code-cli__anthropic_claude-opus-4-5/1774263615.0201504",
+      "evaluation_id": "swe-bench/smolagents-code__anthropic_claude-opus-4-5/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -926,14 +994,14 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7423,
+            "score": 0.65,
             "uncertainty": {
-              "num_samples": 97
+              "num_samples": 100
             },
             "details": {
-              "average_agent_cost": "5.6",
-              "total_run_cost": "543.62",
-              "average_steps": "31.76",
+              "average_agent_cost": "4.85",
+              "total_run_cost": "485.22",
+              "average_steps": "39.13",
               "percent_finished": "1.0"
             }
           },
@@ -941,8 +1009,8 @@
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "Claude Code CLI",
-                  "agent_framework": "claude_code"
+                  "agent_name": "SmolAgents Code",
+                  "agent_framework": "smolagents_code"
                 }
               }
             }
@@ -954,15 +1022,15 @@
         "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/airline/openai-solo__anthropic_claude-opus-4-5/1774263615.0201504",
+      "evaluation_id": "tau-bench-2/airline/litellm-tool-calling-with-shortlisting__anthropic_claude-opus-4-5/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -994,14 +1062,14 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.74,
+            "score": 0.66,
             "uncertainty": {
               "num_samples": 50
             },
             "details": {
-              "average_agent_cost": "0.72",
-              "total_run_cost": "36.55",
-              "average_steps": "12.22",
+              "average_agent_cost": "0.47",
+              "total_run_cost": "24.23",
+              "average_steps": "10.0",
               "percent_finished": "1.0"
             }
           },
@@ -1009,8 +1077,8 @@
             "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"
                 }
               }
             }
@@ -1022,8 +1090,8 @@
         "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"
             }
           }
         }
@@ -1098,7 +1166,7 @@
       }
     },
     {
-      "evaluation_id": "tau-bench-2/airline/litellm-tool-calling-with-shortlisting__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",
@@ -1145,8 +1213,8 @@
             "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"
                 }
               }
             }
@@ -1158,15 +1226,15 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "LiteLLM Tool Calling with Shortlisting",
-              "agent_framework": "tool_calling_with_shortlisting"
+              "agent_name": "LiteLLM Tool Calling",
+              "agent_framework": "tool_calling"
             }
           }
         }
       }
     },
     {
-      "evaluation_id": "tau-bench-2/airline/smolagents-code__anthropic_claude-opus-4-5/1774263615.0201504",
+      "evaluation_id": "tau-bench-2/airline/openai-solo__anthropic_claude-opus-4-5/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -1198,82 +1266,14 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.72,
+            "score": 0.74,
             "uncertainty": {
               "num_samples": 50
             },
             "details": {
-              "average_agent_cost": "0.78",
-              "total_run_cost": "39.67",
-              "average_steps": "11.88",
-              "percent_finished": "1.0"
-            }
-          },
-          "generation_config": {
-            "generation_args": {
-              "agentic_eval_config": {
-                "additional_details": {
-                  "agent_name": "SmolAgents Code",
-                  "agent_framework": "smolagents_code"
-                }
-              }
-            }
-          }
-        }
-      ],
-      "detailed_evaluation_results": null,
-      "generation_config": {
-        "generation_args": {
-          "agentic_eval_config": {
-            "additional_details": {
-              "agent_name": "SmolAgents Code",
-              "agent_framework": "smolagents_code"
-            }
-          }
-        }
-      }
-    },
-    {
-      "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",
-        "source_type": "evaluation_run",
-        "source_organization_name": "Exgentic",
-        "source_organization_url": "https://github.com/Exgentic",
-        "evaluator_relationship": "third_party"
-      },
-      "eval_library": {
-        "name": "exgentic",
-        "version": "0.1.0"
-      },
-      "benchmark": "swe-bench",
-      "evaluation_results": [
-        {
-          "evaluation_name": "swe-bench",
-          "source_data": {
-            "dataset_name": "swe-bench",
-            "source_type": "url",
-            "url": [
-              "https://github.com/Exgentic/exgentic"
-            ]
-          },
-          "metric_config": {
-            "evaluation_description": "SWE-bench benchmark evaluation",
-            "lower_is_better": false,
-            "score_type": "continuous",
-            "min_score": 0.0,
-            "max_score": 1.0
-          },
-          "score_details": {
-            "score": 0.8072,
-            "uncertainty": {
-              "num_samples": 83
-            },
-            "details": {
-              "average_agent_cost": "2.96",
-              "total_run_cost": "245.78",
-              "average_steps": "34.1",
+              "average_agent_cost": "0.72",
+              "total_run_cost": "36.55",
+              "average_steps": "12.22",
               "percent_finished": "1.0"
             }
           },
@@ -1302,7 +1302,7 @@
       }
     },
     {
-      "evaluation_id": "tau-bench-2/airline/litellm-tool-calling__anthropic_claude-opus-4-5/1774263615.0201504",
+      "evaluation_id": "tau-bench-2/airline/smolagents-code__anthropic_claude-opus-4-5/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -1334,14 +1334,14 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.66,
+            "score": 0.72,
             "uncertainty": {
               "num_samples": 50
             },
             "details": {
-              "average_agent_cost": "0.47",
-              "total_run_cost": "24.23",
-              "average_steps": "10.0",
+              "average_agent_cost": "0.78",
+              "total_run_cost": "39.67",
+              "average_steps": "11.88",
               "percent_finished": "1.0"
             }
           },
@@ -1349,8 +1349,8 @@
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "LiteLLM Tool Calling",
-                  "agent_framework": "tool_calling"
+                  "agent_name": "SmolAgents Code",
+                  "agent_framework": "smolagents_code"
                 }
               }
             }
@@ -1362,15 +1362,15 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "LiteLLM Tool Calling",
-              "agent_framework": "tool_calling"
+              "agent_name": "SmolAgents Code",
+              "agent_framework": "smolagents_code"
             }
           }
         }
       }
     },
     {
-      "evaluation_id": "tau-bench-2/retail/smolagents-code__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",
@@ -1407,9 +1407,9 @@
               "num_samples": 100
             },
             "details": {
-              "average_agent_cost": "0.67",
-              "total_run_cost": "68.24",
-              "average_steps": "11.71",
+              "average_agent_cost": "0.47",
+              "total_run_cost": "48.01",
+              "average_steps": "11.33",
               "percent_finished": "1.0"
             }
           },
@@ -1417,8 +1417,8 @@
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "SmolAgents Code",
-                  "agent_framework": "smolagents_code"
+                  "agent_name": "LiteLLM Tool Calling",
+                  "agent_framework": "tool_calling"
                 }
               }
             }
@@ -1430,15 +1430,15 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "SmolAgents Code",
-              "agent_framework": "smolagents_code"
+              "agent_name": "LiteLLM Tool Calling",
+              "agent_framework": "tool_calling"
             }
           }
         }
       }
     },
     {
-      "evaluation_id": "tau-bench-2/retail/litellm-tool-calling__anthropic_claude-opus-4-5/1774263615.0201504",
+      "evaluation_id": "tau-bench-2/retail/claude-code-cli__anthropic_claude-opus-4-5/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -1470,14 +1470,14 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.78,
+            "score": 0.83,
             "uncertainty": {
               "num_samples": 100
             },
             "details": {
-              "average_agent_cost": "0.47",
-              "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"
             }
           },
@@ -1485,8 +1485,8 @@
             "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"
                 }
               }
             }
@@ -1498,15 +1498,15 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "LiteLLM Tool Calling",
-              "agent_framework": "tool_calling"
+              "agent_name": "Claude Code CLI",
+              "agent_framework": "claude_code"
             }
           }
         }
       }
     },
     {
-      "evaluation_id": "tau-bench-2/retail/claude-code-cli__anthropic_claude-opus-4-5/1774263615.0201504",
+      "evaluation_id": "tau-bench-2/retail/smolagents-code__anthropic_claude-opus-4-5/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -1538,14 +1538,14 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.83,
+            "score": 0.78,
             "uncertainty": {
               "num_samples": 100
             },
             "details": {
-              "average_agent_cost": "1.6",
-              "total_run_cost": "161.14",
-              "average_steps": "12.54",
+              "average_agent_cost": "0.67",
+              "total_run_cost": "68.24",
+              "average_steps": "11.71",
               "percent_finished": "1.0"
             }
           },
@@ -1553,8 +1553,8 @@
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "Claude Code CLI",
-                  "agent_framework": "claude_code"
+                  "agent_name": "SmolAgents Code",
+                  "agent_framework": "smolagents_code"
                 }
               }
             }
@@ -1566,8 +1566,8 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "Claude Code CLI",
-              "agent_framework": "claude_code"
+              "agent_name": "SmolAgents Code",
+              "agent_framework": "smolagents_code"
             }
           }
         }
@@ -1710,7 +1710,7 @@
       }
     },
     {
-      "evaluation_id": "tau-bench-2/telecom/litellm-tool-calling-with-shortlisting__anthropic_claude-opus-4-5/1774263615.0201504",
+      "evaluation_id": "tau-bench-2/telecom/smolagents-code__anthropic_claude-opus-4-5/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -1742,14 +1742,14 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.76,
+            "score": 0.58,
             "uncertainty": {
               "num_samples": 100
             },
             "details": {
-              "average_agent_cost": "0.92",
-              "total_run_cost": "102.01",
-              "average_steps": "17.22",
+              "average_agent_cost": "1.06",
+              "total_run_cost": "114.62",
+              "average_steps": "13.77",
               "percent_finished": "1.0"
             }
           },
@@ -1757,8 +1757,8 @@
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "LiteLLM Tool Calling with Shortlisting",
-                  "agent_framework": "tool_calling_with_shortlisting"
+                  "agent_name": "SmolAgents Code",
+                  "agent_framework": "smolagents_code"
                 }
               }
             }
@@ -1770,15 +1770,15 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "LiteLLM Tool Calling with Shortlisting",
-              "agent_framework": "tool_calling_with_shortlisting"
+              "agent_name": "SmolAgents Code",
+              "agent_framework": "smolagents_code"
             }
           }
         }
       }
     },
     {
-      "evaluation_id": "tau-bench-2/telecom/smolagents-code__anthropic_claude-opus-4-5/1774263615.0201504",
+      "evaluation_id": "tau-bench-2/telecom/litellm-tool-calling__anthropic_claude-opus-4-5/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -1810,14 +1810,14 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.58,
+            "score": 0.76,
             "uncertainty": {
               "num_samples": 100
             },
             "details": {
-              "average_agent_cost": "1.06",
-              "total_run_cost": "114.62",
-              "average_steps": "13.77",
+              "average_agent_cost": "0.92",
+              "total_run_cost": "102.01",
+              "average_steps": "17.22",
               "percent_finished": "1.0"
             }
           },
@@ -1825,8 +1825,8 @@
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "SmolAgents Code",
-                  "agent_framework": "smolagents_code"
+                  "agent_name": "LiteLLM Tool Calling",
+                  "agent_framework": "tool_calling"
                 }
               }
             }
@@ -1838,8 +1838,8 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "SmolAgents Code",
-              "agent_framework": "smolagents_code"
+              "agent_name": "LiteLLM Tool Calling",
+              "agent_framework": "tool_calling"
             }
           }
         }
@@ -1914,7 +1914,7 @@
       }
     },
     {
-      "evaluation_id": "tau-bench-2/telecom/litellm-tool-calling__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",
@@ -1961,8 +1961,8 @@
             "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"
                 }
               }
             }
@@ -1974,8 +1974,8 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "LiteLLM Tool Calling",
-              "agent_framework": "tool_calling"
+              "agent_name": "LiteLLM Tool Calling with Shortlisting",
+              "agent_framework": "tool_calling_with_shortlisting"
             }
           }
         }
diff --git a/data/models/anthropic_claude-opus-4.1.json b/data/models/anthropic_claude-opus-4.1.json
index 66d9a9691d54a3cae59a5a4b0972ad6110b06a9b..643c986c59e6df513c07edafb084900951fa2ab2 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": "Mini-SWE-Agent",
-      "agent_organization": "Princeton"
+      "agent_name": "Claude Code",
+      "agent_organization": "Anthropic"
     }
   },
   "evaluations": [
     {
-      "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",
@@ -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": 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": [
                   {
@@ -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 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": [
               {
@@ -84,7 +84,7 @@
       }
     },
     {
-      "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",
@@ -108,7 +108,7 @@
               "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,
@@ -117,17 +117,17 @@
             "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": [
                   {
@@ -144,7 +144,7 @@
       "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": [
               {
@@ -158,7 +158,7 @@
       }
     },
     {
-      "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",
@@ -182,7 +182,7 @@
               "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,
@@ -191,17 +191,17 @@
             "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": [
                   {
@@ -218,7 +218,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Claude Code\" -m \"Claude Opus 4.1\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"Claude Opus 4.1\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -232,7 +232,7 @@
       }
     },
     {
-      "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",
@@ -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": 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": [
                   {
@@ -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 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": [
               {
diff --git a/data/models/anthropic_claude-opus-4.5.json b/data/models/anthropic_claude-opus-4.5.json
index 08f15dd6e988a559ca38856b6df4c4e4d53b00a1..04c518e21852763638180858614bb6ac2be608de 100644
--- a/data/models/anthropic_claude-opus-4.5.json
+++ b/data/models/anthropic_claude-opus-4.5.json
@@ -78,7 +78,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/mux__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",
@@ -102,7 +102,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2026-01-17",
+          "evaluation_timestamp": "2025-11-22",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -111,11 +111,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 58.4
+            "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 \"Mux\" -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": [
                   {
@@ -132,7 +138,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Mux\" -m \"Claude Opus 4.5\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"Claude Opus 4.5\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -146,7 +152,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/terminus-2__claude-opus-4.5/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/mux__claude-opus-4.5/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -170,7 +176,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-11-22",
+          "evaluation_timestamp": "2026-01-17",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -179,17 +185,11 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 57.8,
-            "uncertainty": {
-              "standard_error": {
-                "value": 2.5
-              },
-              "num_samples": 435
-            }
+            "score": 58.4
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"Claude Opus 4.5\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Mux\" -m \"Claude Opus 4.5\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -206,7 +206,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"Claude Opus 4.5\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Mux\" -m \"Claude Opus 4.5\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -220,7 +220,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/openhands__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",
@@ -244,7 +244,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2026-01-04",
+          "evaluation_timestamp": "2025-12-17",
           "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": 51.9,
+            "score": 59.1,
             "uncertainty": {
               "standard_error": {
-                "value": 2.9
+                "value": 2.4
               },
               "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 \"Letta Code\" -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 \"OpenHands\" -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": [
               {
@@ -516,7 +516,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/letta-code__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",
@@ -540,7 +540,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-12-17",
+          "evaluation_timestamp": "2026-01-04",
           "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": 59.1,
+            "score": 51.9,
             "uncertainty": {
               "standard_error": {
-                "value": 2.4
+                "value": 2.9
               },
               "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 \"OpenHands\" -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 \"Letta Code\" -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": [
               {
diff --git a/data/models/anthropic_claude-opus-4.6.json b/data/models/anthropic_claude-opus-4.6.json
index 1ae6eba958aa9144fbbc47e84b576827e9ba8012..a41a27dbfdbf4960b47a33e1930b531d6b54f85b 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": "TongAgents",
-      "agent_organization": "Bigai"
+      "agent_name": "Droid",
+      "agent_organization": "Factory"
     }
   },
   "evaluations": [
     {
-      "evaluation_id": "terminal-bench-2.0/tongagents__claude-opus-4.6/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/droid__claude-opus-4.6/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -34,7 +34,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2026-02-22",
+          "evaluation_timestamp": "2026-02-05",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -43,17 +43,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 71.9,
+            "score": 69.9,
             "uncertainty": {
               "standard_error": {
-                "value": 2.7
+                "value": 2.5
               },
               "num_samples": 435
             }
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"TongAgents\" -m \"Claude Opus 4.6\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Droid\" -m \"Claude Opus 4.6\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -70,7 +70,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"TongAgents\" -m \"Claude Opus 4.6\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Droid\" -m \"Claude Opus 4.6\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -84,7 +84,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/droid__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",
@@ -108,7 +108,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2026-02-05",
+          "evaluation_timestamp": "2026-02-23",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -117,17 +117,11 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 69.9,
-            "uncertainty": {
-              "standard_error": {
-                "value": 2.5
-              },
-              "num_samples": 435
-            }
+            "score": 66.9
           },
           "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 \"Crux\" -m \"Claude Opus 4.6\" -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 \"Droid\" -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": [
               {
@@ -158,7 +152,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/terminus-kira__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",
@@ -182,7 +176,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2026-02-22",
+          "evaluation_timestamp": "2026-02-13",
           "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": 74.7,
+            "score": 66.5,
             "uncertainty": {
               "standard_error": {
-                "value": 2.6
+                "value": 2.5
               },
               "num_samples": 435
             }
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus-KIRA\" -m \"Claude Opus 4.6\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Mux\" -m \"Claude Opus 4.6\" -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-KIRA\" -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": [
               {
@@ -232,7 +226,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/terminus-2__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",
@@ -256,7 +250,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2026-02-06",
+          "evaluation_timestamp": "2026-02-07",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -265,17 +259,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 62.9,
+            "score": 58.0,
             "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 \"Terminus 2\" -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": [
                   {
@@ -292,7 +286,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"Claude Opus 4.6\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Claude Code\" -m \"Claude Opus 4.6\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -306,7 +300,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/mux__claude-opus-4.6/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/terminus-2__claude-opus-4.6/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -330,7 +324,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2026-02-13",
+          "evaluation_timestamp": "2026-02-06",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -339,17 +333,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 66.5,
+            "score": 62.9,
             "uncertainty": {
               "standard_error": {
-                "value": 2.5
+                "value": 2.7
               },
               "num_samples": 435
             }
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Mux\" -m \"Claude Opus 4.6\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"Claude Opus 4.6\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -366,7 +360,7 @@
       "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 \"Terminus 2\" -m \"Claude Opus 4.6\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -380,7 +374,7 @@
       }
     },
     {
-      "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",
@@ -404,7 +398,7 @@
               "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,
@@ -413,17 +407,17 @@
             "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": [
                   {
@@ -440,7 +434,7 @@
       "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": [
               {
@@ -454,7 +448,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/crux__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",
@@ -478,7 +472,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2026-02-23",
+          "evaluation_timestamp": "2026-02-22",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -487,11 +481,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 66.9
+            "score": 74.7,
+            "uncertainty": {
+              "standard_error": {
+                "value": 2.6
+              },
+              "num_samples": 435
+            }
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Crux\" -m \"Claude Opus 4.6\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus-KIRA\" -m \"Claude Opus 4.6\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -508,7 +508,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Crux\" -m \"Claude Opus 4.6\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus-KIRA\" -m \"Claude Opus 4.6\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
diff --git a/data/models/anthropic_claude-sonnet-4.5.json b/data/models/anthropic_claude-sonnet-4.5.json
index c0439a05bb694a022b80d498957deb384990a100..53dd8e2195a24f3d530bf69beec973cc6e94f1f4 100644
--- a/data/models/anthropic_claude-sonnet-4.5.json
+++ b/data/models/anthropic_claude-sonnet-4.5.json
@@ -4,13 +4,13 @@
     "id": "anthropic/claude-sonnet-4.5",
     "developer": "Anthropic",
     "additional_details": {
-      "agent_name": "Goose",
-      "agent_organization": "Block"
+      "agent_name": "CAMEL-AI",
+      "agent_organization": "CAMEL-AI"
     }
   },
   "evaluations": [
     {
-      "evaluation_id": "terminal-bench-2.0/goose__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",
@@ -34,7 +34,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-12-11",
+          "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": 43.1,
+            "score": 46.5,
             "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 \"Goose\" -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": [
                   {
@@ -70,7 +70,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Goose\" -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": [
               {
@@ -84,7 +84,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/camel-ai__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",
@@ -108,7 +108,7 @@
               "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,
@@ -117,17 +117,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 46.5,
+            "score": 42.8,
             "uncertainty": {
               "standard_error": {
-                "value": 2.4
+                "value": 2.8
               },
               "num_samples": 435
             }
           },
           "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 \"Terminus 2\" -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 \"CAMEL-AI\" -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": [
               {
@@ -158,7 +158,7 @@
       }
     },
     {
-      "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",
@@ -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": 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": [
                   {
@@ -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 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": [
               {
@@ -232,7 +232,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/terminus-2__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",
@@ -256,7 +256,7 @@
               "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,
@@ -265,7 +265,7 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 42.8,
+            "score": 42.5,
             "uncertainty": {
               "standard_error": {
                 "value": 2.8
@@ -275,7 +275,7 @@
           },
           "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 \"Mini-SWE-Agent\" -m \"Claude Sonnet 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 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": [
               {
@@ -306,7 +306,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/openhands__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",
@@ -330,7 +330,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-11-02",
+          "evaluation_timestamp": "2026-01-04",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -339,17 +339,11 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 42.6,
-            "uncertainty": {
-              "standard_error": {
-                "value": 2.8
-              },
-              "num_samples": 435
-            }
+            "score": 42.7
           },
           "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 \"MAYA\" -m \"Claude Sonnet 4.5\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -366,7 +360,7 @@
       "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 \"MAYA\" -m \"Claude Sonnet 4.5\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -380,7 +374,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/maya__claude-sonnet-4.5/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/goose__claude-sonnet-4.5/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -404,7 +398,7 @@
               "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,
@@ -413,11 +407,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 42.7
+            "score": 43.1,
+            "uncertainty": {
+              "standard_error": {
+                "value": 2.6
+              },
+              "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 \"Goose\" -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 \"MAYA\" -m \"Claude Sonnet 4.5\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Goose\" -m \"Claude Sonnet 4.5\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -448,7 +448,7 @@
       }
     },
     {
-      "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",
@@ -472,7 +472,7 @@
               "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,
@@ -481,17 +481,17 @@
             "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": [
                   {
@@ -508,7 +508,7 @@
       "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": [
               {
diff --git a/data/models/arcee-ai_arcee-spark.json b/data/models/arcee-ai_arcee-spark.json
index e194ce4efc974318b0bb01e7560254bdd047ab55..611dbc409a44fd2eadd33b4e30a3048a3002308e 100644
--- a/data/models/arcee-ai_arcee-spark.json
+++ b/data/models/arcee-ai_arcee-spark.json
@@ -5,7 +5,7 @@
     "developer": "arcee-ai",
     "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": 0.5718
+            "score": 0.5621
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5481
+            "score": 0.5489
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.114
+            "score": 0.2953
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3062
+            "score": 0.307
           }
         },
         {
@@ -116,7 +116,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4008
+            "score": 0.4021
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3813
+            "score": 0.3822
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5621
+            "score": 0.5718
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5489
+            "score": 0.5481
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2953
+            "score": 0.114
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.307
+            "score": 0.3062
           }
         },
         {
@@ -246,7 +246,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4021
+            "score": 0.4008
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3822
+            "score": 0.3813
           }
         }
       ],
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 c02cc4e6043653215ef5039a1e40518d83ff39e0..d9c4a63a2048d58930bc10ecb5695a3676976b8f 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": "float16",
+      "precision": "bfloat16",
       "architecture": "Qwen2ForCausalLM",
       "params_billions": "1.544"
     }
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4605
+            "score": 0.4511
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4258
+            "score": 0.4275
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0748
+            "score": 0.1473
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2659
+            "score": 0.2701
           }
         },
         {
@@ -116,7 +116,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3636
+            "score": 0.3623
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2812
+            "score": 0.2806
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4511
+            "score": 0.4605
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4275
+            "score": 0.4258
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1473
+            "score": 0.0748
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2701
+            "score": 0.2659
           }
         },
         {
@@ -246,7 +246,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3623
+            "score": 0.3636
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2806
+            "score": 0.2812
           }
         }
       ],
diff --git a/data/models/boltmonkey_neuraldaredevil-supernova-lite-7b-dareties-abliterated.json b/data/models/boltmonkey_neuraldaredevil-supernova-lite-7b-dareties-abliterated.json
index eb03ad8b35e71a4f26603a2960132d29f0246b60..ed5c0ad9e23e3e1024094c595c2931cbc579e102 100644
--- a/data/models/boltmonkey_neuraldaredevil-supernova-lite-7b-dareties-abliterated.json
+++ b/data/models/boltmonkey_neuraldaredevil-supernova-lite-7b-dareties-abliterated.json
@@ -5,7 +5,7 @@
     "developer": "BoltMonkey",
     "inference_platform": "unknown",
     "additional_details": {
-      "precision": "bfloat16",
+      "precision": "float16",
       "architecture": "LlamaForCausalLM",
       "params_billions": "8.03"
     }
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7999
+            "score": 0.459
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5152
+            "score": 0.5185
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1193
+            "score": 0.0937
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.281
+            "score": 0.2743
           }
         },
         {
@@ -116,7 +116,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4019
+            "score": 0.4083
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3733
+            "score": 0.3631
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.459
+            "score": 0.7999
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5185
+            "score": 0.5152
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0937
+            "score": 0.1193
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2743
+            "score": 0.281
           }
         },
         {
@@ -246,7 +246,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4083
+            "score": 0.4019
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3631
+            "score": 0.3733
           }
         }
       ],
diff --git a/data/models/cognitivecomputations_dolphin-2.9.2-phi-3-medium-abliterated.json b/data/models/cognitivecomputations_dolphin-2.9.2-phi-3-medium-abliterated.json
index 62d09c3db567da9932caf7141d7a1389c1aafea9..9b7cc35f188c98dba3f0427de09e77d4b26cfc40 100644
--- a/data/models/cognitivecomputations_dolphin-2.9.2-phi-3-medium-abliterated.json
+++ b/data/models/cognitivecomputations_dolphin-2.9.2-phi-3-medium-abliterated.json
@@ -5,7 +5,7 @@
     "developer": "cognitivecomputations",
     "inference_platform": "unknown",
     "additional_details": {
-      "precision": "bfloat16",
+      "precision": "float16",
       "architecture": "MistralForCausalLM",
       "params_billions": "13.96"
     }
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4124
+            "score": 0.3613
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6383
+            "score": 0.6123
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.182
+            "score": 0.1239
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3289
+            "score": 0.328
           }
         },
         {
@@ -116,7 +116,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4349
+            "score": 0.4112
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4525
+            "score": 0.4494
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3613
+            "score": 0.4124
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6123
+            "score": 0.6383
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1239
+            "score": 0.182
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.328
+            "score": 0.3289
           }
         },
         {
@@ -246,7 +246,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4112
+            "score": 0.4349
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4494
+            "score": 0.4525
           }
         }
       ],
diff --git a/data/models/cohere_command-a-03-2025.json b/data/models/cohere_command-a-03-2025.json
index 205f7c496ed81b612dd2b182b3cf2e9fd9ac9c54..aedaf4e5f944a400d87afc543fa422bde24be135 100644
--- a/data/models/cohere_command-a-03-2025.json
+++ b/data/models/cohere_command-a-03-2025.json
@@ -10,8 +10,8 @@
   },
   "evaluations": [
     {
-      "evaluation_id": "global-mmlu-lite/cohere_command-a-03-2025/1773936583.743359",
-      "retrieved_timestamp": "1773936583.743359",
+      "evaluation_id": "global-mmlu-lite/cohere_command-a-03-2025/1773936496.366405",
+      "retrieved_timestamp": "1773936496.366405",
       "source_metadata": {
         "source_name": "Global MMLU Lite Leaderboard",
         "source_type": "documentation",
@@ -525,8 +525,8 @@
       "generation_config": null
     },
     {
-      "evaluation_id": "global-mmlu-lite/cohere_command-a-03-2025/1773936496.366405",
-      "retrieved_timestamp": "1773936496.366405",
+      "evaluation_id": "global-mmlu-lite/cohere_command-a-03-2025/1773936583.743359",
+      "retrieved_timestamp": "1773936583.743359",
       "source_metadata": {
         "source_name": "Global MMLU Lite Leaderboard",
         "source_type": "documentation",
diff --git a/data/models/columbia-nlp_lion-gemma-2b-dpo-v1.0.json b/data/models/columbia-nlp_lion-gemma-2b-dpo-v1.0.json
index fcba7390760a9757eb868fa82619eef91d551f86..e1500a121f56ad89301900472e223d7937764cb0 100644
--- a/data/models/columbia-nlp_lion-gemma-2b-dpo-v1.0.json
+++ b/data/models/columbia-nlp_lion-gemma-2b-dpo-v1.0.json
@@ -5,7 +5,7 @@
     "developer": "Columbia-NLP",
     "inference_platform": "unknown",
     "additional_details": {
-      "precision": "bfloat16",
+      "precision": "float16",
       "architecture": "GemmaForCausalLM",
       "params_billions": "2.506"
     }
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3102
+            "score": 0.3278
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3881
+            "score": 0.392
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0536
+            "score": 0.0431
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2534
+            "score": 0.2492
           }
         },
         {
@@ -116,7 +116,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4081
+            "score": 0.412
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1665
+            "score": 0.1666
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3278
+            "score": 0.3102
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.392
+            "score": 0.3881
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0431
+            "score": 0.0536
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2492
+            "score": 0.2534
           }
         },
         {
@@ -246,7 +246,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.412
+            "score": 0.4081
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1666
+            "score": 0.1665
           }
         }
       ],
diff --git a/data/models/cpayne1303_llama-43m-beta.json b/data/models/cpayne1303_llama-43m-beta.json
index 0f0d3430f35b22a1aef8ac071591532d594d6d4d..8e62d1be9edc1ccaeda7702d1a793fd5db4d4150 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": "float16",
+      "precision": "bfloat16",
       "architecture": "LlamaForCausalLM",
       "params_billions": "0.043"
     }
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1949
+            "score": 0.1916
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2965
+            "score": 0.2977
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0045
+            "score": 0.0
           }
         },
         {
@@ -116,7 +116,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3885
+            "score": 0.3872
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1111
+            "score": 0.1132
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1916
+            "score": 0.1949
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2977
+            "score": 0.2965
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0
+            "score": 0.0045
           }
         },
         {
@@ -246,7 +246,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3872
+            "score": 0.3885
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1132
+            "score": 0.1111
           }
         }
       ],
diff --git a/data/models/daemontatox_documentcogito.json b/data/models/daemontatox_documentcogito.json
index 157a2466b6d71022e4fcfd8ace48804c5b301a99..6383820e3f19a97d2a08bca3546e5cca52a154e3 100644
--- a/data/models/daemontatox_documentcogito.json
+++ b/data/models/daemontatox_documentcogito.json
@@ -5,7 +5,7 @@
     "developer": "Daemontatox",
     "inference_platform": "unknown",
     "additional_details": {
-      "precision": "bfloat16",
+      "precision": "float16",
       "architecture": "MllamaForConditionalGeneration",
       "params_billions": "10.67"
     }
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5064
+            "score": 0.777
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5112
+            "score": 0.5187
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1631
+            "score": 0.2198
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3163
+            "score": 0.2936
           }
         },
         {
@@ -116,7 +116,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3973
+            "score": 0.3911
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3802
+            "score": 0.3738
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.777
+            "score": 0.5064
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5187
+            "score": 0.5112
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2198
+            "score": 0.1631
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2936
+            "score": 0.3163
           }
         },
         {
@@ -246,7 +246,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3911
+            "score": 0.3973
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3738
+            "score": 0.3802
           }
         }
       ],
diff --git a/data/models/daemontatox_pathfinderai.json b/data/models/daemontatox_pathfinderai.json
index 8b13e2aabf79ff36b82f8d8bd4c0bcdf2b41e385..7a5f7d25c7278e2df08548a48abfe0b0ee9b4f2a 100644
--- a/data/models/daemontatox_pathfinderai.json
+++ b/data/models/daemontatox_pathfinderai.json
@@ -5,7 +5,7 @@
     "developer": "Daemontatox",
     "inference_platform": "unknown",
     "additional_details": {
-      "precision": "float16",
+      "precision": "bfloat16",
       "architecture": "Qwen2ForCausalLM",
       "params_billions": "32.764"
     }
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3745
+            "score": 0.4855
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6668
+            "score": 0.6627
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4758
+            "score": 0.4841
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3943
+            "score": 0.3096
           }
         },
         {
@@ -116,7 +116,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4858
+            "score": 0.4256
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5593
+            "score": 0.5542
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4855
+            "score": 0.3745
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6627
+            "score": 0.6668
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4841
+            "score": 0.4758
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3096
+            "score": 0.3943
           }
         },
         {
@@ -246,7 +246,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4256
+            "score": 0.4858
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5542
+            "score": 0.5593
           }
         }
       ],
diff --git a/data/models/deepmount00_llama-3.1-8b-ita.json b/data/models/deepmount00_llama-3.1-8b-ita.json
index be94466036e753700b8de72e15b468fc6edebdee..1fef7ca0b3d471692e7379016093b45312ecc7df 100644
--- a/data/models/deepmount00_llama-3.1-8b-ita.json
+++ b/data/models/deepmount00_llama-3.1-8b-ita.json
@@ -6,8 +6,8 @@
     "inference_platform": "unknown",
     "additional_details": {
       "precision": "bfloat16",
-      "architecture": "Unknown",
-      "params_billions": "0.0",
+      "architecture": "LlamaForCausalLM",
+      "params_billions": "8.03",
       "model_id_aliases": [
         "DeepMount00/Llama-3.1-8b-Ita"
       ]
@@ -15,7 +15,7 @@
   },
   "evaluations": [
     {
-      "evaluation_id": "hfopenllm_v2/DeepMount00_Llama-3.1-8b-Ita/1773936498.240187",
+      "evaluation_id": "hfopenllm_v2/DeepMount00_Llama-3.1-8b-ITA/1773936498.240187",
       "retrieved_timestamp": "1773936498.240187",
       "source_metadata": {
         "source_name": "HF Open LLM v2",
@@ -47,7 +47,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5365
+            "score": 0.7917
           }
         },
         {
@@ -65,7 +65,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.517
+            "score": 0.5109
           }
         },
         {
@@ -83,7 +83,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1707
+            "score": 0.1088
           }
         },
         {
@@ -101,7 +101,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3062
+            "score": 0.2878
           }
         },
         {
@@ -119,7 +119,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4487
+            "score": 0.4136
           }
         },
         {
@@ -137,7 +137,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.396
+            "score": 0.3876
           }
         }
       ],
@@ -145,7 +145,7 @@
       "generation_config": null
     },
     {
-      "evaluation_id": "hfopenllm_v2/DeepMount00_Llama-3.1-8b-ITA/1773936498.240187",
+      "evaluation_id": "hfopenllm_v2/DeepMount00_Llama-3.1-8b-Ita/1773936498.240187",
       "retrieved_timestamp": "1773936498.240187",
       "source_metadata": {
         "source_name": "HF Open LLM v2",
@@ -177,7 +177,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7917
+            "score": 0.5365
           }
         },
         {
@@ -195,7 +195,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5109
+            "score": 0.517
           }
         },
         {
@@ -213,7 +213,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1088
+            "score": 0.1707
           }
         },
         {
@@ -231,7 +231,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2878
+            "score": 0.3062
           }
         },
         {
@@ -249,7 +249,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4136
+            "score": 0.4487
           }
         },
         {
@@ -267,7 +267,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3876
+            "score": 0.396
           }
         }
       ],
diff --git a/data/models/deepseek_deepseek-r1-0528.json b/data/models/deepseek_deepseek-r1-0528.json
index 22f7f1e7159f38877f415a9a6f07905fabcb5d33..712c8d82096fdfa393951ac4421e5d6c18ee722d 100644
--- a/data/models/deepseek_deepseek-r1-0528.json
+++ b/data/models/deepseek_deepseek-r1-0528.json
@@ -10,8 +10,8 @@
   },
   "evaluations": [
     {
-      "evaluation_id": "global-mmlu-lite/deepseek_deepseek-r1-0528/1773936496.366405",
-      "retrieved_timestamp": "1773936496.366405",
+      "evaluation_id": "global-mmlu-lite/deepseek_deepseek-r1-0528/1773936583.743359",
+      "retrieved_timestamp": "1773936583.743359",
       "source_metadata": {
         "source_name": "Global MMLU Lite Leaderboard",
         "source_type": "documentation",
@@ -525,8 +525,8 @@
       "generation_config": null
     },
     {
-      "evaluation_id": "global-mmlu-lite/deepseek_deepseek-r1-0528/1773936583.743359",
-      "retrieved_timestamp": "1773936583.743359",
+      "evaluation_id": "global-mmlu-lite/deepseek_deepseek-r1-0528/1773936496.366405",
+      "retrieved_timestamp": "1773936496.366405",
       "source_metadata": {
         "source_name": "Global MMLU Lite Leaderboard",
         "source_type": "documentation",
diff --git a/data/models/deepseek_deepseek-v3.1.json b/data/models/deepseek_deepseek-v3.1.json
index 28271d97eb42a16e44db35269bdfee0d33d2475a..52e144fa11c26943b339cba2c9fa28b1d9098c61 100644
--- a/data/models/deepseek_deepseek-v3.1.json
+++ b/data/models/deepseek_deepseek-v3.1.json
@@ -7,8 +7,8 @@
   },
   "evaluations": [
     {
-      "evaluation_id": "global-mmlu-lite/deepseek_deepseek-v3.1/1773936583.743359",
-      "retrieved_timestamp": "1773936583.743359",
+      "evaluation_id": "global-mmlu-lite/deepseek_deepseek-v3.1/1773936496.366405",
+      "retrieved_timestamp": "1773936496.366405",
       "source_metadata": {
         "source_name": "Global MMLU Lite Leaderboard",
         "source_type": "documentation",
@@ -522,8 +522,8 @@
       "generation_config": null
     },
     {
-      "evaluation_id": "global-mmlu-lite/deepseek_deepseek-v3.1/1773936496.366405",
-      "retrieved_timestamp": "1773936496.366405",
+      "evaluation_id": "global-mmlu-lite/deepseek_deepseek-v3.1/1773936583.743359",
+      "retrieved_timestamp": "1773936583.743359",
       "source_metadata": {
         "source_name": "Global MMLU Lite Leaderboard",
         "source_type": "documentation",
diff --git a/data/models/doppelreflex_mn-12b-lilithframe.json b/data/models/doppelreflex_mn-12b-lilithframe.json
index 2532c65fe82e1d06f8d68b438dbffc94e3e4e4bb..720fbe0846130d5605f8d9f0e7d4c1731ec8e47c 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": "bfloat16",
+      "precision": "float16",
       "architecture": "MistralForCausalLM",
       "params_billions": "12.248"
     }
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.436
+            "score": 0.451
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4956
+            "score": 0.4944
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0589
+            "score": 0.1156
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3205
+            "score": 0.3196
           }
         },
         {
@@ -116,7 +116,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3843
+            "score": 0.3896
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3237
+            "score": 0.3256
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.451
+            "score": 0.436
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4944
+            "score": 0.4956
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1156
+            "score": 0.0589
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3196
+            "score": 0.3205
           }
         },
         {
@@ -246,7 +246,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3896
+            "score": 0.3843
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3256
+            "score": 0.3237
           }
         }
       ],
diff --git a/data/models/epistemeai_fireball-meta-llama-3.1-8b-instruct-agent-0.003-128k-code-ds-auto.json b/data/models/epistemeai_fireball-meta-llama-3.1-8b-instruct-agent-0.003-128k-code-ds-auto.json
index 34df651aabdc1d7685c9419a18517c0c9ee2b5a2..623bd9c2c8bfaa513dd516b6dc8551699ef2135b 100644
--- a/data/models/epistemeai_fireball-meta-llama-3.1-8b-instruct-agent-0.003-128k-code-ds-auto.json
+++ b/data/models/epistemeai_fireball-meta-llama-3.1-8b-instruct-agent-0.003-128k-code-ds-auto.json
@@ -5,7 +5,7 @@
     "developer": "EpistemeAI",
     "inference_platform": "unknown",
     "additional_details": {
-      "precision": "float16",
+      "precision": "bfloat16",
       "architecture": "LlamaForCausalLM",
       "params_billions": "8.03"
     }
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7305
+            "score": 0.7207
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4649
+            "score": 0.461
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1397
+            "score": 0.1314
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2659
+            "score": 0.2701
           }
         },
         {
@@ -116,7 +116,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3209
+            "score": 0.3432
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.348
+            "score": 0.3354
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7207
+            "score": 0.7305
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.461
+            "score": 0.4649
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1314
+            "score": 0.1397
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2701
+            "score": 0.2659
           }
         },
         {
@@ -246,7 +246,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3432
+            "score": 0.3209
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3354
+            "score": 0.348
           }
         }
       ],
diff --git a/data/models/etherll_herplete-llm-llama-3.1-8b.json b/data/models/etherll_herplete-llm-llama-3.1-8b.json
index 31e2291931d31d5d1deeb312e00cc5de025980fd..1f50fb1261d1ec9c67c961ac513392f51c62e5ca 100644
--- a/data/models/etherll_herplete-llm-llama-3.1-8b.json
+++ b/data/models/etherll_herplete-llm-llama-3.1-8b.json
@@ -5,7 +5,7 @@
     "developer": "Etherll",
     "inference_platform": "unknown",
     "additional_details": {
-      "precision": "bfloat16",
+      "precision": "float16",
       "architecture": "LlamaForCausalLM",
       "params_billions": "8.03"
     }
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6106
+            "score": 0.4672
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5347
+            "score": 0.5013
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1548
+            "score": 0.0279
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3146
+            "score": 0.2861
           }
         },
         {
@@ -116,7 +116,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3991
+            "score": 0.386
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3752
+            "score": 0.3482
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4672
+            "score": 0.6106
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5013
+            "score": 0.5347
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0279
+            "score": 0.1548
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2861
+            "score": 0.3146
           }
         },
         {
@@ -246,7 +246,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.386
+            "score": 0.3991
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3482
+            "score": 0.3752
           }
         }
       ],
diff --git a/data/models/fblgit_thebeagle-v2beta-32b-mgs.json b/data/models/fblgit_thebeagle-v2beta-32b-mgs.json
index 48527656a7b3e346612bd66367de25eb0d8e37d9..9045bce2e8448418fb4689f76787fc39b7a5722c 100644
--- a/data/models/fblgit_thebeagle-v2beta-32b-mgs.json
+++ b/data/models/fblgit_thebeagle-v2beta-32b-mgs.json
@@ -5,7 +5,7 @@
     "developer": "fblgit",
     "inference_platform": "unknown",
     "additional_details": {
-      "precision": "float16",
+      "precision": "bfloat16",
       "architecture": "Qwen2ForCausalLM",
       "params_billions": "32.764"
     }
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4503
+            "score": 0.5181
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7035
+            "score": 0.7033
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3943
+            "score": 0.4947
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.401
+            "score": 0.3826
           }
         },
         {
@@ -116,7 +116,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5021
+            "score": 0.5008
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5911
+            "score": 0.5915
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5181
+            "score": 0.4503
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7033
+            "score": 0.7035
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4947
+            "score": 0.3943
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3826
+            "score": 0.401
           }
         },
         {
@@ -246,7 +246,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5008
+            "score": 0.5021
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5915
+            "score": 0.5911
           }
         }
       ],
diff --git a/data/models/goekdeniz-guelmez_josie-7b-v6.0-step2000.json b/data/models/goekdeniz-guelmez_josie-7b-v6.0-step2000.json
index 37f82f81803012f4270da262872645abffc35b8f..4037d46b51c1d5f1b2d23453c409340e1c080518 100644
--- a/data/models/goekdeniz-guelmez_josie-7b-v6.0-step2000.json
+++ b/data/models/goekdeniz-guelmez_josie-7b-v6.0-step2000.json
@@ -5,7 +5,7 @@
     "developer": "Goekdeniz-Guelmez",
     "inference_platform": "unknown",
     "additional_details": {
-      "precision": "bfloat16",
+      "precision": "float16",
       "architecture": "Qwen2ForCausalLM",
       "params_billions": "7.616"
     }
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7628
+            "score": 0.7598
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5098
+            "score": 0.5107
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0
+            "score": 0.4237
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2802
+            "score": 0.2768
           }
         },
         {
@@ -116,7 +116,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4579
+            "score": 0.4539
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4033
+            "score": 0.4012
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7598
+            "score": 0.7628
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5107
+            "score": 0.5098
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4237
+            "score": 0.0
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2768
+            "score": 0.2802
           }
         },
         {
@@ -246,7 +246,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4539
+            "score": 0.4579
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4012
+            "score": 0.4033
           }
         }
       ],
diff --git a/data/models/google_gemini-2.5-flash.json b/data/models/google_gemini-2.5-flash.json
index e86caee99d92f5b1111f5d4cfe31c4107b3564b0..820c8d9942dde2ebcfddb6efd01e86ba89a1eddf 100644
--- a/data/models/google_gemini-2.5-flash.json
+++ b/data/models/google_gemini-2.5-flash.json
@@ -10,8 +10,8 @@
   },
   "evaluations": [
     {
-      "evaluation_id": "global-mmlu-lite/google_gemini-2.5-flash/1773936583.743359",
-      "retrieved_timestamp": "1773936583.743359",
+      "evaluation_id": "global-mmlu-lite/google_gemini-2.5-flash/1773936496.366405",
+      "retrieved_timestamp": "1773936496.366405",
       "source_metadata": {
         "source_name": "Global MMLU Lite Leaderboard",
         "source_type": "documentation",
@@ -525,8 +525,8 @@
       "generation_config": null
     },
     {
-      "evaluation_id": "global-mmlu-lite/google_gemini-2.5-flash/1773936496.366405",
-      "retrieved_timestamp": "1773936496.366405",
+      "evaluation_id": "global-mmlu-lite/google_gemini-2.5-flash/1773936583.743359",
+      "retrieved_timestamp": "1773936583.743359",
       "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-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",
@@ -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": 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": [
                   {
@@ -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 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": [
               {
@@ -1343,7 +1343,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/openhands__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",
@@ -1367,7 +1367,7 @@
               "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,
@@ -1376,7 +1376,7 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 16.4,
+            "score": 16.9,
             "uncertainty": {
               "standard_error": {
                 "value": 2.4
@@ -1386,7 +1386,7 @@
           },
           "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 \"Terminus 2\" -m \"Gemini 2.5 Flash\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -1403,7 +1403,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"OpenHands\" -m \"Gemini 2.5 Flash\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"Gemini 2.5 Flash\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -1417,7 +1417,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/gemini-cli__gemini-2.5-flash/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/openhands__gemini-2.5-flash/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -1441,7 +1441,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-11-04",
+          "evaluation_timestamp": "2025-11-02",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -1450,17 +1450,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 15.4,
+            "score": 16.4,
             "uncertainty": {
               "standard_error": {
-                "value": 2.3
+                "value": 2.4
               },
               "num_samples": 435
             }
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Gemini CLI\" -m \"Gemini 2.5 Flash\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"OpenHands\" -m \"Gemini 2.5 Flash\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -1477,7 +1477,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Gemini CLI\" -m \"Gemini 2.5 Flash\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"OpenHands\" -m \"Gemini 2.5 Flash\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -1491,7 +1491,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/mini-swe-agent__gemini-2.5-flash/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/gemini-cli__gemini-2.5-flash/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -1515,7 +1515,7 @@
               "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,
@@ -1524,17 +1524,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 17.1,
+            "score": 15.4,
             "uncertainty": {
               "standard_error": {
-                "value": 2.5
+                "value": 2.3
               },
               "num_samples": 435
             }
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Mini-SWE-Agent\" -m \"Gemini 2.5 Flash\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Gemini CLI\" -m \"Gemini 2.5 Flash\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -1551,7 +1551,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Mini-SWE-Agent\" -m \"Gemini 2.5 Flash\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Gemini CLI\" -m \"Gemini 2.5 Flash\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
diff --git a/data/models/google_gemini-2.5-pro.json b/data/models/google_gemini-2.5-pro.json
index f2d7e76912c502afd2dae0560e9a20a114690132..ad69bc6f71351eff92acf181b72bb1ef3d2ca29a 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/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",
@@ -525,8 +525,8 @@
       "generation_config": null
     },
     {
-      "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",
@@ -1269,7 +1269,7 @@
       "generation_config": null
     },
     {
-      "evaluation_id": "terminal-bench-2.0/mini-swe-agent__gemini-2.5-pro/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/terminus-2__gemini-2.5-pro/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -1293,7 +1293,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-11-03",
+          "evaluation_timestamp": "2025-10-31",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -1302,17 +1302,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 26.1,
+            "score": 32.6,
             "uncertainty": {
               "standard_error": {
-                "value": 2.5
+                "value": 3.0
               },
               "num_samples": 435
             }
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Mini-SWE-Agent\" -m \"Gemini 2.5 Pro\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"Gemini 2.5 Pro\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -1329,7 +1329,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Mini-SWE-Agent\" -m \"Gemini 2.5 Pro\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"Gemini 2.5 Pro\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -1343,7 +1343,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/openhands__gemini-2.5-pro/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/mini-swe-agent__gemini-2.5-pro/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -1367,7 +1367,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-11-02",
+          "evaluation_timestamp": "2025-11-03",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -1376,17 +1376,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 16.4,
+            "score": 26.1,
             "uncertainty": {
               "standard_error": {
-                "value": 2.8
+                "value": 2.5
               },
               "num_samples": 435
             }
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"OpenHands\" -m \"Gemini 2.5 Pro\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Mini-SWE-Agent\" -m \"Gemini 2.5 Pro\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -1403,7 +1403,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"OpenHands\" -m \"Gemini 2.5 Pro\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Mini-SWE-Agent\" -m \"Gemini 2.5 Pro\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -1417,7 +1417,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/terminus-2__gemini-2.5-pro/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/gemini-cli__gemini-2.5-pro/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -1441,7 +1441,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-10-31",
+          "evaluation_timestamp": "2025-11-04",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -1450,17 +1450,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 32.6,
+            "score": 19.6,
             "uncertainty": {
               "standard_error": {
-                "value": 3.0
+                "value": 2.9
               },
               "num_samples": 435
             }
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"Gemini 2.5 Pro\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Gemini CLI\" -m \"Gemini 2.5 Pro\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -1477,7 +1477,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"Gemini 2.5 Pro\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Gemini CLI\" -m \"Gemini 2.5 Pro\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -1491,7 +1491,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/gemini-cli__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",
@@ -1515,7 +1515,7 @@
               "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,
@@ -1524,17 +1524,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 19.6,
+            "score": 16.4,
             "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 \"Gemini CLI\" -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": [
                   {
@@ -1551,7 +1551,7 @@
       "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 \"OpenHands\" -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 8ad1fcf1488cbfb100a465260bd9105159bfdda1..47fa2df5c9baf77e090796d7a217aa9e4577803b 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": "Junie CLI",
-      "agent_organization": "JetBrains"
+      "agent_name": "Terminus 2",
+      "agent_organization": "Terminal Bench"
     }
   },
   "evaluations": [
     {
-      "evaluation_id": "terminal-bench-2.0/junie-cli__gemini-3-flash/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/terminus-2__gemini-3-flash/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -34,7 +34,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-12-23",
+          "evaluation_timestamp": "2026-01-07",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -43,17 +43,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 64.3,
+            "score": 51.7,
             "uncertainty": {
               "standard_error": {
-                "value": 2.8
+                "value": 3.1
               },
               "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 \"Terminus 2\" -m \"Gemini 3 Flash\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -70,7 +70,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Junie CLI\" -m \"Gemini 3 Flash\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"Gemini 3 Flash\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -84,7 +84,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/terminus-2__gemini-3-flash/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/junie-cli__gemini-3-flash/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -108,7 +108,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2026-01-07",
+          "evaluation_timestamp": "2025-12-23",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -117,17 +117,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 51.7,
+            "score": 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": [
                   {
@@ -144,7 +144,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"Gemini 3 Flash\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Junie 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 3f20467a04db22c43c2d253a7e0a111a72926152..003d3891c3ed687a312bcf65a5ce96e8186ce448 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": "LiteLLM Tool Calling with Shortlisting",
-      "agent_framework": "tool_calling_with_shortlisting"
+      "agent_name": "SmolAgents Code",
+      "agent_framework": "smolagents_code"
     }
   },
   "evaluations": [
     {
-      "evaluation_id": "appworld/test_normal/litellm-tool-calling-with-shortlisting__google_gemini-3-pro-preview/1774263615.0201504",
+      "evaluation_id": "appworld/test_normal/smolagents-code__google_gemini-3-pro-preview/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -42,23 +42,23 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.55,
+            "score": 0.13,
             "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": "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": "LiteLLM Tool Calling with Shortlisting",
-                  "agent_framework": "tool_calling_with_shortlisting"
+                  "agent_name": "SmolAgents Code",
+                  "agent_framework": "smolagents_code"
                 }
               }
             }
@@ -70,8 +70,8 @@
         "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"
             }
           }
         }
@@ -146,7 +146,7 @@
       }
     },
     {
-      "evaluation_id": "appworld/test_normal/litellm-tool-calling__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",
@@ -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": 0.505,
+            "score": 0.51,
             "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": "2.85",
+              "total_run_cost": "284.68",
+              "average_steps": "22.88",
+              "percent_finished": "0.7"
             }
           },
           "generation_config": {
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "LiteLLM Tool Calling",
-                  "agent_framework": "tool_calling"
+                  "agent_name": "Claude Code CLI",
+                  "agent_framework": "claude_code"
                 }
               }
             }
@@ -206,15 +206,15 @@
         "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__google_gemini-3-pro-preview/1774263615.0201504",
+      "evaluation_id": "appworld/test_normal/litellm-tool-calling-with-shortlisting__google_gemini-3-pro-preview/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -246,23 +246,23 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.36,
+            "score": 0.55,
             "uncertainty": {
               "num_samples": 100
             },
             "details": {
-              "average_agent_cost": "3.11",
-              "total_run_cost": "310.55",
-              "average_steps": "38.01",
-              "percent_finished": "0.86"
+              "average_agent_cost": "1.3",
+              "total_run_cost": "130.49",
+              "average_steps": "22.59",
+              "percent_finished": "1.0"
             }
           },
           "generation_config": {
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "Claude Code CLI",
-                  "agent_framework": "claude_code"
+                  "agent_name": "LiteLLM Tool Calling with Shortlisting",
+                  "agent_framework": "tool_calling_with_shortlisting"
                 }
               }
             }
@@ -274,15 +274,15 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "Claude Code CLI",
-              "agent_framework": "claude_code"
+              "agent_name": "LiteLLM Tool Calling with Shortlisting",
+              "agent_framework": "tool_calling_with_shortlisting"
             }
           }
         }
       }
     },
     {
-      "evaluation_id": "browsecompplus/openai-solo__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",
@@ -314,23 +314,23 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3333,
+            "score": 0.57,
             "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": "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": "OpenAI Solo",
-                  "agent_framework": "openai_solo"
+                  "agent_name": "SmolAgents Code",
+                  "agent_framework": "smolagents_code"
                 }
               }
             }
@@ -342,15 +342,15 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "OpenAI Solo",
-              "agent_framework": "openai_solo"
+              "agent_name": "SmolAgents Code",
+              "agent_framework": "smolagents_code"
             }
           }
         }
       }
     },
     {
-      "evaluation_id": "browsecompplus/claude-code-cli__google_gemini-3-pro-preview/1774263615.0201504",
+      "evaluation_id": "appworld/test_normal/litellm-tool-calling__google_gemini-3-pro-preview/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -363,42 +363,42 @@
         "name": "exgentic",
         "version": "0.1.0"
       },
-      "benchmark": "browsecompplus",
+      "benchmark": "appworld_test_normal",
       "evaluation_results": [
         {
-          "evaluation_name": "browsecompplus",
+          "evaluation_name": "appworld/test_normal",
           "source_data": {
-            "dataset_name": "browsecompplus",
+            "dataset_name": "appworld/test_normal",
             "source_type": "url",
             "url": [
               "https://github.com/Exgentic/exgentic"
             ]
           },
           "metric_config": {
-            "evaluation_description": "BrowseCompPlus benchmark evaluation",
+            "evaluation_description": "AppWorld benchmark evaluation (test_normal subset)",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.51,
+            "score": 0.505,
             "uncertainty": {
               "num_samples": 100
             },
             "details": {
-              "average_agent_cost": "2.85",
-              "total_run_cost": "284.68",
-              "average_steps": "22.88",
-              "percent_finished": "0.7"
+              "average_agent_cost": "1.88",
+              "total_run_cost": "188.19",
+              "average_steps": "21.76",
+              "percent_finished": "0.99"
             }
           },
           "generation_config": {
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "Claude Code CLI",
-                  "agent_framework": "claude_code"
+                  "agent_name": "LiteLLM Tool Calling",
+                  "agent_framework": "tool_calling"
                 }
               }
             }
@@ -410,15 +410,15 @@
         "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/smolagents-code__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",
@@ -450,23 +450,23 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.13,
+            "score": 0.36,
             "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": "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": "SmolAgents Code",
-                  "agent_framework": "smolagents_code"
+                  "agent_name": "Claude Code CLI",
+                  "agent_framework": "claude_code"
                 }
               }
             }
@@ -478,15 +478,15 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "SmolAgents Code",
-              "agent_framework": "smolagents_code"
+              "agent_name": "Claude Code CLI",
+              "agent_framework": "claude_code"
             }
           }
         }
       }
     },
     {
-      "evaluation_id": "browsecompplus/litellm-tool-calling__google_gemini-3-pro-preview/1774263615.0201504",
+      "evaluation_id": "browsecompplus/openai-solo__google_gemini-3-pro-preview/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -518,23 +518,23 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.48,
+            "score": 0.3333,
             "uncertainty": {
-              "num_samples": 100
+              "num_samples": 99
             },
             "details": {
-              "average_agent_cost": "0.44",
-              "total_run_cost": "44.18",
-              "average_steps": "7.85",
-              "percent_finished": "0.99"
+              "average_agent_cost": "0.64",
+              "total_run_cost": "63.79",
+              "average_steps": "8.45",
+              "percent_finished": "0.6061"
             }
           },
           "generation_config": {
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "LiteLLM Tool Calling",
-                  "agent_framework": "tool_calling"
+                  "agent_name": "OpenAI Solo",
+                  "agent_framework": "openai_solo"
                 }
               }
             }
@@ -546,15 +546,15 @@
         "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": "browsecompplus/smolagents-code__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",
@@ -586,23 +586,23 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.57,
+            "score": 0.48,
             "uncertainty": {
               "num_samples": 100
             },
             "details": {
-              "average_agent_cost": "2.39",
-              "total_run_cost": "239.0",
-              "average_steps": "29.63",
-              "percent_finished": "0.69"
+              "average_agent_cost": "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": "SmolAgents Code",
-                  "agent_framework": "smolagents_code"
+                  "agent_name": "LiteLLM Tool Calling with Shortlisting",
+                  "agent_framework": "tool_calling_with_shortlisting"
                 }
               }
             }
@@ -614,15 +614,15 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "SmolAgents Code",
-              "agent_framework": "smolagents_code"
+              "agent_name": "LiteLLM Tool Calling with Shortlisting",
+              "agent_framework": "tool_calling_with_shortlisting"
             }
           }
         }
       }
     },
     {
-      "evaluation_id": "browsecompplus/litellm-tool-calling-with-shortlisting__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",
@@ -669,8 +669,8 @@
             "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"
                 }
               }
             }
@@ -682,8 +682,8 @@
         "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"
             }
           }
         }
@@ -1856,7 +1856,7 @@
       }
     },
     {
-      "evaluation_id": "tau-bench-2/airline/openai-solo__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",
@@ -1869,33 +1869,33 @@
         "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": 0.62,
+            "score": 0.71,
             "uncertainty": {
-              "num_samples": 50
+              "num_samples": 100
             },
             "details": {
-              "average_agent_cost": "0.21",
-              "total_run_cost": "11.18",
-              "average_steps": "10.9",
+              "average_agent_cost": "0.7",
+              "total_run_cost": "69.56",
+              "average_steps": "32.55",
               "percent_finished": "1.0"
             }
           },
@@ -1903,8 +1903,8 @@
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "OpenAI Solo",
-                  "agent_framework": "openai_solo"
+                  "agent_name": "LiteLLM Tool Calling",
+                  "agent_framework": "tool_calling"
                 }
               }
             }
@@ -1916,15 +1916,15 @@
         "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/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",
@@ -1971,8 +1971,8 @@
             "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"
                 }
               }
             }
@@ -1984,15 +1984,15 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "LiteLLM Tool Calling",
-              "agent_framework": "tool_calling"
+              "agent_name": "LiteLLM Tool Calling with Shortlisting",
+              "agent_framework": "tool_calling_with_shortlisting"
             }
           }
         }
       }
     },
     {
-      "evaluation_id": "swe-bench/litellm-tool-calling-with-shortlisting__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",
@@ -2024,14 +2024,14 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.71,
+            "score": 0.7234,
             "uncertainty": {
-              "num_samples": 100
+              "num_samples": 94
             },
             "details": {
-              "average_agent_cost": "0.7",
-              "total_run_cost": "69.56",
-              "average_steps": "32.55",
+              "average_agent_cost": "1.58",
+              "total_run_cost": "148.44",
+              "average_steps": "32.36",
               "percent_finished": "1.0"
             }
           },
@@ -2039,8 +2039,8 @@
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "LiteLLM Tool Calling with Shortlisting",
-                  "agent_framework": "tool_calling_with_shortlisting"
+                  "agent_name": "OpenAI Solo",
+                  "agent_framework": "openai_solo"
                 }
               }
             }
@@ -2052,15 +2052,15 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "LiteLLM Tool Calling with Shortlisting",
-              "agent_framework": "tool_calling_with_shortlisting"
+              "agent_name": "OpenAI Solo",
+              "agent_framework": "openai_solo"
             }
           }
         }
       }
     },
     {
-      "evaluation_id": "swe-bench/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",
@@ -2073,33 +2073,33 @@
         "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": 0.7,
             "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": "0.16",
+              "total_run_cost": "8.48",
+              "average_steps": "10.14",
               "percent_finished": "1.0"
             }
           },
@@ -2107,8 +2107,8 @@
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "OpenAI Solo",
-                  "agent_framework": "openai_solo"
+                  "agent_name": "LiteLLM Tool Calling",
+                  "agent_framework": "tool_calling"
                 }
               }
             }
@@ -2120,15 +2120,15 @@
         "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/claude-code-cli__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",
@@ -2160,14 +2160,14 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7,
+            "score": 0.62,
             "uncertainty": {
               "num_samples": 50
             },
             "details": {
-              "average_agent_cost": "0.34",
-              "total_run_cost": "17.45",
-              "average_steps": "12.62",
+              "average_agent_cost": "0.21",
+              "total_run_cost": "11.18",
+              "average_steps": "10.9",
               "percent_finished": "1.0"
             }
           },
@@ -2175,8 +2175,8 @@
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "Claude Code CLI",
-                  "agent_framework": "claude_code"
+                  "agent_name": "OpenAI Solo",
+                  "agent_framework": "openai_solo"
                 }
               }
             }
@@ -2188,15 +2188,15 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "Claude Code CLI",
-              "agent_framework": "claude_code"
+              "agent_name": "OpenAI Solo",
+              "agent_framework": "openai_solo"
             }
           }
         }
       }
     },
     {
-      "evaluation_id": "tau-bench-2/airline/litellm-tool-calling__google_gemini-3-pro-preview/1774263615.0201504",
+      "evaluation_id": "tau-bench-2/airline/claude-code-cli__google_gemini-3-pro-preview/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -2233,9 +2233,9 @@
               "num_samples": 50
             },
             "details": {
-              "average_agent_cost": "0.16",
-              "total_run_cost": "8.48",
-              "average_steps": "10.14",
+              "average_agent_cost": "0.34",
+              "total_run_cost": "17.45",
+              "average_steps": "12.62",
               "percent_finished": "1.0"
             }
           },
@@ -2243,8 +2243,8 @@
             "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"
                 }
               }
             }
@@ -2256,15 +2256,15 @@
         "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/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",
@@ -2296,14 +2296,14 @@
             "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"
             }
           },
@@ -2311,8 +2311,8 @@
             "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"
                 }
               }
             }
@@ -2324,15 +2324,15 @@
         "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/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",
@@ -2364,14 +2364,14 @@
             "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"
             }
           },
@@ -2379,8 +2379,8 @@
             "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"
                 }
               }
             }
@@ -2392,15 +2392,15 @@
         "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/retail/litellm-tool-calling-with-shortlisting__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",
@@ -2432,14 +2432,14 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.82,
+            "score": 0.7576,
             "uncertainty": {
               "num_samples": 100
             },
             "details": {
-              "average_agent_cost": "0.16",
-              "total_run_cost": "16.64",
-              "average_steps": "11.25",
+              "average_agent_cost": "0.21",
+              "total_run_cost": "21.43",
+              "average_steps": "11.3",
               "percent_finished": "1.0"
             }
           },
@@ -2447,8 +2447,8 @@
             "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"
                 }
               }
             }
@@ -2460,15 +2460,15 @@
         "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/retail/openai-solo__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",
@@ -2500,14 +2500,14 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.73,
+            "score": 0.7805,
             "uncertainty": {
               "num_samples": 100
             },
             "details": {
-              "average_agent_cost": "0.27",
-              "total_run_cost": "27.48",
-              "average_steps": "10.62",
+              "average_agent_cost": "0.19",
+              "total_run_cost": "19.38",
+              "average_steps": "11.18",
               "percent_finished": "1.0"
             }
           },
@@ -2515,8 +2515,8 @@
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "OpenAI Solo",
-                  "agent_framework": "openai_solo"
+                  "agent_name": "Claude Code CLI",
+                  "agent_framework": "claude_code"
                 }
               }
             }
@@ -2528,15 +2528,15 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "OpenAI Solo",
-              "agent_framework": "openai_solo"
+              "agent_name": "Claude Code CLI",
+              "agent_framework": "claude_code"
             }
           }
         }
       }
     },
     {
-      "evaluation_id": "tau-bench-2/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",
@@ -2583,8 +2583,8 @@
             "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"
                 }
               }
             }
@@ -2596,15 +2596,15 @@
         "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",
@@ -2636,14 +2636,14 @@
             "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"
             }
           },
@@ -2651,8 +2651,8 @@
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "SmolAgents Code",
-                  "agent_framework": "smolagents_code"
+                  "agent_name": "OpenAI Solo",
+                  "agent_framework": "openai_solo"
                 }
               }
             }
@@ -2664,15 +2664,15 @@
         "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/litellm-tool-calling__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",
@@ -2685,33 +2685,33 @@
         "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": 0.73,
+            "score": 0.82,
             "uncertainty": {
               "num_samples": 100
             },
             "details": {
-              "average_agent_cost": "0.3",
-              "total_run_cost": "36.75",
-              "average_steps": "14.84",
+              "average_agent_cost": "0.16",
+              "total_run_cost": "16.64",
+              "average_steps": "11.25",
               "percent_finished": "1.0"
             }
           },
@@ -2740,7 +2740,7 @@
       }
     },
     {
-      "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",
@@ -2772,23 +2772,23 @@
             "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"
                 }
               }
             }
@@ -2800,15 +2800,15 @@
         "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/smolagents-code__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",
@@ -2840,23 +2840,23 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.88,
+            "score": 0.8876,
             "uncertainty": {
               "num_samples": 100
             },
             "details": {
-              "average_agent_cost": "0.35",
-              "total_run_cost": "40.25",
-              "average_steps": "12.71",
-              "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": "SmolAgents Code",
-                  "agent_framework": "smolagents_code"
+                  "agent_name": "OpenAI Solo",
+                  "agent_framework": "openai_solo"
                 }
               }
             }
@@ -2868,15 +2868,15 @@
         "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/claude-code-cli__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",
@@ -2889,33 +2889,33 @@
         "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": 0.6852,
             "uncertainty": {
               "num_samples": 100
             },
             "details": {
-              "average_agent_cost": "0.19",
-              "total_run_cost": "19.38",
-              "average_steps": "11.18",
+              "average_agent_cost": "0.21",
+              "total_run_cost": "25.48",
+              "average_steps": "9.9",
               "percent_finished": "1.0"
             }
           },
@@ -2944,7 +2944,7 @@
       }
     },
     {
-      "evaluation_id": "tau-bench-2/telecom/litellm-tool-calling-with-shortlisting__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",
@@ -2976,14 +2976,14 @@
             "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"
             }
           },
@@ -2991,8 +2991,8 @@
             "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"
                 }
               }
             }
@@ -3004,15 +3004,15 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "LiteLLM Tool Calling with Shortlisting",
-              "agent_framework": "tool_calling_with_shortlisting"
+              "agent_name": "SmolAgents Code",
+              "agent_framework": "smolagents_code"
             }
           }
         }
       }
     },
     {
-      "evaluation_id": "tau-bench-2/telecom/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",
@@ -3044,14 +3044,14 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6852,
+            "score": 0.73,
             "uncertainty": {
               "num_samples": 100
             },
             "details": {
-              "average_agent_cost": "0.21",
-              "total_run_cost": "25.48",
-              "average_steps": "9.9",
+              "average_agent_cost": "0.3",
+              "total_run_cost": "36.75",
+              "average_steps": "14.84",
               "percent_finished": "1.0"
             }
           },
@@ -3059,8 +3059,8 @@
             "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"
                 }
               }
             }
@@ -3072,8 +3072,8 @@
         "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"
             }
           }
         }
diff --git a/data/models/google_gemini-3-pro.json b/data/models/google_gemini-3-pro.json
index 5acfd6f3e4c0e364f178f7fde5f99550b7d69ddb..11bc2c604594dba4ea7261f6d2e8fc51b386c982 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": "Droid",
-      "agent_organization": "Factory"
+      "agent_name": "SageAgent",
+      "agent_organization": "OpenSage"
     }
   },
   "evaluations": [
     {
-      "evaluation_id": "terminal-bench-2.0/droid__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",
@@ -34,7 +34,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-12-24",
+          "evaluation_timestamp": "2026-02-23",
           "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": 61.1,
+            "score": 65.2,
             "uncertainty": {
               "standard_error": {
-                "value": 2.8
+                "value": 2.1
               },
               "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 \"SageAgent\" -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 \"Droid\" -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": [
               {
@@ -84,7 +84,7 @@
       }
     },
     {
-      "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",
@@ -108,7 +108,7 @@
               "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,
@@ -117,17 +117,17 @@
             "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": [
                   {
@@ -144,7 +144,7 @@
       "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": [
               {
@@ -158,7 +158,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/terminus-2__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",
@@ -182,7 +182,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-11-21",
+          "evaluation_timestamp": "2025-12-17",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -191,17 +191,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 56.9,
+            "score": 56.0,
             "uncertainty": {
               "standard_error": {
-                "value": 2.5
+                "value": 3.0
               },
               "num_samples": 435
             }
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"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": [
                   {
@@ -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 \"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": [
               {
@@ -232,7 +232,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/ii-agent__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",
@@ -256,7 +256,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-12-23",
+          "evaluation_timestamp": "2026-01-06",
           "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": 61.8,
+            "score": 69.4,
             "uncertainty": {
               "standard_error": {
-                "value": 2.8
+                "value": 2.1
               },
               "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 \"Ante\" -m \"Gemini 3 Pro\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -292,7 +292,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"II-Agent\" -m \"Gemini 3 Pro\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Ante\" -m \"Gemini 3 Pro\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -306,7 +306,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/letta-code__gemini-3-pro/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/ii-agent__gemini-3-pro/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -330,7 +330,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-12-17",
+          "evaluation_timestamp": "2025-12-23",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -339,17 +339,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 56.0,
+            "score": 61.8,
             "uncertainty": {
               "standard_error": {
-                "value": 3.0
+                "value": 2.8
               },
               "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 \"II-Agent\" -m \"Gemini 3 Pro\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -366,7 +366,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Letta Code\" -m \"Gemini 3 Pro\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"II-Agent\" -m \"Gemini 3 Pro\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -380,7 +380,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/ante__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",
@@ -404,7 +404,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2026-01-06",
+          "evaluation_timestamp": "2025-11-21",
           "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": 69.4,
+            "score": 56.9,
             "uncertainty": {
               "standard_error": {
-                "value": 2.1
+                "value": 2.5
               },
               "num_samples": 435
             }
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Ante\" -m \"Gemini 3 Pro\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -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 \"Ante\" -m \"Gemini 3 Pro\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"Gemini 3 Pro\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
diff --git a/data/models/google_gemini-3.1-pro.json b/data/models/google_gemini-3.1-pro.json
index d5a56163d0a60a102dbdbef6cd39c4565d8d4e26..ecc327e910f8e4125f6002db506fbf114eb7832a 100644
--- a/data/models/google_gemini-3.1-pro.json
+++ b/data/models/google_gemini-3.1-pro.json
@@ -4,13 +4,13 @@
     "id": "google/gemini-3.1-pro",
     "developer": "Google",
     "additional_details": {
-      "agent_name": "Terminus-KIRA",
-      "agent_organization": "KRAFTON AI"
+      "agent_name": "Forge Code",
+      "agent_organization": "Forge Code"
     }
   },
   "evaluations": [
     {
-      "evaluation_id": "terminal-bench-2.0/terminus-kira__gemini-3.1-pro/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/forge-code__gemini-3.1-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": "2026-03-02",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -43,17 +43,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 74.8,
+            "score": 78.4,
             "uncertainty": {
               "standard_error": {
-                "value": 2.6
+                "value": 1.8
               },
               "num_samples": 435
             }
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus-KIRA\" -m \"Gemini 3.1 Pro\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Forge Code\" -m \"Gemini 3.1 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 \"Terminus-KIRA\" -m \"Gemini 3.1 Pro\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Forge Code\" -m \"Gemini 3.1 Pro\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -84,7 +84,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/forge-code__gemini-3.1-pro/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/terminus-kira__gemini-3.1-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": "2026-03-02",
+          "evaluation_timestamp": "2026-02-23",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -117,17 +117,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 78.4,
+            "score": 74.8,
             "uncertainty": {
               "standard_error": {
-                "value": 1.8
+                "value": 2.6
               },
               "num_samples": 435
             }
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Forge Code\" -m \"Gemini 3.1 Pro\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus-KIRA\" -m \"Gemini 3.1 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 \"Forge Code\" -m \"Gemini 3.1 Pro\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus-KIRA\" -m \"Gemini 3.1 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 6beb736773081d366f65edf05d1bf54bd7e07ce2..3a911939d887cdc9433884fdde5ee11c97c277a4 100644
--- a/data/models/google_gemini_3_flash.json
+++ b/data/models/google_gemini_3_flash.json
@@ -6,6 +6,53 @@
     "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",
@@ -205,53 +252,6 @@
         }
       }
     },
-    {
-      "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-3-27b-it.json b/data/models/google_gemma-3-27b-it.json
index 0d22aa7a55f613493f23d93430a44590b7aa715d..31e90c4548397bec1dec70a558a4830dc0c4f7c9 100644
--- a/data/models/google_gemma-3-27b-it.json
+++ b/data/models/google_gemma-3-27b-it.json
@@ -10,8 +10,8 @@
   },
   "evaluations": [
     {
-      "evaluation_id": "global-mmlu-lite/google_gemma-3-27b-it/1773936583.743359",
-      "retrieved_timestamp": "1773936583.743359",
+      "evaluation_id": "global-mmlu-lite/google_gemma-3-27b-it/1773936496.366405",
+      "retrieved_timestamp": "1773936496.366405",
       "source_metadata": {
         "source_name": "Global MMLU Lite Leaderboard",
         "source_type": "documentation",
@@ -525,8 +525,8 @@
       "generation_config": null
     },
     {
-      "evaluation_id": "global-mmlu-lite/google_gemma-3-27b-it/1773936496.366405",
-      "retrieved_timestamp": "1773936496.366405",
+      "evaluation_id": "global-mmlu-lite/google_gemma-3-27b-it/1773936583.743359",
+      "retrieved_timestamp": "1773936583.743359",
       "source_metadata": {
         "source_name": "Global MMLU Lite Leaderboard",
         "source_type": "documentation",
diff --git a/data/models/gunulhona_gemma-ko-merge-peft.json b/data/models/gunulhona_gemma-ko-merge-peft.json
index 632db743d31cc31d893a565c873ea7be7cc73fb2..7aaca8e76ac4d54a166ddba85afcaa38d76748c4 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": "bfloat16",
+      "precision": "float16",
       "architecture": "?",
       "params_billions": "20.318"
     }
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.288
+            "score": 0.4441
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5154
+            "score": 0.4863
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3247
+            "score": 0.307
           }
         },
         {
@@ -116,7 +116,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.408
+            "score": 0.3986
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3817
+            "score": 0.3098
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4441
+            "score": 0.288
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4863
+            "score": 0.5154
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.307
+            "score": 0.3247
           }
         },
         {
@@ -246,7 +246,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3986
+            "score": 0.408
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3098
+            "score": 0.3817
           }
         }
       ],
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 357f438b07831c53712dd63f870b6b2401c4d681..69bdc21b5b14ca68b6163472e8eef6fd89e268f5 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-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",
@@ -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": 0.5851
-          },
-          "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"
           }
         }
       ],
@@ -159,10 +141,10 @@
       "generation_config": null
     },
     {
-      "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",
@@ -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": 0.7847
+            "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"
           }
         }
       ],
diff --git a/data/models/huggingfacetb_smollm2-360m-instruct.json b/data/models/huggingfacetb_smollm2-360m-instruct.json
index a4edda6b87f3cb7e0eeabaee9333bba91d019d12..b9a479d91c3b9226f2e42a0a5392df69dc01d9df 100644
--- a/data/models/huggingfacetb_smollm2-360m-instruct.json
+++ b/data/models/huggingfacetb_smollm2-360m-instruct.json
@@ -5,9 +5,9 @@
     "developer": "HuggingFaceTB",
     "inference_platform": "unknown",
     "additional_details": {
-      "precision": "float16",
+      "precision": "bfloat16",
       "architecture": "LlamaForCausalLM",
-      "params_billions": "0.362"
+      "params_billions": "0.36"
     }
   },
   "evaluations": [
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.083
+            "score": 0.3842
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3053
+            "score": 0.3144
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0083
+            "score": 0.0151
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2651
+            "score": 0.255
           }
         },
         {
@@ -116,7 +116,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3423
+            "score": 0.3461
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1126
+            "score": 0.1117
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3842
+            "score": 0.083
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3144
+            "score": 0.3053
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0151
+            "score": 0.0083
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.255
+            "score": 0.2651
           }
         },
         {
@@ -246,7 +246,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3461
+            "score": 0.3423
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1117
+            "score": 0.1126
           }
         }
       ],
diff --git a/data/models/infly_inf-orm-llama3.1-70b.json b/data/models/infly_inf-orm-llama3.1-70b.json
index 82e76ad6cd43b3a105b801967d5f616a3924844a..e7947ee940015eb0652da9a52891a9ab47739595 100644
--- a/data/models/infly_inf-orm-llama3.1-70b.json
+++ b/data/models/infly_inf-orm-llama3.1-70b.json
@@ -9,10 +9,10 @@
   },
   "evaluations": [
     {
-      "evaluation_id": "reward-bench/infly_INF-ORM-Llama3.1-70B/1766412838.146816",
+      "evaluation_id": "reward-bench-2/infly_INF-ORM-Llama3.1-70B/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": 0.9511
+            "score": 0.7648
           },
           "source_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": 0.7411
           },
           "source_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": 0.9101
+            "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": "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": 0.9365
+            "score": 0.6995
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Reasoning",
+          "evaluation_name": "Safety",
           "metric_config": {
-            "evaluation_description": "Reasoning accuracy - includes code and math subsets",
+            "evaluation_description": "Safety score - measures safety awareness",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9912
+            "score": 0.9644
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
-        }
-      ],
-      "detailed_evaluation_results": null,
-      "generation_config": null
-    },
-    {
-      "evaluation_id": "reward-bench-2/infly_INF-ORM-Llama3.1-70B/1766412838.146816",
-      "retrieved_timestamp": "1766412838.146816",
-      "source_metadata": {
-        "source_name": "RewardBench 2",
-        "source_type": "documentation",
-        "source_organization_name": "Allen Institute for AI",
-        "source_organization_url": "https://allenai.org",
-        "evaluator_relationship": "third_party"
-      },
-      "eval_library": {
-        "name": "rewardbench",
-        "version": "0.1.3",
-        "additional_details": {
-          "subsets": "Chat, Chat Hard, Safety, Reasoning",
-          "hf_space": "allenai/reward-bench"
-        }
-      },
-      "benchmark": "reward-bench",
-      "evaluation_results": [
+        },
         {
-          "evaluation_name": "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": 0.7648
+            "score": 0.903
           },
           "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": 0.7411
+            "score": 0.8622
           },
           "source_data": {
             "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
             "hf_repo": "allenai/reward-bench-2-results"
           }
-        },
+        }
+      ],
+      "detailed_evaluation_results": null,
+      "generation_config": null
+    },
+    {
+      "evaluation_id": "reward-bench/infly_INF-ORM-Llama3.1-70B/1766412838.146816",
+      "retrieved_timestamp": "1766412838.146816",
+      "source_metadata": {
+        "source_name": "RewardBench",
+        "source_type": "documentation",
+        "source_organization_name": "Allen Institute for AI",
+        "source_organization_url": "https://allenai.org",
+        "evaluator_relationship": "third_party"
+      },
+      "eval_library": {
+        "name": "rewardbench",
+        "version": "0.1.3",
+        "additional_details": {
+          "subsets": "Chat, Chat Hard, Safety, Reasoning",
+          "hf_space": "allenai/reward-bench"
+        }
+      },
+      "benchmark": "reward-bench",
+      "evaluation_results": [
         {
-          "evaluation_name": "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": 0.4188
+            "score": 0.9511
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Math",
+          "evaluation_name": "Chat",
           "metric_config": {
-            "evaluation_description": "Math score - measures mathematical reasoning",
+            "evaluation_description": "Chat accuracy - includes easy chat subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6995
+            "score": 0.9665
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Safety",
+          "evaluation_name": "Chat Hard",
           "metric_config": {
-            "evaluation_description": "Safety score - measures safety awareness",
+            "evaluation_description": "Chat Hard accuracy - includes hard chat subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9644
+            "score": 0.9101
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "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": 0.903
+            "score": 0.9365
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "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": 0.8622
+            "score": 0.9912
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         }
       ],
diff --git a/data/models/internlm_internlm2-1_8b-reward.json b/data/models/internlm_internlm2-1_8b-reward.json
index db02a96edd7d4deec66c9db68ed23c5ecfdc96f9..fdd95af043dae0ccf6943006b6d82bc9a69847ba 100644
--- a/data/models/internlm_internlm2-1_8b-reward.json
+++ b/data/models/internlm_internlm2-1_8b-reward.json
@@ -9,10 +9,10 @@
   },
   "evaluations": [
     {
-      "evaluation_id": "reward-bench/internlm_internlm2-1_8b-reward/1766412838.146816",
+      "evaluation_id": "reward-bench-2/internlm_internlm2-1_8b-reward/1766412838.146816",
       "retrieved_timestamp": "1766412838.146816",
       "source_metadata": {
-        "source_name": "RewardBench",
+        "source_name": "RewardBench 2",
         "source_type": "documentation",
         "source_organization_name": "Allen Institute for AI",
         "source_organization_url": "https://allenai.org",
@@ -31,128 +31,104 @@
         {
           "evaluation_name": "Score",
           "metric_config": {
-            "evaluation_description": "Overall RewardBench Score",
+            "evaluation_description": "Overall RewardBench 2 Score (mean of all metrics)",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.8217
+            "score": 0.3902
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Chat",
+          "evaluation_name": "Factuality",
           "metric_config": {
-            "evaluation_description": "Chat accuracy - includes easy chat subsets",
+            "evaluation_description": "Factuality score - measures factual accuracy",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9358
+            "score": 0.2758
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Chat Hard",
+          "evaluation_name": "Precise IF",
           "metric_config": {
-            "evaluation_description": "Chat Hard accuracy - includes hard chat subsets",
+            "evaluation_description": "Precise Instruction Following score",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6623
+            "score": 0.3625
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Safety",
+          "evaluation_name": "Math",
           "metric_config": {
-            "evaluation_description": "Safety accuracy - includes safety subsets",
+            "evaluation_description": "Math score - measures mathematical reasoning",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.8162
+            "score": 0.4426
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Reasoning",
+          "evaluation_name": "Safety",
           "metric_config": {
-            "evaluation_description": "Reasoning accuracy - includes code and math subsets",
+            "evaluation_description": "Safety score - measures safety awareness",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.8724
+            "score": 0.4711
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
-        }
-      ],
-      "detailed_evaluation_results": null,
-      "generation_config": null
-    },
-    {
-      "evaluation_id": "reward-bench-2/internlm_internlm2-1_8b-reward/1766412838.146816",
-      "retrieved_timestamp": "1766412838.146816",
-      "source_metadata": {
-        "source_name": "RewardBench 2",
-        "source_type": "documentation",
-        "source_organization_name": "Allen Institute for AI",
-        "source_organization_url": "https://allenai.org",
-        "evaluator_relationship": "third_party"
-      },
-      "eval_library": {
-        "name": "rewardbench",
-        "version": "0.1.3",
-        "additional_details": {
-          "subsets": "Chat, Chat Hard, Safety, Reasoning",
-          "hf_space": "allenai/reward-bench"
-        }
-      },
-      "benchmark": "reward-bench",
-      "evaluation_results": [
+        },
         {
-          "evaluation_name": "Score",
+          "evaluation_name": "Focus",
           "metric_config": {
-            "evaluation_description": "Overall RewardBench 2 Score (mean of all metrics)",
+            "evaluation_description": "Focus score - measures response focus",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3902
+            "score": 0.596
           },
           "source_data": {
             "dataset_name": "RewardBench 2",
@@ -161,111 +137,135 @@
           }
         },
         {
-          "evaluation_name": "Factuality",
+          "evaluation_name": "Ties",
           "metric_config": {
-            "evaluation_description": "Factuality score - measures factual accuracy",
+            "evaluation_description": "Ties score - ability to identify tie cases",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2758
+            "score": 0.1934
           },
           "source_data": {
             "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
             "hf_repo": "allenai/reward-bench-2-results"
           }
-        },
+        }
+      ],
+      "detailed_evaluation_results": null,
+      "generation_config": null
+    },
+    {
+      "evaluation_id": "reward-bench/internlm_internlm2-1_8b-reward/1766412838.146816",
+      "retrieved_timestamp": "1766412838.146816",
+      "source_metadata": {
+        "source_name": "RewardBench",
+        "source_type": "documentation",
+        "source_organization_name": "Allen Institute for AI",
+        "source_organization_url": "https://allenai.org",
+        "evaluator_relationship": "third_party"
+      },
+      "eval_library": {
+        "name": "rewardbench",
+        "version": "0.1.3",
+        "additional_details": {
+          "subsets": "Chat, Chat Hard, Safety, Reasoning",
+          "hf_space": "allenai/reward-bench"
+        }
+      },
+      "benchmark": "reward-bench",
+      "evaluation_results": [
         {
-          "evaluation_name": "Precise IF",
+          "evaluation_name": "Score",
           "metric_config": {
-            "evaluation_description": "Precise Instruction Following score",
+            "evaluation_description": "Overall RewardBench Score",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3625
+            "score": 0.8217
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Math",
+          "evaluation_name": "Chat",
           "metric_config": {
-            "evaluation_description": "Math score - measures mathematical reasoning",
+            "evaluation_description": "Chat accuracy - includes easy chat subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4426
+            "score": 0.9358
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Safety",
+          "evaluation_name": "Chat Hard",
           "metric_config": {
-            "evaluation_description": "Safety score - measures safety awareness",
+            "evaluation_description": "Chat Hard accuracy - includes hard chat subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4711
+            "score": 0.6623
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Focus",
+          "evaluation_name": "Safety",
           "metric_config": {
-            "evaluation_description": "Focus score - measures response focus",
+            "evaluation_description": "Safety accuracy - includes safety subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.596
+            "score": 0.8162
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Ties",
+          "evaluation_name": "Reasoning",
           "metric_config": {
-            "evaluation_description": "Ties score - ability to identify tie cases",
+            "evaluation_description": "Reasoning accuracy - includes code and math subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1934
+            "score": 0.8724
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         }
       ],
diff --git a/data/models/internlm_internlm2-20b-reward.json b/data/models/internlm_internlm2-20b-reward.json
index db57bc6ddd293d585b6bca7ac06b0b270dabb864..4de166855af75438b275f87369424e25bd91920e 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-2/internlm_internlm2-20b-reward/1766412838.146816",
+      "evaluation_id": "reward-bench/internlm_internlm2-20b-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": 0.5628
+            "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": "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": 0.5558
+            "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": "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": 0.7654
           },
           "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": "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": 0.5738
+            "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": "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": 0.6111
+            "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"
           }
-        },
+        }
+      ],
+      "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": "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": 0.7253
+            "score": 0.5628
           },
           "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": 0.5483
+            "score": 0.5558
           },
           "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": "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": 0.9016
+            "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": 0.9888
+            "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": "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": 0.7654
+            "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"
           }
         },
         {
-          "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": 0.8946
+            "score": 0.7253
           },
           "source_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": 0.9576
+            "score": 0.5483
           },
           "source_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 4be5b49897aa6863276434fc48c4d6962992c15e..3d8b7bc1575ec467cf84b27d25552c6269300054 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": "float16",
+      "precision": "bfloat16",
       "architecture": "LlamaForCausalLM",
       "params_billions": "8.03"
     }
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2553
+            "score": 0.2477
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4725
+            "score": 0.4758
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0529
+            "score": 0.0453
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2919
+            "score": 0.2911
           }
         },
         {
@@ -116,7 +116,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3654
+            "score": 0.3641
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3316
+            "score": 0.3292
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2477
+            "score": 0.2553
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4758
+            "score": 0.4725
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0453
+            "score": 0.0529
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2911
+            "score": 0.2919
           }
         },
         {
@@ -246,7 +246,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3641
+            "score": 0.3654
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3292
+            "score": 0.3316
           }
         }
       ],
diff --git a/data/models/jaspionjader_kosmos-evaa-fusion-8b.json b/data/models/jaspionjader_kosmos-evaa-fusion-8b.json
index 88cf241ec28671fc887627a1e7bb1af09c15f9cf..1160e36435338576bea29bef2eb39f295798e22d 100644
--- a/data/models/jaspionjader_kosmos-evaa-fusion-8b.json
+++ b/data/models/jaspionjader_kosmos-evaa-fusion-8b.json
@@ -5,7 +5,7 @@
     "developer": "jaspionjader",
     "inference_platform": "unknown",
     "additional_details": {
-      "precision": "float16",
+      "precision": "bfloat16",
       "architecture": "LlamaForCausalLM",
       "params_billions": "8.03"
     }
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4418
+            "score": 0.4345
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5406
+            "score": 0.5419
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1352
+            "score": 0.1292
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3062
+            "score": 0.3087
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.386
+            "score": 0.3854
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4345
+            "score": 0.4418
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5419
+            "score": 0.5406
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1292
+            "score": 0.1352
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3087
+            "score": 0.3062
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3854
+            "score": 0.386
           }
         }
       ],
diff --git a/data/models/kavonalds_bundermaxx-0710.json b/data/models/kavonalds_bundermaxx-0710.json
index 1c392120900a40ecef63990c2ea6f8c3e297a9f1..c6ac0f8a7475b90498abe064315ec79f3f2bd920 100644
--- a/data/models/kavonalds_bundermaxx-0710.json
+++ b/data/models/kavonalds_bundermaxx-0710.json
@@ -5,7 +5,7 @@
     "developer": "kavonalds",
     "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": 0.3283
+            "score": 0.2701
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6651
+            "score": 0.5566
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2609
+            "score": 0.2802
           }
         },
         {
@@ -116,7 +116,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3393
+            "score": 0.3682
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1314
+            "score": 0.1449
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2701
+            "score": 0.3283
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5566
+            "score": 0.6651
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2802
+            "score": 0.2609
           }
         },
         {
@@ -246,7 +246,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3682
+            "score": 0.3393
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1449
+            "score": 0.1314
           }
         }
       ],
diff --git a/data/models/lxzgordon_urm-llama-3.1-8b.json b/data/models/lxzgordon_urm-llama-3.1-8b.json
index 7f03035f2bd809fb14be27130e313f5b86a26f9a..2ce56c90ce0d5fb5788660f5b3f1f1e179701786 100644
--- a/data/models/lxzgordon_urm-llama-3.1-8b.json
+++ b/data/models/lxzgordon_urm-llama-3.1-8b.json
@@ -9,10 +9,10 @@
   },
   "evaluations": [
     {
-      "evaluation_id": "reward-bench-2/LxzGordon_URM-LLaMa-3.1-8B/1766412838.146816",
+      "evaluation_id": "reward-bench/LxzGordon_URM-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": 0.7394
+            "score": 0.9294
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "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": 0.6884
+            "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": "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": 0.45
+            "score": 0.8816
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "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": 0.6393
+            "score": 0.9108
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "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": 0.9178
+            "score": 0.9698
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
-        },
+        }
+      ],
+      "detailed_evaluation_results": null,
+      "generation_config": null
+    },
+    {
+      "evaluation_id": "reward-bench-2/LxzGordon_URM-LLaMa-3.1-8B/1766412838.146816",
+      "retrieved_timestamp": "1766412838.146816",
+      "source_metadata": {
+        "source_name": "RewardBench 2",
+        "source_type": "documentation",
+        "source_organization_name": "Allen Institute for AI",
+        "source_organization_url": "https://allenai.org",
+        "evaluator_relationship": "third_party"
+      },
+      "eval_library": {
+        "name": "rewardbench",
+        "version": "0.1.3",
+        "additional_details": {
+          "subsets": "Chat, Chat Hard, Safety, Reasoning",
+          "hf_space": "allenai/reward-bench"
+        }
+      },
+      "benchmark": "reward-bench",
+      "evaluation_results": [
         {
-          "evaluation_name": "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": 0.9758
+            "score": 0.7394
           },
           "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": 0.7653
+            "score": 0.6884
           },
           "source_data": {
             "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
             "hf_repo": "allenai/reward-bench-2-results"
           }
-        }
-      ],
-      "detailed_evaluation_results": null,
-      "generation_config": null
-    },
-    {
-      "evaluation_id": "reward-bench/LxzGordon_URM-LLaMa-3.1-8B/1766412838.146816",
-      "retrieved_timestamp": "1766412838.146816",
-      "source_metadata": {
-        "source_name": "RewardBench",
-        "source_type": "documentation",
-        "source_organization_name": "Allen Institute for AI",
-        "source_organization_url": "https://allenai.org",
-        "evaluator_relationship": "third_party"
-      },
-      "eval_library": {
-        "name": "rewardbench",
-        "version": "0.1.3",
-        "additional_details": {
-          "subsets": "Chat, Chat Hard, Safety, Reasoning",
-          "hf_space": "allenai/reward-bench"
-        }
-      },
-      "benchmark": "reward-bench",
-      "evaluation_results": [
+        },
         {
-          "evaluation_name": "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": 0.9294
+            "score": 0.45
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "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": 0.9553
+            "score": 0.6393
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "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": 0.8816
+            "score": 0.9178
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "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": 0.9108
+            "score": 0.9758
           },
           "source_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": 0.9698
+            "score": 0.7653
           },
           "source_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/magpie-align_llama-3-8b-magpie-align-v0.1.json b/data/models/magpie-align_llama-3-8b-magpie-align-v0.1.json
index 2ac3bb48cceaf59e0da754702b99c90edec98998..018a3210e6da83ca7e6d3501fd6a7fefdb10449c 100644
--- a/data/models/magpie-align_llama-3-8b-magpie-align-v0.1.json
+++ b/data/models/magpie-align_llama-3-8b-magpie-align-v0.1.json
@@ -5,7 +5,7 @@
     "developer": "Magpie-Align",
     "inference_platform": "unknown",
     "additional_details": {
-      "precision": "float16",
+      "precision": "bfloat16",
       "architecture": "LlamaForCausalLM",
       "params_billions": "8.03"
     }
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4027
+            "score": 0.4118
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4789
+            "score": 0.4811
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0461
+            "score": 0.034
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2768
+            "score": 0.2752
           }
         },
         {
@@ -116,7 +116,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3087
+            "score": 0.3047
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3001
+            "score": 0.3006
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4118
+            "score": 0.4027
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4811
+            "score": 0.4789
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.034
+            "score": 0.0461
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2752
+            "score": 0.2768
           }
         },
         {
@@ -246,7 +246,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3047
+            "score": 0.3087
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3006
+            "score": 0.3001
           }
         }
       ],
diff --git a/data/models/meta-llama_meta-llama-3-8b-instruct.json b/data/models/meta-llama_meta-llama-3-8b-instruct.json
index 7f250b5cb54b80c03e9c7605296b8768c6176139..6b360a3e795c08b36f8a5ae66db62ef8475fd282 100644
--- a/data/models/meta-llama_meta-llama-3-8b-instruct.json
+++ b/data/models/meta-llama_meta-llama-3-8b-instruct.json
@@ -5,7 +5,7 @@
     "developer": "meta-llama",
     "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": 0.7408
+            "score": 0.4782
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4989
+            "score": 0.491
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0869
+            "score": 0.0914
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2592
+            "score": 0.2928
           }
         },
         {
@@ -116,7 +116,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3568
+            "score": 0.3805
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3664
+            "score": 0.3591
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4782
+            "score": 0.7408
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.491
+            "score": 0.4989
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0914
+            "score": 0.0869
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2928
+            "score": 0.2592
           }
         },
         {
@@ -246,7 +246,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3805
+            "score": 0.3568
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3591
+            "score": 0.3664
           }
         }
       ],
diff --git a/data/models/mistralai_mistral-small-2503.json b/data/models/mistralai_mistral-small-2503.json
index be5d73de7278abb3c747dbebd44b60d3fa624503..6df0d972b005ae32b060fdc4673d6092e770670f 100644
--- a/data/models/mistralai_mistral-small-2503.json
+++ b/data/models/mistralai_mistral-small-2503.json
@@ -10,8 +10,8 @@
   },
   "evaluations": [
     {
-      "evaluation_id": "global-mmlu-lite/mistralai_mistral-small-2503/1773936496.366405",
-      "retrieved_timestamp": "1773936496.366405",
+      "evaluation_id": "global-mmlu-lite/mistralai_mistral-small-2503/1773936583.743359",
+      "retrieved_timestamp": "1773936583.743359",
       "source_metadata": {
         "source_name": "Global MMLU Lite Leaderboard",
         "source_type": "documentation",
@@ -525,8 +525,8 @@
       "generation_config": null
     },
     {
-      "evaluation_id": "global-mmlu-lite/mistralai_mistral-small-2503/1773936583.743359",
-      "retrieved_timestamp": "1773936583.743359",
+      "evaluation_id": "global-mmlu-lite/mistralai_mistral-small-2503/1773936496.366405",
+      "retrieved_timestamp": "1773936496.366405",
       "source_metadata": {
         "source_name": "Global MMLU Lite Leaderboard",
         "source_type": "documentation",
diff --git a/data/models/mistralai_mistral-small-instruct-2409.json b/data/models/mistralai_mistral-small-instruct-2409.json
index 02a04ce41b1de063befb30b7d94d3ad197cffb0e..5aac65e94f46e67333b7cb66dd77ae7f5415d17b 100644
--- a/data/models/mistralai_mistral-small-instruct-2409.json
+++ b/data/models/mistralai_mistral-small-instruct-2409.json
@@ -5,9 +5,9 @@
     "developer": "mistralai",
     "inference_platform": "unknown",
     "additional_details": {
-      "precision": "bfloat16",
+      "precision": "float16",
       "architecture": "MistralForCausalLM",
-      "params_billions": "22.05"
+      "params_billions": "22.247"
     }
   },
   "evaluations": [
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.667
+            "score": 0.6283
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5213
+            "score": 0.583
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1435
+            "score": 0.2039
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3238
+            "score": 0.3331
           }
         },
         {
@@ -116,7 +116,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3632
+            "score": 0.4063
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.396
+            "score": 0.4099
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6283
+            "score": 0.667
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.583
+            "score": 0.5213
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2039
+            "score": 0.1435
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3331
+            "score": 0.3238
           }
         },
         {
@@ -246,7 +246,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4063
+            "score": 0.3632
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4099
+            "score": 0.396
           }
         }
       ],
diff --git a/data/models/mlabonne_neuraldaredevil-8b-abliterated.json b/data/models/mlabonne_neuraldaredevil-8b-abliterated.json
index 7ef165972eafdeec56d923c82e02fdbbc9479eac..d443de39bb7ed82b00df80190432e583c21fd660 100644
--- a/data/models/mlabonne_neuraldaredevil-8b-abliterated.json
+++ b/data/models/mlabonne_neuraldaredevil-8b-abliterated.json
@@ -5,7 +5,7 @@
     "developer": "mlabonne",
     "inference_platform": "unknown",
     "additional_details": {
-      "precision": "bfloat16",
+      "precision": "float16",
       "architecture": "LlamaForCausalLM",
       "params_billions": "8.03"
     }
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4162
+            "score": 0.7561
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5124
+            "score": 0.5111
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0853
+            "score": 0.0906
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3029
+            "score": 0.3062
           }
         },
         {
@@ -116,7 +116,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.415
+            "score": 0.4019
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3802
+            "score": 0.3841
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7561
+            "score": 0.4162
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5111
+            "score": 0.5124
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0906
+            "score": 0.0853
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3062
+            "score": 0.3029
           }
         },
         {
@@ -246,7 +246,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4019
+            "score": 0.415
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3841
+            "score": 0.3802
           }
         }
       ],
diff --git a/data/models/moonshot-ai_kimi-k2-instruct.json b/data/models/moonshot-ai_kimi-k2-instruct.json
index 2cfded0145e5c6821159f45b392f6b86e15c7f49..758984500ae56b028445a56fb8562c74a90a3a8f 100644
--- a/data/models/moonshot-ai_kimi-k2-instruct.json
+++ b/data/models/moonshot-ai_kimi-k2-instruct.json
@@ -4,13 +4,13 @@
     "id": "moonshot-ai/kimi-k2-instruct",
     "developer": "Moonshot AI",
     "additional_details": {
-      "agent_name": "Terminus 2",
-      "agent_organization": "Terminal Bench"
+      "agent_name": "OpenHands",
+      "agent_organization": "OpenHands"
     }
   },
   "evaluations": [
     {
-      "evaluation_id": "terminal-bench-2.0/terminus-2__kimi-k2-instruct/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/openhands__kimi-k2-instruct/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -34,7 +34,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-11-01",
+          "evaluation_timestamp": "2025-11-02",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -43,17 +43,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 27.8,
+            "score": 26.7,
             "uncertainty": {
               "standard_error": {
-                "value": 2.5
+                "value": 2.7
               },
               "num_samples": 435
             }
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"Kimi K2 Instruct\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"OpenHands\" -m \"Kimi K2 Instruct\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -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 \"Kimi K2 Instruct\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"OpenHands\" -m \"Kimi K2 Instruct\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -84,7 +84,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/openhands__kimi-k2-instruct/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/terminus-2__kimi-k2-instruct/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -108,7 +108,7 @@
               "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,
@@ -117,17 +117,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 26.7,
+            "score": 27.8,
             "uncertainty": {
               "standard_error": {
-                "value": 2.7
+                "value": 2.5
               },
               "num_samples": 435
             }
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"OpenHands\" -m \"Kimi K2 Instruct\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"Kimi K2 Instruct\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -144,7 +144,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"OpenHands\" -m \"Kimi K2 Instruct\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"Kimi K2 Instruct\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
diff --git a/data/models/multiple_multiple.json b/data/models/multiple_multiple.json
index 01b06a48bec6c0ec600ef83ad482f6552d46d980..45d5496f95937f9e2416eacde936df0b731a4892 100644
--- a/data/models/multiple_multiple.json
+++ b/data/models/multiple_multiple.json
@@ -34,7 +34,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-12-12",
+          "evaluation_timestamp": "2025-11-20",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -43,10 +43,10 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 61.2,
+            "score": 59.1,
             "uncertainty": {
               "standard_error": {
-                "value": 3.0
+                "value": 2.8
               },
               "num_samples": 435
             }
@@ -84,7 +84,7 @@
       }
     },
     {
-      "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",
@@ -108,7 +108,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-11-20",
+          "evaluation_timestamp": "2026-03-07",
           "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": 59.1,
+            "score": 71.0,
             "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 \"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": [
                   {
@@ -144,7 +144,7 @@
       "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": [
               {
@@ -158,7 +158,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/ob-1__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",
@@ -182,7 +182,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2026-03-05",
+          "evaluation_timestamp": "2025-11-11",
           "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": 72.4,
+            "score": 50.1,
             "uncertainty": {
               "standard_error": {
-                "value": 2.3
+                "value": 2.7
               },
               "num_samples": 435
             }
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"OB-1\" -m \"Multiple\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Warp\" -m \"Multiple\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -218,7 +218,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"OB-1\" -m \"Multiple\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Warp\" -m \"Multiple\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -232,7 +232,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/warp__multiple/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/abacus-ai-desktop__multiple/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -256,7 +256,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-11-11",
+          "evaluation_timestamp": "2025-12-11",
           "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": 50.1,
+            "score": 58.4,
             "uncertainty": {
               "standard_error": {
-                "value": 2.7
+                "value": 2.8
               },
               "num_samples": 435
             }
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Warp\" -m \"Multiple\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Abacus AI Desktop\" -m \"Multiple\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -292,7 +292,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Warp\" -m \"Multiple\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Abacus AI Desktop\" -m \"Multiple\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -306,7 +306,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/junie-cli__multiple/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/warp__multiple/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -330,7 +330,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2026-03-07",
+          "evaluation_timestamp": "2025-12-12",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -339,17 +339,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 71.0,
+            "score": 61.2,
             "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 \"Junie CLI\" -m \"Multiple\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Warp\" -m \"Multiple\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -366,7 +366,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Junie CLI\" -m \"Multiple\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Warp\" -m \"Multiple\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -380,7 +380,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/abacus-ai-desktop__multiple/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/ob-1__multiple/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -404,7 +404,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-12-11",
+          "evaluation_timestamp": "2026-03-05",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -413,17 +413,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 58.4,
+            "score": 72.4,
             "uncertainty": {
               "standard_error": {
-                "value": 2.8
+                "value": 2.3
               },
               "num_samples": 435
             }
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Abacus AI Desktop\" -m \"Multiple\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"OB-1\" -m \"Multiple\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -440,7 +440,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Abacus AI Desktop\" -m \"Multiple\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"OB-1\" -m \"Multiple\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
diff --git a/data/models/ncsoft_llama-3-offsetbias-rm-8b.json b/data/models/ncsoft_llama-3-offsetbias-rm-8b.json
index 14fabae93f5ca8f04e2a0c2d895536cd5cdfcb3a..0a839fbe35d3881341976e6cd6ecdba200fd0827 100644
--- a/data/models/ncsoft_llama-3-offsetbias-rm-8b.json
+++ b/data/models/ncsoft_llama-3-offsetbias-rm-8b.json
@@ -9,10 +9,10 @@
   },
   "evaluations": [
     {
-      "evaluation_id": "reward-bench-2/NCSOFT_Llama-3-OffsetBias-RM-8B/1766412838.146816",
+      "evaluation_id": "reward-bench/NCSOFT_Llama-3-OffsetBias-RM-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": 0.648
+            "score": 0.8942
           },
           "source_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": 0.6084
+            "score": 0.9721
           },
           "source_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": 0.818
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Math",
+          "evaluation_name": "Safety",
           "metric_config": {
-            "evaluation_description": "Math score - measures mathematical reasoning",
+            "evaluation_description": "Safety accuracy - includes safety subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5191
+            "score": 0.8676
           },
           "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": "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": 0.7222
+            "score": 0.9192
           },
           "source_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/NCSOFT_Llama-3-OffsetBias-RM-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": 0.9596
+            "score": 0.648
           },
           "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": 0.6786
+            "score": 0.6084
           },
           "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/NCSOFT_Llama-3-OffsetBias-RM-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": 0.8942
+            "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": 0.9721
+            "score": 0.5191
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Chat Hard",
+          "evaluation_name": "Safety",
           "metric_config": {
-            "evaluation_description": "Chat Hard accuracy - includes hard chat subsets",
+            "evaluation_description": "Safety score - measures safety awareness",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.818
+            "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": "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": 0.8676
+            "score": 0.9596
           },
           "source_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": 0.9192
+            "score": 0.6786
           },
           "source_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/nexusflow_starling-rm-34b.json b/data/models/nexusflow_starling-rm-34b.json
index 0373bd963cc9795a2ad38fc9da30f8417d64ff6d..8ab4f392fbf3047e7bcb88c6ed9f3a2b6d8e5a37 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/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",
@@ -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": 0.8133
+            "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"
           }
         }
       ],
@@ -141,10 +159,10 @@
       "generation_config": null
     },
     {
-      "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",
@@ -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": 0.4553
-          },
-          "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"
           }
         }
       ],
diff --git a/data/models/ontocord_wide_3b_sft_stage1.1-ss1-with_generics_intr_math_stories.no_issue.json b/data/models/ontocord_wide_3b_sft_stage1.1-ss1-with_generics_intr_math_stories.no_issue.json
index 486ba5e61208261c68f73d7d2bf88d78b1b36131..f86ab61b521749eb0f8fa030a3c29f5a32d327a1 100644
--- a/data/models/ontocord_wide_3b_sft_stage1.1-ss1-with_generics_intr_math_stories.no_issue.json
+++ b/data/models/ontocord_wide_3b_sft_stage1.1-ss1-with_generics_intr_math_stories.no_issue.json
@@ -5,7 +5,7 @@
     "developer": "ontocord",
     "inference_platform": "unknown",
     "additional_details": {
-      "precision": "bfloat16",
+      "precision": "float16",
       "architecture": "Qwen2ForCausalLM",
       "params_billions": "3.759"
     }
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1128
+            "score": 0.1162
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3171
+            "score": 0.3184
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0113
+            "score": 0.0076
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2685
+            "score": 0.2634
           }
         },
         {
@@ -116,7 +116,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.346
+            "score": 0.3447
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1129
+            "score": 0.1124
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1162
+            "score": 0.1128
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3184
+            "score": 0.3171
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0076
+            "score": 0.0113
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2634
+            "score": 0.2685
           }
         },
         {
@@ -246,7 +246,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3447
+            "score": 0.346
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1124
+            "score": 0.1129
           }
         }
       ],
diff --git a/data/models/openai_gpt-4o-2024-08-06.json b/data/models/openai_gpt-4o-2024-08-06.json
index ca15abfce433f9cf3b132cc5fefadfcef719867a..4523783fb76c33e56985cf8706dfcde93c76d009 100644
--- a/data/models/openai_gpt-4o-2024-08-06.json
+++ b/data/models/openai_gpt-4o-2024-08-06.json
@@ -1900,10 +1900,10 @@
       }
     },
     {
-      "evaluation_id": "reward-bench-2/openai_gpt-4o-2024-08-06/1766412838.146816",
+      "evaluation_id": "reward-bench/openai_gpt-4o-2024-08-06/1766412838.146816",
       "retrieved_timestamp": "1766412838.146816",
       "source_metadata": {
-        "source_name": "RewardBench 2",
+        "source_name": "RewardBench",
         "source_type": "documentation",
         "source_organization_name": "Allen Institute for AI",
         "source_organization_url": "https://allenai.org",
@@ -1922,104 +1922,128 @@
         {
           "evaluation_name": "Score",
           "metric_config": {
-            "evaluation_description": "Overall RewardBench 2 Score (mean of all metrics)",
+            "evaluation_description": "Overall RewardBench Score",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6493
+            "score": 0.8673
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Factuality",
+          "evaluation_name": "Chat",
           "metric_config": {
-            "evaluation_description": "Factuality score - measures factual accuracy",
+            "evaluation_description": "Chat accuracy - includes easy chat subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5684
+            "score": 0.9609
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Precise IF",
+          "evaluation_name": "Chat Hard",
           "metric_config": {
-            "evaluation_description": "Precise Instruction Following score",
+            "evaluation_description": "Chat Hard accuracy - includes hard chat subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3312
+            "score": 0.761
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Math",
+          "evaluation_name": "Safety",
           "metric_config": {
-            "evaluation_description": "Math score - measures mathematical reasoning",
+            "evaluation_description": "Safety accuracy - includes safety subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.623
+            "score": 0.8811
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Safety",
+          "evaluation_name": "Reasoning",
           "metric_config": {
-            "evaluation_description": "Safety score - measures safety awareness",
+            "evaluation_description": "Reasoning accuracy - includes code and math subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.8619
+            "score": 0.8661
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
-        },
+        }
+      ],
+      "detailed_evaluation_results": null,
+      "generation_config": null
+    },
+    {
+      "evaluation_id": "reward-bench-2/openai_gpt-4o-2024-08-06/1766412838.146816",
+      "retrieved_timestamp": "1766412838.146816",
+      "source_metadata": {
+        "source_name": "RewardBench 2",
+        "source_type": "documentation",
+        "source_organization_name": "Allen Institute for AI",
+        "source_organization_url": "https://allenai.org",
+        "evaluator_relationship": "third_party"
+      },
+      "eval_library": {
+        "name": "rewardbench",
+        "version": "0.1.3",
+        "additional_details": {
+          "subsets": "Chat, Chat Hard, Safety, Reasoning",
+          "hf_space": "allenai/reward-bench"
+        }
+      },
+      "benchmark": "reward-bench",
+      "evaluation_results": [
         {
-          "evaluation_name": "Focus",
+          "evaluation_name": "Score",
           "metric_config": {
-            "evaluation_description": "Focus score - measures response focus",
+            "evaluation_description": "Overall RewardBench 2 Score (mean of all metrics)",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7293
+            "score": 0.6493
           },
           "source_data": {
             "dataset_name": "RewardBench 2",
@@ -2028,135 +2052,111 @@
           }
         },
         {
-          "evaluation_name": "Ties",
+          "evaluation_name": "Factuality",
           "metric_config": {
-            "evaluation_description": "Ties score - ability to identify tie cases",
+            "evaluation_description": "Factuality score - measures factual accuracy",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7819
+            "score": 0.5684
           },
           "source_data": {
             "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
             "hf_repo": "allenai/reward-bench-2-results"
           }
-        }
-      ],
-      "detailed_evaluation_results": null,
-      "generation_config": null
-    },
-    {
-      "evaluation_id": "reward-bench/openai_gpt-4o-2024-08-06/1766412838.146816",
-      "retrieved_timestamp": "1766412838.146816",
-      "source_metadata": {
-        "source_name": "RewardBench",
-        "source_type": "documentation",
-        "source_organization_name": "Allen Institute for AI",
-        "source_organization_url": "https://allenai.org",
-        "evaluator_relationship": "third_party"
-      },
-      "eval_library": {
-        "name": "rewardbench",
-        "version": "0.1.3",
-        "additional_details": {
-          "subsets": "Chat, Chat Hard, Safety, Reasoning",
-          "hf_space": "allenai/reward-bench"
-        }
-      },
-      "benchmark": "reward-bench",
-      "evaluation_results": [
+        },
         {
-          "evaluation_name": "Score",
+          "evaluation_name": "Precise IF",
           "metric_config": {
-            "evaluation_description": "Overall RewardBench Score",
+            "evaluation_description": "Precise Instruction Following score",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.8673
+            "score": 0.3312
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Chat",
+          "evaluation_name": "Math",
           "metric_config": {
-            "evaluation_description": "Chat accuracy - includes easy chat subsets",
+            "evaluation_description": "Math score - measures mathematical reasoning",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9609
+            "score": 0.623
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Chat Hard",
+          "evaluation_name": "Safety",
           "metric_config": {
-            "evaluation_description": "Chat Hard accuracy - includes hard chat subsets",
+            "evaluation_description": "Safety score - measures safety awareness",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.761
+            "score": 0.8619
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Safety",
+          "evaluation_name": "Focus",
           "metric_config": {
-            "evaluation_description": "Safety accuracy - includes safety subsets",
+            "evaluation_description": "Focus score - measures response focus",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.8811
+            "score": 0.7293
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Reasoning",
+          "evaluation_name": "Ties",
           "metric_config": {
-            "evaluation_description": "Reasoning accuracy - includes code and math subsets",
+            "evaluation_description": "Ties score - ability to identify tie cases",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.8661
+            "score": 0.7819
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         }
       ],
diff --git a/data/models/openai_gpt-4o-mini-2024-07-18.json b/data/models/openai_gpt-4o-mini-2024-07-18.json
index 1b3fb4c30102ee1f603e3640bb4c4b14c38b8cac..f38f4e1ddedf08dfff3e3ceeb97aeebb3dcce913 100644
--- a/data/models/openai_gpt-4o-mini-2024-07-18.json
+++ b/data/models/openai_gpt-4o-mini-2024-07-18.json
@@ -2124,10 +2124,10 @@
       }
     },
     {
-      "evaluation_id": "reward-bench-2/openai_gpt-4o-mini-2024-07-18/1766412838.146816",
+      "evaluation_id": "reward-bench/openai_gpt-4o-mini-2024-07-18/1766412838.146816",
       "retrieved_timestamp": "1766412838.146816",
       "source_metadata": {
-        "source_name": "RewardBench 2",
+        "source_name": "RewardBench",
         "source_type": "documentation",
         "source_organization_name": "Allen Institute for AI",
         "source_organization_url": "https://allenai.org",
@@ -2146,104 +2146,128 @@
         {
           "evaluation_name": "Score",
           "metric_config": {
-            "evaluation_description": "Overall RewardBench 2 Score (mean of all metrics)",
+            "evaluation_description": "Overall RewardBench Score",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5796
+            "score": 0.8007
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Factuality",
+          "evaluation_name": "Chat",
           "metric_config": {
-            "evaluation_description": "Factuality score - measures factual accuracy",
+            "evaluation_description": "Chat accuracy - includes easy chat subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4105
+            "score": 0.9497
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Precise IF",
+          "evaluation_name": "Chat Hard",
           "metric_config": {
-            "evaluation_description": "Precise Instruction Following score",
+            "evaluation_description": "Chat Hard accuracy - includes hard chat subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3438
+            "score": 0.6075
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Math",
+          "evaluation_name": "Safety",
           "metric_config": {
-            "evaluation_description": "Math score - measures mathematical reasoning",
+            "evaluation_description": "Safety accuracy - includes safety subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5191
+            "score": 0.8081
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Safety",
+          "evaluation_name": "Reasoning",
           "metric_config": {
-            "evaluation_description": "Safety score - measures safety awareness",
+            "evaluation_description": "Reasoning accuracy - includes code and math subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7667
+            "score": 0.8374
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
-        },
+        }
+      ],
+      "detailed_evaluation_results": null,
+      "generation_config": null
+    },
+    {
+      "evaluation_id": "reward-bench-2/openai_gpt-4o-mini-2024-07-18/1766412838.146816",
+      "retrieved_timestamp": "1766412838.146816",
+      "source_metadata": {
+        "source_name": "RewardBench 2",
+        "source_type": "documentation",
+        "source_organization_name": "Allen Institute for AI",
+        "source_organization_url": "https://allenai.org",
+        "evaluator_relationship": "third_party"
+      },
+      "eval_library": {
+        "name": "rewardbench",
+        "version": "0.1.3",
+        "additional_details": {
+          "subsets": "Chat, Chat Hard, Safety, Reasoning",
+          "hf_space": "allenai/reward-bench"
+        }
+      },
+      "benchmark": "reward-bench",
+      "evaluation_results": [
         {
-          "evaluation_name": "Focus",
+          "evaluation_name": "Score",
           "metric_config": {
-            "evaluation_description": "Focus score - measures response focus",
+            "evaluation_description": "Overall RewardBench 2 Score (mean of all metrics)",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7414
+            "score": 0.5796
           },
           "source_data": {
             "dataset_name": "RewardBench 2",
@@ -2252,135 +2276,111 @@
           }
         },
         {
-          "evaluation_name": "Ties",
+          "evaluation_name": "Factuality",
           "metric_config": {
-            "evaluation_description": "Ties score - ability to identify tie cases",
+            "evaluation_description": "Factuality score - measures factual accuracy",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6962
+            "score": 0.4105
           },
           "source_data": {
             "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
             "hf_repo": "allenai/reward-bench-2-results"
           }
-        }
-      ],
-      "detailed_evaluation_results": null,
-      "generation_config": null
-    },
-    {
-      "evaluation_id": "reward-bench/openai_gpt-4o-mini-2024-07-18/1766412838.146816",
-      "retrieved_timestamp": "1766412838.146816",
-      "source_metadata": {
-        "source_name": "RewardBench",
-        "source_type": "documentation",
-        "source_organization_name": "Allen Institute for AI",
-        "source_organization_url": "https://allenai.org",
-        "evaluator_relationship": "third_party"
-      },
-      "eval_library": {
-        "name": "rewardbench",
-        "version": "0.1.3",
-        "additional_details": {
-          "subsets": "Chat, Chat Hard, Safety, Reasoning",
-          "hf_space": "allenai/reward-bench"
-        }
-      },
-      "benchmark": "reward-bench",
-      "evaluation_results": [
+        },
         {
-          "evaluation_name": "Score",
+          "evaluation_name": "Precise IF",
           "metric_config": {
-            "evaluation_description": "Overall RewardBench Score",
+            "evaluation_description": "Precise Instruction Following score",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.8007
+            "score": 0.3438
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Chat",
+          "evaluation_name": "Math",
           "metric_config": {
-            "evaluation_description": "Chat accuracy - includes easy chat subsets",
+            "evaluation_description": "Math score - measures mathematical reasoning",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9497
+            "score": 0.5191
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Chat Hard",
+          "evaluation_name": "Safety",
           "metric_config": {
-            "evaluation_description": "Chat Hard accuracy - includes hard chat subsets",
+            "evaluation_description": "Safety score - measures safety awareness",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6075
+            "score": 0.7667
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Safety",
+          "evaluation_name": "Focus",
           "metric_config": {
-            "evaluation_description": "Safety accuracy - includes safety subsets",
+            "evaluation_description": "Focus score - measures response focus",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.8081
+            "score": 0.7414
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Reasoning",
+          "evaluation_name": "Ties",
           "metric_config": {
-            "evaluation_description": "Reasoning accuracy - includes code and math subsets",
+            "evaluation_description": "Ties score - ability to identify tie cases",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.8374
+            "score": 0.6962
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         }
       ],
diff --git a/data/models/openai_gpt-5-2025-08-07.json b/data/models/openai_gpt-5-2025-08-07.json
index fdb97ce4111978e08938be252c1bd72645c11969..0853492fcc4bbd45f07185718454686350fe1be2 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-5-2025-08-07/1773936583.743359",
-      "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",
@@ -525,8 +525,8 @@
       "generation_config": null
     },
     {
-      "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",
diff --git a/data/models/openai_gpt-5-codex.json b/data/models/openai_gpt-5-codex.json
index bfb9d809d90faf4023c720a69d517cc43ddb6092..21a2358b27ce78cb6bd659dfe0536dac012c1818 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": "Terminus 2",
-      "agent_organization": "Terminal Bench"
+      "agent_name": "Mini-SWE-Agent",
+      "agent_organization": "Princeton"
     }
   },
   "evaluations": [
     {
-      "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",
@@ -34,7 +34,7 @@
               "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,
@@ -43,17 +43,17 @@
             "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": [
                   {
@@ -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-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": [
               {
@@ -158,7 +158,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/mini-swe-agent__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",
@@ -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": 41.3,
+            "score": 43.4,
             "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 \"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": [
                   {
@@ -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-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": [
               {
diff --git a/data/models/openai_gpt-5-mini.json b/data/models/openai_gpt-5-mini.json
index c2da3f31323642732ef7d6d76ecea92f3ae2ea0b..a9c814071acbfdd08e7ec7cb2178b705e66b8da6 100644
--- a/data/models/openai_gpt-5-mini.json
+++ b/data/models/openai_gpt-5-mini.json
@@ -4,13 +4,13 @@
     "id": "openai/gpt-5-mini",
     "developer": "OpenAI",
     "additional_details": {
-      "agent_name": "Codex CLI",
-      "agent_organization": "OpenAI"
+      "agent_name": "OpenHands",
+      "agent_organization": "OpenHands"
     }
   },
   "evaluations": [
     {
-      "evaluation_id": "terminal-bench-2.0/codex-cli__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",
@@ -34,7 +34,7 @@
               "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,
@@ -43,17 +43,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 31.9,
+            "score": 29.2,
             "uncertainty": {
               "standard_error": {
-                "value": 3.0
+                "value": 2.8
               },
               "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 \"OpenHands\" -m \"GPT-5-Mini\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -70,7 +70,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Codex CLI\" -m \"GPT-5-Mini\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"OpenHands\" -m \"GPT-5-Mini\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -84,7 +84,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/openhands__gpt-5-mini/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/codex-cli__gpt-5-mini/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -108,7 +108,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-11-02",
+          "evaluation_timestamp": "2025-11-04",
           "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": 29.2,
+            "score": 31.9,
             "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 \"OpenHands\" -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": [
                   {
@@ -144,7 +144,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"OpenHands\" -m \"GPT-5-Mini\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Codex CLI\" -m \"GPT-5-Mini\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -232,7 +232,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/spoox-m__gpt-5-mini/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/mini-swe-agent__gpt-5-mini/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -256,7 +256,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-12-24",
+          "evaluation_timestamp": "2025-11-03",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -265,17 +265,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 34.8,
+            "score": 22.2,
             "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 \"spoox-m\" -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": [
                   {
@@ -292,7 +292,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"spoox-m\" -m \"GPT-5-Mini\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Mini-SWE-Agent\" -m \"GPT-5-Mini\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -306,7 +306,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/mini-swe-agent__gpt-5-mini/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/spoox-m__gpt-5-mini/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -330,7 +330,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-11-03",
+          "evaluation_timestamp": "2025-12-24",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -339,17 +339,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 22.2,
+            "score": 34.8,
             "uncertainty": {
               "standard_error": {
-                "value": 2.6
+                "value": 2.7
               },
               "num_samples": 435
             }
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Mini-SWE-Agent\" -m \"GPT-5-Mini\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"spoox-m\" -m \"GPT-5-Mini\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -366,7 +366,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Mini-SWE-Agent\" -m \"GPT-5-Mini\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"spoox-m\" -m \"GPT-5-Mini\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
diff --git a/data/models/openai_gpt-5-nano.json b/data/models/openai_gpt-5-nano.json
index 17031b27e97ab53bd889b020db9c4f3335b70c14..0d64dfdab152e442151bbf86365c72d39472c605 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": "Mini-SWE-Agent",
-      "agent_organization": "Princeton"
+      "agent_name": "OpenHands",
+      "agent_organization": "OpenHands"
     }
   },
   "evaluations": [
     {
-      "evaluation_id": "terminal-bench-2.0/mini-swe-agent__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",
@@ -34,7 +34,7 @@
               "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,
@@ -43,17 +43,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 7.0,
+            "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 \"Mini-SWE-Agent\" -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": [
                   {
@@ -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-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": [
               {
@@ -84,7 +84,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/openhands__gpt-5-nano/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/codex-cli__gpt-5-nano/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -108,7 +108,7 @@
               "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,
@@ -117,17 +117,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 9.9,
+            "score": 11.5,
             "uncertainty": {
               "standard_error": {
-                "value": 2.1
+                "value": 2.3
               },
               "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 \"Codex CLI\" -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 \"OpenHands\" -m \"GPT-5-Nano\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Codex CLI\" -m \"GPT-5-Nano\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -158,7 +158,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/codex-cli__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",
@@ -182,7 +182,7 @@
               "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,
@@ -191,17 +191,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 11.5,
+            "score": 7.9,
             "uncertainty": {
               "standard_error": {
-                "value": 2.3
+                "value": 1.9
               },
               "num_samples": 435
             }
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Codex CLI\" -m \"GPT-5-Nano\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"GPT-5-Nano\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -218,7 +218,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Codex CLI\" -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": [
               {
@@ -232,7 +232,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/terminus-2__gpt-5-nano/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/mini-swe-agent__gpt-5-nano/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -256,7 +256,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-10-31",
+          "evaluation_timestamp": "2025-11-03",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -265,7 +265,7 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 7.9,
+            "score": 7.0,
             "uncertainty": {
               "standard_error": {
                 "value": 1.9
@@ -275,7 +275,7 @@
           },
           "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 \"Mini-SWE-Agent\" -m \"GPT-5-Nano\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -292,7 +292,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"GPT-5-Nano\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Mini-SWE-Agent\" -m \"GPT-5-Nano\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
diff --git a/data/models/openai_gpt-5.1-codex.json b/data/models/openai_gpt-5.1-codex.json
index d4b36a19fcc7086223ae8f218d54f2b1a6ca0184..5ac777453649e155d2cf4ca5c0edb4c1fb8d16a4 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": "Crux",
-      "agent_organization": "Roam"
+      "agent_name": "Terminus 2",
+      "agent_organization": "Terminal Bench"
     }
   },
   "evaluations": [
     {
-      "evaluation_id": "terminal-bench-2.0/crux__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",
@@ -34,7 +34,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-11-16",
+          "evaluation_timestamp": "2025-11-17",
           "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": 57.8,
+            "score": 36.9,
             "uncertainty": {
               "standard_error": {
-                "value": 2.9
+                "value": 3.2
               },
               "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 \"Terminus 2\" -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 \"Crux\" -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": [
               {
@@ -84,7 +84,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/letta-code__gpt-5.1-codex/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/crux__gpt-5.1-codex/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -108,7 +108,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-12-17",
+          "evaluation_timestamp": "2025-11-16",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -117,17 +117,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 53.5,
+            "score": 57.8,
             "uncertainty": {
               "standard_error": {
-                "value": 2.8
+                "value": 2.9
               },
               "num_samples": 435
             }
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Letta Code\" -m \"GPT-5.1-Codex\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Crux\" -m \"GPT-5.1-Codex\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -144,7 +144,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Letta Code\" -m \"GPT-5.1-Codex\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Crux\" -m \"GPT-5.1-Codex\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -158,7 +158,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/terminus-2__gpt-5.1-codex/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/letta-code__gpt-5.1-codex/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -182,7 +182,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-11-17",
+          "evaluation_timestamp": "2025-12-17",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -191,17 +191,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 36.9,
+            "score": 53.5,
             "uncertainty": {
               "standard_error": {
-                "value": 3.2
+                "value": 2.8
               },
               "num_samples": 435
             }
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"GPT-5.1-Codex\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Letta Code\" -m \"GPT-5.1-Codex\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -218,7 +218,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"GPT-5.1-Codex\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Letta Code\" -m \"GPT-5.1-Codex\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
diff --git a/data/models/openai_gpt-5.2-2025-12-11.json b/data/models/openai_gpt-5.2-2025-12-11.json
index 296a87eb83719a9fcbce40e624e36b0e1264dcb7..b1415af8e1fa1580e027129e48746b8a6ec316b5 100644
--- a/data/models/openai_gpt-5.2-2025-12-11.json
+++ b/data/models/openai_gpt-5.2-2025-12-11.json
@@ -4,13 +4,13 @@
     "id": "openai/gpt-5.2-2025-12-11",
     "developer": "OpenAI",
     "additional_details": {
-      "agent_name": "SmolAgents Code",
-      "agent_framework": "smolagents_code"
+      "agent_name": "LiteLLM Tool Calling with Shortlisting",
+      "agent_framework": "tool_calling_with_shortlisting"
     }
   },
   "evaluations": [
     {
-      "evaluation_id": "appworld/test_normal/smolagents-code__openai_gpt-5.2-2025-12-11/1774263615.0201504",
+      "evaluation_id": "appworld/test_normal/litellm-tool-calling-with-shortlisting__openai_gpt-5.2-2025-12-11/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -42,23 +42,23 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.071,
+            "score": 0.22,
             "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": "0.36",
+              "total_run_cost": "36.37",
+              "average_steps": "10.05",
+              "percent_finished": "1.0"
             }
           },
           "generation_config": {
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "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__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",
@@ -125,8 +125,8 @@
             "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"
                 }
               }
             }
@@ -138,15 +138,15 @@
         "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/litellm-tool-calling-with-shortlisting__openai_gpt-5.2-2025-12-11/1774263615.0201504",
+      "evaluation_id": "appworld/test_normal/litellm-tool-calling__openai_gpt-5.2-2025-12-11/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -178,23 +178,23 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.22,
+            "score": 0.0,
             "uncertainty": {
               "num_samples": 100
             },
             "details": {
-              "average_agent_cost": "0.36",
-              "total_run_cost": "36.37",
-              "average_steps": "10.05",
-              "percent_finished": "1.0"
+              "average_agent_cost": "0.0",
+              "total_run_cost": "0.0",
+              "average_steps": "0.0",
+              "percent_finished": "0.0"
             }
           },
           "generation_config": {
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "LiteLLM Tool Calling with Shortlisting",
-                  "agent_framework": "tool_calling_with_shortlisting"
+                  "agent_name": "LiteLLM Tool Calling",
+                  "agent_framework": "tool_calling"
                 }
               }
             }
@@ -206,15 +206,15 @@
         "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": "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",
@@ -261,8 +261,8 @@
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "Claude Code CLI",
-                  "agent_framework": "claude_code"
+                  "agent_name": "OpenAI Solo",
+                  "agent_framework": "openai_solo"
                 }
               }
             }
@@ -274,15 +274,15 @@
         "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": "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",
@@ -314,23 +314,23 @@
             "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"
                 }
               }
             }
@@ -342,15 +342,15 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "OpenAI Solo",
-              "agent_framework": "openai_solo"
+              "agent_name": "SmolAgents Code",
+              "agent_framework": "smolagents_code"
             }
           }
         }
       }
     },
     {
-      "evaluation_id": "browsecompplus/claude-code-cli__openai_gpt-5.2-2025-12-11/1774263615.0201504",
+      "evaluation_id": "browsecompplus/litellm-tool-calling__openai_gpt-5.2-2025-12-11/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -382,23 +382,23 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.43,
+            "score": 0.46,
             "uncertainty": {
               "num_samples": 100
             },
             "details": {
-              "average_agent_cost": "0.43",
-              "total_run_cost": "43.11",
-              "average_steps": "8.97",
-              "percent_finished": "1.0"
+              "average_agent_cost": "0.3",
+              "total_run_cost": "29.78",
+              "average_steps": "8.14",
+              "percent_finished": "0.99"
             }
           },
           "generation_config": {
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "Claude Code CLI",
-                  "agent_framework": "claude_code"
+                  "agent_name": "LiteLLM Tool Calling",
+                  "agent_framework": "tool_calling"
                 }
               }
             }
@@ -410,15 +410,15 @@
         "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": "browsecompplus/smolagents-code__openai_gpt-5.2-2025-12-11/1774263615.0201504",
+      "evaluation_id": "browsecompplus/claude-code-cli__openai_gpt-5.2-2025-12-11/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -450,23 +450,23 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.26,
+            "score": 0.43,
             "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": "0.43",
+              "total_run_cost": "43.11",
+              "average_steps": "8.97",
+              "percent_finished": "1.0"
             }
           },
           "generation_config": {
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "SmolAgents Code",
-                  "agent_framework": "smolagents_code"
+                  "agent_name": "Claude Code CLI",
+                  "agent_framework": "claude_code"
                 }
               }
             }
@@ -478,15 +478,15 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "SmolAgents Code",
-              "agent_framework": "smolagents_code"
+              "agent_name": "Claude Code CLI",
+              "agent_framework": "claude_code"
             }
           }
         }
       }
     },
     {
-      "evaluation_id": "browsecompplus/litellm-tool-calling__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",
@@ -518,23 +518,23 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.46,
+            "score": 0.48,
             "uncertainty": {
               "num_samples": 100
             },
             "details": {
-              "average_agent_cost": "0.3",
-              "total_run_cost": "29.78",
-              "average_steps": "8.14",
-              "percent_finished": "0.99"
+              "average_agent_cost": "0.38",
+              "total_run_cost": "38.21",
+              "average_steps": "14.27",
+              "percent_finished": "1.0"
             }
           },
           "generation_config": {
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "LiteLLM Tool Calling",
-                  "agent_framework": "tool_calling"
+                  "agent_name": "OpenAI Solo",
+                  "agent_framework": "openai_solo"
                 }
               }
             }
@@ -546,15 +546,15 @@
         "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": "browsecompplus/litellm-tool-calling-with-shortlisting__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",
@@ -586,14 +586,14 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.46,
+            "score": 0.26,
             "uncertainty": {
               "num_samples": 100
             },
             "details": {
-              "average_agent_cost": "0.3",
-              "total_run_cost": "29.78",
-              "average_steps": "8.14",
+              "average_agent_cost": "0.17",
+              "total_run_cost": "17.31",
+              "average_steps": "6.57",
               "percent_finished": "0.99"
             }
           },
@@ -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": "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/openai-solo__openai_gpt-5.2-2025-12-11/1774263615.0201504",
+      "evaluation_id": "browsecompplus/litellm-tool-calling-with-shortlisting__openai_gpt-5.2-2025-12-11/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -654,23 +654,23 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.48,
+            "score": 0.46,
             "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": "0.3",
+              "total_run_cost": "29.78",
+              "average_steps": "8.14",
+              "percent_finished": "0.99"
             }
           },
           "generation_config": {
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "OpenAI Solo",
-                  "agent_framework": "openai_solo"
+                  "agent_name": "LiteLLM Tool Calling with Shortlisting",
+                  "agent_framework": "tool_calling_with_shortlisting"
                 }
               }
             }
@@ -682,8 +682,8 @@
         "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"
             }
           }
         }
@@ -769,7 +769,7 @@
       "generation_config": null
     },
     {
-      "evaluation_id": "swe-bench/smolagents-code__openai_gpt-5.2-2025-12-11/1774263615.0201504",
+      "evaluation_id": "swe-bench/litellm-tool-calling__openai_gpt-5.2-2025-12-11/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -801,14 +801,14 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5253,
+            "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"
             }
           },
@@ -816,8 +816,8 @@
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "SmolAgents Code",
-                  "agent_framework": "smolagents_code"
+                  "agent_name": "LiteLLM Tool Calling",
+                  "agent_framework": "tool_calling"
                 }
               }
             }
@@ -829,15 +829,15 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "SmolAgents Code",
-              "agent_framework": "smolagents_code"
+              "agent_name": "LiteLLM Tool Calling",
+              "agent_framework": "tool_calling"
             }
           }
         }
       }
     },
     {
-      "evaluation_id": "swe-bench/litellm-tool-calling__openai_gpt-5.2-2025-12-11/1774263615.0201504",
+      "evaluation_id": "swe-bench/claude-code-cli__openai_gpt-5.2-2025-12-11/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -869,14 +869,14 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.57,
+            "score": 0.58,
             "uncertainty": {
               "num_samples": 100
             },
             "details": {
-              "average_agent_cost": "0.25",
-              "total_run_cost": "24.76",
-              "average_steps": "20.47",
+              "average_agent_cost": "0.94",
+              "total_run_cost": "93.98",
+              "average_steps": "23.99",
               "percent_finished": "1.0"
             }
           },
@@ -884,8 +884,8 @@
             "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"
                 }
               }
             }
@@ -897,15 +897,15 @@
         "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__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",
@@ -937,14 +937,14 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.57,
+            "score": 0.5455,
             "uncertainty": {
-              "num_samples": 100
+              "num_samples": 99
             },
             "details": {
-              "average_agent_cost": "0.25",
-              "total_run_cost": "24.76",
-              "average_steps": "20.47",
+              "average_agent_cost": "0.26",
+              "total_run_cost": "25.64",
+              "average_steps": "20.44",
               "percent_finished": "1.0"
             }
           },
@@ -952,8 +952,8 @@
             "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"
                 }
               }
             }
@@ -965,15 +965,15 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "LiteLLM Tool Calling with Shortlisting",
-              "agent_framework": "tool_calling_with_shortlisting"
+              "agent_name": "OpenAI Solo",
+              "agent_framework": "openai_solo"
             }
           }
         }
       }
     },
     {
-      "evaluation_id": "swe-bench/claude-code-cli__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",
@@ -1005,14 +1005,14 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.58,
+            "score": 0.5253,
             "uncertainty": {
-              "num_samples": 100
+              "num_samples": 99
             },
             "details": {
-              "average_agent_cost": "0.94",
-              "total_run_cost": "93.98",
-              "average_steps": "23.99",
+              "average_agent_cost": "0.45",
+              "total_run_cost": "44.58",
+              "average_steps": "19.98",
               "percent_finished": "1.0"
             }
           },
@@ -1020,8 +1020,8 @@
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "Claude Code CLI",
-                  "agent_framework": "claude_code"
+                  "agent_name": "SmolAgents Code",
+                  "agent_framework": "smolagents_code"
                 }
               }
             }
@@ -1033,15 +1033,15 @@
         "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/airline/litellm-tool-calling-with-shortlisting__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",
@@ -1054,33 +1054,33 @@
         "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": 0.57,
             "uncertainty": {
-              "num_samples": 50
+              "num_samples": 100
             },
             "details": {
-              "average_agent_cost": "0.13",
-              "total_run_cost": "6.96",
-              "average_steps": "11.22",
+              "average_agent_cost": "0.25",
+              "total_run_cost": "24.76",
+              "average_steps": "20.47",
               "percent_finished": "1.0"
             }
           },
@@ -1177,7 +1177,7 @@
       }
     },
     {
-      "evaluation_id": "tau-bench-2/airline/smolagents-code__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",
@@ -1209,14 +1209,14 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6,
+            "score": 0.54,
             "uncertainty": {
               "num_samples": 50
             },
             "details": {
-              "average_agent_cost": "0.29",
-              "total_run_cost": "15.28",
-              "average_steps": "10.68",
+              "average_agent_cost": "0.13",
+              "total_run_cost": "6.96",
+              "average_steps": "11.22",
               "percent_finished": "1.0"
             }
           },
@@ -1224,8 +1224,8 @@
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "SmolAgents Code",
-                  "agent_framework": "smolagents_code"
+                  "agent_name": "LiteLLM Tool Calling",
+                  "agent_framework": "tool_calling"
                 }
               }
             }
@@ -1237,15 +1237,15 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "SmolAgents Code",
-              "agent_framework": "smolagents_code"
+              "agent_name": "LiteLLM Tool Calling",
+              "agent_framework": "tool_calling"
             }
           }
         }
       }
     },
     {
-      "evaluation_id": "tau-bench-2/airline/litellm-tool-calling__openai_gpt-5.2-2025-12-11/1774263615.0201504",
+      "evaluation_id": "tau-bench-2/airline/claude-code-cli__openai_gpt-5.2-2025-12-11/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -1277,14 +1277,14 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.54,
+            "score": 0.48,
             "uncertainty": {
               "num_samples": 50
             },
             "details": {
-              "average_agent_cost": "0.13",
-              "total_run_cost": "6.96",
-              "average_steps": "11.22",
+              "average_agent_cost": "0.21",
+              "total_run_cost": "11.23",
+              "average_steps": "10.18",
               "percent_finished": "1.0"
             }
           },
@@ -1292,8 +1292,8 @@
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "LiteLLM Tool Calling",
-                  "agent_framework": "tool_calling"
+                  "agent_name": "Claude Code CLI",
+                  "agent_framework": "claude_code"
                 }
               }
             }
@@ -1305,15 +1305,15 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "LiteLLM Tool Calling",
-              "agent_framework": "tool_calling"
+              "agent_name": "Claude Code CLI",
+              "agent_framework": "claude_code"
             }
           }
         }
       }
     },
     {
-      "evaluation_id": "swe-bench/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",
@@ -1326,33 +1326,33 @@
         "name": "exgentic",
         "version": "0.1.0"
       },
-      "benchmark": "swe-bench",
+      "benchmark": "tau-bench-2_airline",
       "evaluation_results": [
         {
-          "evaluation_name": "swe-bench",
+          "evaluation_name": "tau-bench-2/airline",
           "source_data": {
-            "dataset_name": "swe-bench",
+            "dataset_name": "tau-bench-2/airline",
             "source_type": "url",
             "url": [
               "https://github.com/Exgentic/exgentic"
             ]
           },
           "metric_config": {
-            "evaluation_description": "SWE-bench benchmark evaluation",
+            "evaluation_description": "Tau Bench 2 benchmark evaluation (airline subset)",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5455,
+            "score": 0.54,
             "uncertainty": {
-              "num_samples": 99
+              "num_samples": 50
             },
             "details": {
-              "average_agent_cost": "0.26",
-              "total_run_cost": "25.64",
-              "average_steps": "20.44",
+              "average_agent_cost": "0.13",
+              "total_run_cost": "6.96",
+              "average_steps": "11.22",
               "percent_finished": "1.0"
             }
           },
@@ -1360,8 +1360,8 @@
             "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"
                 }
               }
             }
@@ -1373,15 +1373,15 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "OpenAI Solo",
-              "agent_framework": "openai_solo"
+              "agent_name": "LiteLLM Tool Calling with Shortlisting",
+              "agent_framework": "tool_calling_with_shortlisting"
             }
           }
         }
       }
     },
     {
-      "evaluation_id": "tau-bench-2/airline/claude-code-cli__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",
@@ -1413,14 +1413,14 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.48,
+            "score": 0.6,
             "uncertainty": {
               "num_samples": 50
             },
             "details": {
-              "average_agent_cost": "0.21",
-              "total_run_cost": "11.23",
-              "average_steps": "10.18",
+              "average_agent_cost": "0.29",
+              "total_run_cost": "15.28",
+              "average_steps": "10.68",
               "percent_finished": "1.0"
             }
           },
@@ -1428,8 +1428,8 @@
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "Claude Code CLI",
-                  "agent_framework": "claude_code"
+                  "agent_name": "SmolAgents Code",
+                  "agent_framework": "smolagents_code"
                 }
               }
             }
@@ -1441,15 +1441,15 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "Claude Code CLI",
-              "agent_framework": "claude_code"
+              "agent_name": "SmolAgents Code",
+              "agent_framework": "smolagents_code"
             }
           }
         }
       }
     },
     {
-      "evaluation_id": "tau-bench-2/retail/litellm-tool-calling-with-shortlisting__openai_gpt-5.2-2025-12-11/1774263615.0201504",
+      "evaluation_id": "tau-bench-2/retail/openai-solo__openai_gpt-5.2-2025-12-11/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -1481,23 +1481,23 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.73,
+            "score": 0.5354,
             "uncertainty": {
               "num_samples": 100
             },
             "details": {
               "average_agent_cost": "0.11",
-              "total_run_cost": "12.27",
-              "average_steps": "10.33",
-              "percent_finished": "1.0"
+              "total_run_cost": "11.54",
+              "average_steps": "9.55",
+              "percent_finished": "0.99"
             }
           },
           "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"
                 }
               }
             }
@@ -1509,15 +1509,15 @@
         "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/retail/litellm-tool-calling__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",
@@ -1564,8 +1564,8 @@
             "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"
                 }
               }
             }
@@ -1577,15 +1577,15 @@
         "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__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",
@@ -1617,23 +1617,23 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.68,
+            "score": 0.51,
             "uncertainty": {
               "num_samples": 100
             },
             "details": {
-              "average_agent_cost": "0.25",
-              "total_run_cost": "26.27",
-              "average_steps": "11.08",
-              "percent_finished": "1.0"
+              "average_agent_cost": "0.12",
+              "total_run_cost": "12.63",
+              "average_steps": "9.92",
+              "percent_finished": "0.98"
             }
           },
           "generation_config": {
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "SmolAgents Code",
-                  "agent_framework": "smolagents_code"
+                  "agent_name": "Claude Code CLI",
+                  "agent_framework": "claude_code"
                 }
               }
             }
@@ -1645,15 +1645,15 @@
         "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/smolagents-code__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": 0.5354,
+            "score": 0.68,
             "uncertainty": {
               "num_samples": 100
             },
             "details": {
-              "average_agent_cost": "0.11",
-              "total_run_cost": "11.54",
-              "average_steps": "9.55",
-              "percent_finished": "0.99"
+              "average_agent_cost": "0.25",
+              "total_run_cost": "26.27",
+              "average_steps": "11.08",
+              "percent_finished": "1.0"
             }
           },
           "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"
                 }
               }
             }
@@ -1713,15 +1713,15 @@
         "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/telecom/smolagents-code__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",
@@ -1734,33 +1734,33 @@
         "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": 0.71,
+            "score": 0.73,
             "uncertainty": {
               "num_samples": 100
             },
             "details": {
-              "average_agent_cost": "0.3",
-              "total_run_cost": "35.31",
-              "average_steps": "10.11",
+              "average_agent_cost": "0.11",
+              "total_run_cost": "12.27",
+              "average_steps": "10.33",
               "percent_finished": "1.0"
             }
           },
@@ -1768,8 +1768,8 @@
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "SmolAgents Code",
-                  "agent_framework": "smolagents_code"
+                  "agent_name": "LiteLLM Tool Calling",
+                  "agent_framework": "tool_calling"
                 }
               }
             }
@@ -1781,15 +1781,15 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "SmolAgents Code",
-              "agent_framework": "smolagents_code"
+              "agent_name": "LiteLLM Tool Calling",
+              "agent_framework": "tool_calling"
             }
           }
         }
       }
     },
     {
-      "evaluation_id": "tau-bench-2/telecom/claude-code-cli__openai_gpt-5.2-2025-12-11/1774263615.0201504",
+      "evaluation_id": "tau-bench-2/telecom/litellm-tool-calling-with-shortlisting__openai_gpt-5.2-2025-12-11/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -1821,23 +1821,23 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.55,
+            "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"
                 }
               }
             }
@@ -1849,8 +1849,8 @@
         "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"
             }
           }
         }
@@ -1993,7 +1993,7 @@
       }
     },
     {
-      "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/smolagents-code__openai_gpt-5.2-2025-12-11/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -2025,23 +2025,23 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5354,
+            "score": 0.71,
             "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": "0.3",
+              "total_run_cost": "35.31",
+              "average_steps": "10.11",
+              "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": "SmolAgents Code",
+                  "agent_framework": "smolagents_code"
                 }
               }
             }
@@ -2053,15 +2053,15 @@
         "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/retail/claude-code-cli__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",
@@ -2074,34 +2074,34 @@
         "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": 0.51,
+            "score": 0.55,
             "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": "0.1",
+              "total_run_cost": "15.15",
+              "average_steps": "9.36",
+              "percent_finished": "1.0"
             }
           },
           "generation_config": {
diff --git a/data/models/openai_gpt-5.2.json b/data/models/openai_gpt-5.2.json
index ff63f2052ea0b7c9a5cea40f5696ce46050721df..77930b98006acfd2c6efa9a1e831cbd44874ee48 100644
--- a/data/models/openai_gpt-5.2.json
+++ b/data/models/openai_gpt-5.2.json
@@ -84,7 +84,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/mux__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",
@@ -108,7 +108,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2026-01-17",
+          "evaluation_timestamp": "2025-12-24",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -117,11 +117,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 60.7
+            "score": 64.9,
+            "uncertainty": {
+              "standard_error": {
+                "value": 2.8
+              },
+              "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 \"Droid\" -m \"GPT-5.2\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -138,7 +144,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Mux\" -m \"GPT-5.2\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Droid\" -m \"GPT-5.2\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -152,7 +158,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/droid__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",
@@ -176,7 +182,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-12-24",
+          "evaluation_timestamp": "2025-12-12",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -185,17 +191,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 64.9,
+            "score": 54.0,
             "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 \"Droid\" -m \"GPT-5.2\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"GPT-5.2\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -212,7 +218,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Droid\" -m \"GPT-5.2\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"GPT-5.2\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -226,7 +232,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/terminus-2__gpt-5.2/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/mux__gpt-5.2/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -250,7 +256,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-12-12",
+          "evaluation_timestamp": "2026-01-17",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -259,17 +265,11 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 54.0,
-            "uncertainty": {
-              "standard_error": {
-                "value": 2.9
-              },
-              "num_samples": 435
-            }
+            "score": 60.7
           },
           "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 \"Mux\" -m \"GPT-5.2\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -286,7 +286,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"GPT-5.2\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Mux\" -m \"GPT-5.2\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
diff --git a/data/models/openai_gpt-5.3-codex.json b/data/models/openai_gpt-5.3-codex.json
index 65f8130b44c7c4318430a774c580739b4e8b1cab..29bf24de6a839acf45f0dd14a04022b9052f2277 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": "Mux",
-      "agent_organization": "Coder"
+      "agent_name": "Terminus 2",
+      "agent_organization": "Terminal Bench"
     }
   },
   "evaluations": [
     {
-      "evaluation_id": "terminal-bench-2.0/mux__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",
@@ -34,7 +34,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2026-03-06",
+          "evaluation_timestamp": "2026-02-05",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -43,17 +43,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 74.6,
+            "score": 64.7,
             "uncertainty": {
               "standard_error": {
-                "value": 2.5
+                "value": 2.7
               },
               "num_samples": 435
             }
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Mux\" -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": [
                   {
@@ -70,7 +70,7 @@
       "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 \"Terminus 2\" -m \"GPT-5.3-Codex\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -158,7 +158,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/terminus-2__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",
@@ -182,7 +182,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2026-02-05",
+          "evaluation_timestamp": "2026-02-06",
           "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": 64.7,
+            "score": 75.1,
             "uncertainty": {
               "standard_error": {
-                "value": 2.7
+                "value": 2.4
               },
               "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 \"Simple Codex\" -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 \"Terminus 2\" -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": [
               {
@@ -232,7 +232,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/simple-codex__gpt-5.3-codex/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/droid__gpt-5.3-codex/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -256,7 +256,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2026-02-06",
+          "evaluation_timestamp": "2026-02-24",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -265,17 +265,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 75.1,
+            "score": 77.3,
             "uncertainty": {
               "standard_error": {
-                "value": 2.4
+                "value": 2.2
               },
               "num_samples": 435
             }
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Simple Codex\" -m \"GPT-5.3-Codex\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Droid\" -m \"GPT-5.3-Codex\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -292,7 +292,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Simple Codex\" -m \"GPT-5.3-Codex\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Droid\" -m \"GPT-5.3-Codex\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -306,7 +306,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/droid__gpt-5.3-codex/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/mux__gpt-5.3-codex/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -330,7 +330,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2026-02-24",
+          "evaluation_timestamp": "2026-03-06",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -339,17 +339,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 77.3,
+            "score": 74.6,
             "uncertainty": {
               "standard_error": {
-                "value": 2.2
+                "value": 2.5
               },
               "num_samples": 435
             }
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Droid\" -m \"GPT-5.3-Codex\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Mux\" -m \"GPT-5.3-Codex\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -366,7 +366,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Droid\" -m \"GPT-5.3-Codex\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Mux\" -m \"GPT-5.3-Codex\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
diff --git a/data/models/openai_gpt-oss-20b.json b/data/models/openai_gpt-oss-20b.json
index 584e35a6df7897b2cd4e9e1cdb5c6db8d87d90ab..d658cd5464b4783e6e0372fda0cb20e4e0a6a422 100644
--- a/data/models/openai_gpt-oss-20b.json
+++ b/data/models/openai_gpt-oss-20b.json
@@ -310,7 +310,7 @@
       "generation_config": null
     },
     {
-      "evaluation_id": "terminal-bench-2.0/terminus-2__gpt-oss-20b/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/mini-swe-agent__gpt-oss-20b/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -334,7 +334,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-11-01",
+          "evaluation_timestamp": "2025-11-03",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -343,17 +343,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 3.1,
+            "score": 3.4,
             "uncertainty": {
               "standard_error": {
-                "value": 1.5
+                "value": 1.4
               },
               "num_samples": 435
             }
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"GPT-OSS-20B\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Mini-SWE-Agent\" -m \"GPT-OSS-20B\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -370,7 +370,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"GPT-OSS-20B\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Mini-SWE-Agent\" -m \"GPT-OSS-20B\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -384,7 +384,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/mini-swe-agent__gpt-oss-20b/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/terminus-2__gpt-oss-20b/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -408,7 +408,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-11-03",
+          "evaluation_timestamp": "2025-11-01",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -417,17 +417,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 3.4,
+            "score": 3.1,
             "uncertainty": {
               "standard_error": {
-                "value": 1.4
+                "value": 1.5
               },
               "num_samples": 435
             }
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Mini-SWE-Agent\" -m \"GPT-OSS-20B\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"GPT-OSS-20B\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -444,7 +444,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Mini-SWE-Agent\" -m \"GPT-OSS-20B\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"GPT-OSS-20B\" -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 e5de01feca478b0842db2b2533d006446492021b..fec8e3d9659540e746cd368872cad0ec3c496416 100644
--- a/data/models/openai_gpt_5.2.json
+++ b/data/models/openai_gpt_5.2.json
@@ -7,10 +7,10 @@
   },
   "evaluations": [
     {
-      "evaluation_id": "apex-agents/openai_gpt-5.2/1773260200",
+      "evaluation_id": "ace/openai_gpt-5.2/1773260200",
       "retrieved_timestamp": "1773260200",
       "source_metadata": {
-        "source_name": "Mercor APEX-Agents Leaderboard",
+        "source_name": "Mercor ACE 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": "apex-agents",
+      "benchmark": "ace",
       "evaluation_results": [
         {
-          "evaluation_name": "Overall 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": "Overall Pass@1 (dataset card / paper snapshot).",
+            "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": 0.23,
+            "score": 0.515,
             "uncertainty": {
               "confidence_interval": {
                 "lower": -0.032,
@@ -53,28 +53,21 @@
           }
         },
         {
-          "evaluation_name": "Overall Pass@8",
+          "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": "Overall Pass@8 (dataset card / paper snapshot).",
+            "evaluation_description": "Food domain score.",
             "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": 0.65
           },
           "generation_config": {
             "additional_details": {
@@ -83,44 +76,75 @@
           }
         },
         {
-          "evaluation_name": "Overall 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": "Overall mean rubric score.",
+            "evaluation_description": "Gaming domain score.",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0,
             "max_score": 1
           },
           "score_details": {
-            "score": 0.387
+            "score": 0.578
           },
           "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": "Investment Banking Pass@1",
+          "evaluation_name": "Overall Pass@1",
           "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": "Overall Pass@1 (dataset card / paper snapshot).",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0,
             "max_score": 1
           },
           "score_details": {
-            "score": 0.273
+            "score": 0.23,
+            "uncertainty": {
+              "confidence_interval": {
+                "lower": -0.032,
+                "upper": 0.032,
+                "method": "bootstrap"
+              }
+            }
           },
           "generation_config": {
             "additional_details": {
@@ -129,21 +153,28 @@
           }
         },
         {
-          "evaluation_name": "Management Consulting Pass@1",
+          "evaluation_name": "Overall Pass@8",
           "source_data": {
             "dataset_name": "apex-agents",
             "source_type": "hf_dataset",
             "hf_repo": "mercor/apex-agents"
           },
           "metric_config": {
-            "evaluation_description": "Management consulting world Pass@1.",
+            "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": 0.227
+            "score": 0.4,
+            "uncertainty": {
+              "confidence_interval": {
+                "lower": -0.044,
+                "upper": 0.044,
+                "method": "bootstrap"
+              }
+            }
           },
           "generation_config": {
             "additional_details": {
@@ -152,21 +183,21 @@
           }
         },
         {
-          "evaluation_name": "Corporate Law Pass@1",
+          "evaluation_name": "Overall Mean Score",
           "source_data": {
             "dataset_name": "apex-agents",
             "source_type": "hf_dataset",
             "hf_repo": "mercor/apex-agents"
           },
           "metric_config": {
-            "evaluation_description": "Corporate law world Pass@1.",
+            "evaluation_description": "Overall mean rubric score.",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0,
             "max_score": 1
           },
           "score_details": {
-            "score": 0.189
+            "score": 0.387
           },
           "generation_config": {
             "additional_details": {
@@ -175,75 +206,44 @@
           }
         },
         {
-          "evaluation_name": "Corporate Lawyer Mean Score",
+          "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": "Corporate lawyer world mean score.",
+            "evaluation_description": "Investment banking world Pass@1.",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0,
             "max_score": 1
           },
           "score_details": {
-            "score": 0.443
+            "score": 0.273
           },
           "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": "Overall Score",
+          "evaluation_name": "Management Consulting 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": "Management consulting world Pass@1.",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0,
             "max_score": 1
           },
           "score_details": {
-            "score": 0.515,
-            "uncertainty": {
-              "confidence_interval": {
-                "lower": -0.032,
-                "upper": 0.032,
-                "method": "bootstrap"
-              }
-            }
+            "score": 0.227
           },
           "generation_config": {
             "additional_details": {
@@ -252,21 +252,21 @@
           }
         },
         {
-          "evaluation_name": "Food Score",
+          "evaluation_name": "Corporate Law 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": "Food domain score.",
+            "evaluation_description": "Corporate law world Pass@1.",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0,
             "max_score": 1
           },
           "score_details": {
-            "score": 0.65
+            "score": 0.189
           },
           "generation_config": {
             "additional_details": {
@@ -275,21 +275,21 @@
           }
         },
         {
-          "evaluation_name": "Gaming Score",
+          "evaluation_name": "Corporate Lawyer 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": "Corporate lawyer world mean score.",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0,
             "max_score": 1
           },
           "score_details": {
-            "score": 0.578
+            "score": 0.443
           },
           "generation_config": {
             "additional_details": {
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 b28ca5c5700af0f5cf22d77dcb1c4fea033ecc2d..cf1ba02f6dd573bf3e0770ff614660b73e92dbb8 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/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",
@@ -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": 0.6126
+            "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"
           }
         }
       ],
@@ -141,10 +159,10 @@
       "generation_config": null
     },
     {
-      "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",
@@ -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": 0.32
-          },
-          "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"
           }
         }
       ],
diff --git a/data/models/openbmb_eurus-rm-7b.json b/data/models/openbmb_eurus-rm-7b.json
index 44637ca17276f082725f61866dcfa3229cc54274..e1154a660c89f219cec7ec844602d9d8fdfa08ad 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/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",
@@ -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": 0.8159
+            "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"
           }
         }
       ],
@@ -141,10 +159,10 @@
       "generation_config": null
     },
     {
-      "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",
@@ -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": 0.5806
-          },
-          "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"
           }
         }
       ],
diff --git a/data/models/pku-alignment_beaver-7b-v1.0-cost.json b/data/models/pku-alignment_beaver-7b-v1.0-cost.json
index 8e786484059e3101c1249c1cce8c4b2be81faa5a..3777eba3edfdc470c669a503ac85994bf8139135 100644
--- a/data/models/pku-alignment_beaver-7b-v1.0-cost.json
+++ b/data/models/pku-alignment_beaver-7b-v1.0-cost.json
@@ -9,10 +9,10 @@
   },
   "evaluations": [
     {
-      "evaluation_id": "reward-bench/PKU-Alignment_beaver-7b-v1.0-cost/1766412838.146816",
+      "evaluation_id": "reward-bench-2/PKU-Alignment_beaver-7b-v1.0-cost/1766412838.146816",
       "retrieved_timestamp": "1766412838.146816",
       "source_metadata": {
-        "source_name": "RewardBench",
+        "source_name": "RewardBench 2",
         "source_type": "documentation",
         "source_organization_name": "Allen Institute for AI",
         "source_organization_url": "https://allenai.org",
@@ -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": 0.5798
+            "score": 0.3332
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Chat",
+          "evaluation_name": "Factuality",
           "metric_config": {
-            "evaluation_description": "Chat accuracy - includes easy chat subsets",
+            "evaluation_description": "Factuality score - measures factual accuracy",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6173
+            "score": 0.3263
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Chat Hard",
+          "evaluation_name": "Precise IF",
           "metric_config": {
-            "evaluation_description": "Chat Hard accuracy - includes hard chat subsets",
+            "evaluation_description": "Precise Instruction Following score",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4232
+            "score": 0.2313
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
+          }
+        },
+        {
+          "evaluation_name": "Math",
+          "metric_config": {
+            "evaluation_description": "Math score - measures mathematical reasoning",
+            "lower_is_better": false,
+            "score_type": "continuous",
+            "min_score": 0.0,
+            "max_score": 1.0
+          },
+          "score_details": {
+            "score": 0.3989
+          },
+          "source_data": {
+            "dataset_name": "RewardBench 2",
+            "source_type": "hf_dataset",
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
           "evaluation_name": "Safety",
           "metric_config": {
-            "evaluation_description": "Safety accuracy - includes safety subsets",
+            "evaluation_description": "Safety score - measures safety awareness",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7351
+            "score": 0.7589
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Reasoning",
+          "evaluation_name": "Focus",
           "metric_config": {
-            "evaluation_description": "Reasoning accuracy - includes code and math subsets",
+            "evaluation_description": "Focus score - measures response focus",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5482
+            "score": 0.2939
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Prior Sets (0.5 weight)",
+          "evaluation_name": "Ties",
           "metric_config": {
-            "evaluation_description": "Prior Sets score (weighted 0.5) - includes test sets",
+            "evaluation_description": "Ties score - ability to identify tie cases",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.57
+            "score": -0.01
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         }
       ],
@@ -141,10 +159,10 @@
       "generation_config": null
     },
     {
-      "evaluation_id": "reward-bench-2/PKU-Alignment_beaver-7b-v1.0-cost/1766412838.146816",
+      "evaluation_id": "reward-bench/PKU-Alignment_beaver-7b-v1.0-cost/1766412838.146816",
       "retrieved_timestamp": "1766412838.146816",
       "source_metadata": {
-        "source_name": "RewardBench 2",
+        "source_name": "RewardBench",
         "source_type": "documentation",
         "source_organization_name": "Allen Institute for AI",
         "source_organization_url": "https://allenai.org",
@@ -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": 0.3332
-          },
-          "source_data": {
-            "dataset_name": "RewardBench 2",
-            "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
-          }
-        },
-        {
-          "evaluation_name": "Factuality",
-          "metric_config": {
-            "evaluation_description": "Factuality score - measures factual accuracy",
+            "evaluation_description": "Overall RewardBench Score",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3263
+            "score": 0.5798
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Precise IF",
+          "evaluation_name": "Chat",
           "metric_config": {
-            "evaluation_description": "Precise Instruction Following score",
+            "evaluation_description": "Chat accuracy - includes easy chat subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2313
+            "score": 0.6173
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Math",
+          "evaluation_name": "Chat Hard",
           "metric_config": {
-            "evaluation_description": "Math score - measures mathematical reasoning",
+            "evaluation_description": "Chat Hard accuracy - includes hard chat subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3989
+            "score": 0.4232
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
           "evaluation_name": "Safety",
           "metric_config": {
-            "evaluation_description": "Safety score - measures safety awareness",
+            "evaluation_description": "Safety accuracy - includes safety subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7589
+            "score": 0.7351
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Focus",
+          "evaluation_name": "Reasoning",
           "metric_config": {
-            "evaluation_description": "Focus score - measures response focus",
+            "evaluation_description": "Reasoning accuracy - includes code and math subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2939
+            "score": 0.5482
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Ties",
+          "evaluation_name": "Prior Sets (0.5 weight)",
           "metric_config": {
-            "evaluation_description": "Ties score - ability to identify tie cases",
+            "evaluation_description": "Prior Sets score (weighted 0.5) - includes test sets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": -0.01
+            "score": 0.57
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         }
       ],
diff --git a/data/models/prithivmlmods_calcium-opus-14b-elite.json b/data/models/prithivmlmods_calcium-opus-14b-elite.json
index 746fd41957e7795e0f0f3751181ce9bfef3d8e70..89a0dd9277acb0b40655f39809af8ab4d96076ef 100644
--- a/data/models/prithivmlmods_calcium-opus-14b-elite.json
+++ b/data/models/prithivmlmods_calcium-opus-14b-elite.json
@@ -5,7 +5,7 @@
     "developer": "prithivMLmods",
     "inference_platform": "unknown",
     "additional_details": {
-      "precision": "float16",
+      "precision": "bfloat16",
       "architecture": "Qwen2ForCausalLM",
       "params_billions": "14.766"
     }
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6064
+            "score": 0.6052
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6296
+            "score": 0.6317
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3708
+            "score": 0.4789
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3733
+            "score": 0.3742
           }
         },
         {
@@ -116,7 +116,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4873
+            "score": 0.486
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5307
+            "score": 0.5302
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6052
+            "score": 0.6064
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6317
+            "score": 0.6296
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4789
+            "score": 0.3708
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3742
+            "score": 0.3733
           }
         },
         {
@@ -246,7 +246,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.486
+            "score": 0.4873
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5302
+            "score": 0.5307
           }
         }
       ],
diff --git a/data/models/qingy2019_qwen2.5-math-14b-instruct.json b/data/models/qingy2019_qwen2.5-math-14b-instruct.json
index d07b0024c79975f453423bba6d277d902ff3056c..21a12461d0cce8974037575db54605a0da19b661 100644
--- a/data/models/qingy2019_qwen2.5-math-14b-instruct.json
+++ b/data/models/qingy2019_qwen2.5-math-14b-instruct.json
@@ -5,7 +5,7 @@
     "developer": "qingy2019",
     "inference_platform": "unknown",
     "additional_details": {
-      "precision": "float16",
+      "precision": "bfloat16",
       "architecture": "Qwen2ForCausalLM",
       "params_billions": "14.0"
     }
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6066
+            "score": 0.6005
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.635
+            "score": 0.6356
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3716
+            "score": 0.2764
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3725
+            "score": 0.3691
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5331
+            "score": 0.5339
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6005
+            "score": 0.6066
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6356
+            "score": 0.635
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2764
+            "score": 0.3716
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3691
+            "score": 0.3725
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5339
+            "score": 0.5331
           }
         }
       ],
diff --git a/data/models/ray2333_grm-llama3-8b-distill.json b/data/models/ray2333_grm-llama3-8b-distill.json
index 28bee941f1d39ce464ca73210ca8cbef67a5d082..a698e2dc0120e472c95dbd375c2ce72c243acf20 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-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",
@@ -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": 0.589
-          },
-          "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"
           }
         }
       ],
@@ -159,10 +141,10 @@
       "generation_config": null
     },
     {
-      "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",
@@ -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": 0.8464
+            "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"
           }
         }
       ],
diff --git a/data/models/ray2333_grm-llama3-8b-rewardmodel-ft.json b/data/models/ray2333_grm-llama3-8b-rewardmodel-ft.json
index 569e87e2d1650530a990e95b347a974efc9f47d2..294d09da30917c4eff496ef892b03ff9d96db067 100644
--- a/data/models/ray2333_grm-llama3-8b-rewardmodel-ft.json
+++ b/data/models/ray2333_grm-llama3-8b-rewardmodel-ft.json
@@ -9,10 +9,10 @@
   },
   "evaluations": [
     {
-      "evaluation_id": "reward-bench-2/Ray2333_GRM-Llama3-8B-rewardmodel-ft/1766412838.146816",
+      "evaluation_id": "reward-bench/Ray2333_GRM-Llama3-8B-rewardmodel-ft/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": 0.6766
+            "score": 0.9154
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "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": 0.6274
+            "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": "Precise IF",
+          "evaluation_name": "Chat Hard",
           "metric_config": {
-            "evaluation_description": "Precise Instruction Following score",
+            "evaluation_description": "Chat Hard accuracy - includes hard chat subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.35
+            "score": 0.8618
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "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": 0.5847
+            "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": 0.9222
+            "score": 0.9362
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
-        },
+        }
+      ],
+      "detailed_evaluation_results": null,
+      "generation_config": null
+    },
+    {
+      "evaluation_id": "reward-bench-2/Ray2333_GRM-Llama3-8B-rewardmodel-ft/1766412838.146816",
+      "retrieved_timestamp": "1766412838.146816",
+      "source_metadata": {
+        "source_name": "RewardBench 2",
+        "source_type": "documentation",
+        "source_organization_name": "Allen Institute for AI",
+        "source_organization_url": "https://allenai.org",
+        "evaluator_relationship": "third_party"
+      },
+      "eval_library": {
+        "name": "rewardbench",
+        "version": "0.1.3",
+        "additional_details": {
+          "subsets": "Chat, Chat Hard, Safety, Reasoning",
+          "hf_space": "allenai/reward-bench"
+        }
+      },
+      "benchmark": "reward-bench",
+      "evaluation_results": [
         {
-          "evaluation_name": "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": 0.8929
+            "score": 0.6766
           },
           "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": 0.6824
+            "score": 0.6274
           },
           "source_data": {
             "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
             "hf_repo": "allenai/reward-bench-2-results"
           }
-        }
-      ],
-      "detailed_evaluation_results": null,
-      "generation_config": null
-    },
-    {
-      "evaluation_id": "reward-bench/Ray2333_GRM-Llama3-8B-rewardmodel-ft/1766412838.146816",
-      "retrieved_timestamp": "1766412838.146816",
-      "source_metadata": {
-        "source_name": "RewardBench",
-        "source_type": "documentation",
-        "source_organization_name": "Allen Institute for AI",
-        "source_organization_url": "https://allenai.org",
-        "evaluator_relationship": "third_party"
-      },
-      "eval_library": {
-        "name": "rewardbench",
-        "version": "0.1.3",
-        "additional_details": {
-          "subsets": "Chat, Chat Hard, Safety, Reasoning",
-          "hf_space": "allenai/reward-bench"
-        }
-      },
-      "benchmark": "reward-bench",
-      "evaluation_results": [
+        },
         {
-          "evaluation_name": "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": 0.9154
+            "score": 0.35
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Chat",
+          "evaluation_name": "Math",
           "metric_config": {
-            "evaluation_description": "Chat accuracy - includes easy chat subsets",
+            "evaluation_description": "Math score - measures mathematical reasoning",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9553
+            "score": 0.5847
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "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": 0.8618
+            "score": 0.9222
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Safety",
+          "evaluation_name": "Focus",
           "metric_config": {
-            "evaluation_description": "Safety accuracy - includes safety subsets",
+            "evaluation_description": "Focus score - measures response focus",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9081
+            "score": 0.8929
           },
           "source_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": 0.9362
+            "score": 0.6824
           },
           "source_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/ray2333_grm-llama3-8b-sftreg.json b/data/models/ray2333_grm-llama3-8b-sftreg.json
index 15f35c842dfd5169bfd85bae53f76a90d5850421..bd70639489991e3e8880cad041284119bd35ecc9 100644
--- a/data/models/ray2333_grm-llama3-8b-sftreg.json
+++ b/data/models/ray2333_grm-llama3-8b-sftreg.json
@@ -9,10 +9,10 @@
   },
   "evaluations": [
     {
-      "evaluation_id": "reward-bench-2/Ray2333_GRM-llama3-8B-sftreg/1766412838.146816",
+      "evaluation_id": "reward-bench/Ray2333_GRM-llama3-8B-sftreg/1766412838.146816",
       "retrieved_timestamp": "1766412838.146816",
       "source_metadata": {
-        "source_name": "RewardBench 2",
+        "source_name": "RewardBench",
         "source_type": "documentation",
         "source_organization_name": "Allen Institute for AI",
         "source_organization_url": "https://allenai.org",
@@ -31,127 +31,109 @@
         {
           "evaluation_name": "Score",
           "metric_config": {
-            "evaluation_description": "Overall RewardBench 2 Score (mean of all metrics)",
-            "lower_is_better": false,
-            "score_type": "continuous",
-            "min_score": 0.0,
-            "max_score": 1.0
-          },
-          "score_details": {
-            "score": 0.6089
-          },
-          "source_data": {
-            "dataset_name": "RewardBench 2",
-            "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
-          }
-        },
-        {
-          "evaluation_name": "Factuality",
-          "metric_config": {
-            "evaluation_description": "Factuality score - measures factual accuracy",
+            "evaluation_description": "Overall RewardBench Score",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6189
+            "score": 0.8542
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Precise IF",
+          "evaluation_name": "Chat",
           "metric_config": {
-            "evaluation_description": "Precise Instruction Following score",
+            "evaluation_description": "Chat accuracy - includes easy chat subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3875
+            "score": 0.986
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Math",
+          "evaluation_name": "Chat Hard",
           "metric_config": {
-            "evaluation_description": "Math score - measures mathematical reasoning",
+            "evaluation_description": "Chat Hard accuracy - includes hard chat subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5792
+            "score": 0.6776
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
           "evaluation_name": "Safety",
           "metric_config": {
-            "evaluation_description": "Safety score - measures safety awareness",
+            "evaluation_description": "Safety accuracy - includes safety subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7867
+            "score": 0.8919
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Focus",
+          "evaluation_name": "Reasoning",
           "metric_config": {
-            "evaluation_description": "Focus score - measures response focus",
+            "evaluation_description": "Reasoning accuracy - includes code and math subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6828
+            "score": 0.9229
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Ties",
+          "evaluation_name": "Prior Sets (0.5 weight)",
           "metric_config": {
-            "evaluation_description": "Ties score - ability to identify tie cases",
+            "evaluation_description": "Prior Sets score (weighted 0.5) - includes test sets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5981
+            "score": 0.7309
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         }
       ],
@@ -159,10 +141,10 @@
       "generation_config": null
     },
     {
-      "evaluation_id": "reward-bench/Ray2333_GRM-llama3-8B-sftreg/1766412838.146816",
+      "evaluation_id": "reward-bench-2/Ray2333_GRM-llama3-8B-sftreg/1766412838.146816",
       "retrieved_timestamp": "1766412838.146816",
       "source_metadata": {
-        "source_name": "RewardBench",
+        "source_name": "RewardBench 2",
         "source_type": "documentation",
         "source_organization_name": "Allen Institute for AI",
         "source_organization_url": "https://allenai.org",
@@ -181,109 +163,127 @@
         {
           "evaluation_name": "Score",
           "metric_config": {
-            "evaluation_description": "Overall RewardBench Score",
+            "evaluation_description": "Overall RewardBench 2 Score (mean of all metrics)",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.8542
+            "score": 0.6089
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Chat",
+          "evaluation_name": "Factuality",
           "metric_config": {
-            "evaluation_description": "Chat accuracy - includes easy chat subsets",
+            "evaluation_description": "Factuality score - measures factual accuracy",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.986
+            "score": 0.6189
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Chat Hard",
+          "evaluation_name": "Precise IF",
           "metric_config": {
-            "evaluation_description": "Chat Hard accuracy - includes hard chat subsets",
+            "evaluation_description": "Precise Instruction Following score",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6776
+            "score": 0.3875
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
+          }
+        },
+        {
+          "evaluation_name": "Math",
+          "metric_config": {
+            "evaluation_description": "Math score - measures mathematical reasoning",
+            "lower_is_better": false,
+            "score_type": "continuous",
+            "min_score": 0.0,
+            "max_score": 1.0
+          },
+          "score_details": {
+            "score": 0.5792
+          },
+          "source_data": {
+            "dataset_name": "RewardBench 2",
+            "source_type": "hf_dataset",
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
           "evaluation_name": "Safety",
           "metric_config": {
-            "evaluation_description": "Safety accuracy - includes safety subsets",
+            "evaluation_description": "Safety score - measures safety awareness",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.8919
+            "score": 0.7867
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Reasoning",
+          "evaluation_name": "Focus",
           "metric_config": {
-            "evaluation_description": "Reasoning accuracy - includes code and math subsets",
+            "evaluation_description": "Focus score - measures response focus",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9229
+            "score": 0.6828
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Prior Sets (0.5 weight)",
+          "evaluation_name": "Ties",
           "metric_config": {
-            "evaluation_description": "Prior Sets score (weighted 0.5) - includes test sets",
+            "evaluation_description": "Ties score - ability to identify tie cases",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7309
+            "score": 0.5981
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         }
       ],
diff --git a/data/models/recoilme_gemma-2-ataraxy-gemmasutra-9b-slerp.json b/data/models/recoilme_gemma-2-ataraxy-gemmasutra-9b-slerp.json
index f26fe1b9038e8edc381d5411187a5c6b2c7cbf6e..07191bcaa576a8b8b67650d88a341b91a6316705 100644
--- a/data/models/recoilme_gemma-2-ataraxy-gemmasutra-9b-slerp.json
+++ b/data/models/recoilme_gemma-2-ataraxy-gemmasutra-9b-slerp.json
@@ -5,7 +5,7 @@
     "developer": "recoilme",
     "inference_platform": "unknown",
     "additional_details": {
-      "precision": "float16",
+      "precision": "bfloat16",
       "architecture": "Gemma2ForCausalLM",
       "params_billions": "10.159"
     }
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7649
+            "score": 0.2854
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5974
+            "score": 0.5984
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0174
+            "score": 0.1005
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3305
+            "score": 0.3297
           }
         },
         {
@@ -116,7 +116,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4245
+            "score": 0.4607
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4207
+            "score": 0.4162
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2854
+            "score": 0.7649
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5984
+            "score": 0.5974
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1005
+            "score": 0.0174
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3297
+            "score": 0.3305
           }
         },
         {
@@ -246,7 +246,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4607
+            "score": 0.4245
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4162
+            "score": 0.4207
           }
         }
       ],
diff --git a/data/models/recoilme_recoilme-gemma-2-9b-v0.2.json b/data/models/recoilme_recoilme-gemma-2-9b-v0.2.json
index 83bfdb05cda442c3bac351d424fa26cf0ae864fe..34121094195afd5811c50d769ba5e5e07669b30d 100644
--- a/data/models/recoilme_recoilme-gemma-2-9b-v0.2.json
+++ b/data/models/recoilme_recoilme-gemma-2-9b-v0.2.json
@@ -5,7 +5,7 @@
     "developer": "recoilme",
     "inference_platform": "unknown",
     "additional_details": {
-      "precision": "float16",
+      "precision": "bfloat16",
       "architecture": "Gemma2ForCausalLM",
       "params_billions": "10.159"
     }
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7592
+            "score": 0.2747
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6026
+            "score": 0.6031
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0529
+            "score": 0.0831
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3289
+            "score": 0.3305
           }
         },
         {
@@ -116,7 +116,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4099
+            "score": 0.4686
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4163
+            "score": 0.4122
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2747
+            "score": 0.7592
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6031
+            "score": 0.6026
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0831
+            "score": 0.0529
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3305
+            "score": 0.3289
           }
         },
         {
@@ -246,7 +246,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4686
+            "score": 0.4099
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4122
+            "score": 0.4163
           }
         }
       ],
diff --git a/data/models/recoilme_recoilme-gemma-2-9b-v0.3.json b/data/models/recoilme_recoilme-gemma-2-9b-v0.3.json
index d5cadb462419994ffdabe8b6cdbd73be57e99fa8..812871dcfb75c54e3765d2c8d03eeadc60d898aa 100644
--- a/data/models/recoilme_recoilme-gemma-2-9b-v0.3.json
+++ b/data/models/recoilme_recoilme-gemma-2-9b-v0.3.json
@@ -5,7 +5,7 @@
     "developer": "recoilme",
     "inference_platform": "unknown",
     "additional_details": {
-      "precision": "bfloat16",
+      "precision": "float16",
       "architecture": "Gemma2ForCausalLM",
       "params_billions": "10.159"
     }
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5761
+            "score": 0.7439
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.602
+            "score": 0.5993
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1888
+            "score": 0.0876
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3372
+            "score": 0.3238
           }
         },
         {
@@ -116,7 +116,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4632
+            "score": 0.4204
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4039
+            "score": 0.4072
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7439
+            "score": 0.5761
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5993
+            "score": 0.602
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0876
+            "score": 0.1888
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3238
+            "score": 0.3372
           }
         },
         {
@@ -246,7 +246,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4204
+            "score": 0.4632
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4072
+            "score": 0.4039
           }
         }
       ],
diff --git a/data/models/replete-ai_replete-llm-qwen2-7b.json b/data/models/replete-ai_replete-llm-qwen2-7b.json
index 627d67572ee0cd0135e173767115d5ee7360b5e6..e51b10d1bb4ff7d76603042a5cdf25b16b9bc87f 100644
--- a/data/models/replete-ai_replete-llm-qwen2-7b.json
+++ b/data/models/replete-ai_replete-llm-qwen2-7b.json
@@ -5,7 +5,7 @@
     "developer": "Replete-AI",
     "inference_platform": "unknown",
     "additional_details": {
-      "precision": "float16",
+      "precision": "bfloat16",
       "architecture": "Qwen2ForCausalLM",
       "params_billions": "7.616"
     }
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0905
+            "score": 0.0932
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2985
+            "score": 0.2977
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2534
+            "score": 0.2475
           }
         },
         {
@@ -116,7 +116,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3848
+            "score": 0.3941
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1158
+            "score": 0.1157
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0932
+            "score": 0.0905
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2977
+            "score": 0.2985
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2475
+            "score": 0.2534
           }
         },
         {
@@ -246,7 +246,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3941
+            "score": 0.3848
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1157
+            "score": 0.1158
           }
         }
       ],
diff --git a/data/models/riaz_finellama-3.1-8b.json b/data/models/riaz_finellama-3.1-8b.json
index 926e4908b22e1e63c1ff9b2a4076f85fbbd8288e..554fa555a5c7288aadab0b51655132daffa7eed6 100644
--- a/data/models/riaz_finellama-3.1-8b.json
+++ b/data/models/riaz_finellama-3.1-8b.json
@@ -5,7 +5,7 @@
     "developer": "riaz",
     "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": 0.4137
+            "score": 0.4373
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4565
+            "score": 0.4586
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0453
+            "score": 0.0514
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.276
+            "score": 0.2752
           }
         },
         {
@@ -116,7 +116,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3776
+            "score": 0.3763
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2978
+            "score": 0.2964
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4373
+            "score": 0.4137
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4586
+            "score": 0.4565
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0514
+            "score": 0.0453
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2752
+            "score": 0.276
           }
         },
         {
@@ -246,7 +246,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3763
+            "score": 0.3776
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2964
+            "score": 0.2978
           }
         }
       ],
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 9d341a3c927e4d25f7836c99807ee069a16cbedc..12ab734b7e3e0cffe5b67bb178df3f51d09ec598 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": "bfloat16",
+      "precision": "float16",
       "architecture": "Qwen2ForCausalLM",
       "params_billions": "3.397"
     }
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2595
+            "score": 0.2566
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3884
+            "score": 0.39
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0914
+            "score": 0.1208
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2743
+            "score": 0.2626
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2719
+            "score": 0.2741
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2566
+            "score": 0.2595
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.39
+            "score": 0.3884
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1208
+            "score": 0.0914
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2626
+            "score": 0.2743
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2741
+            "score": 0.2719
           }
         }
       ],
diff --git a/data/models/sao10k_l3-70b-euryale-v2.1.json b/data/models/sao10k_l3-70b-euryale-v2.1.json
index c24d09a959df8d13e2602095ebcf1b7a3f8d330c..66fd342cda2fcd43939fb102adcaae988f1eb857 100644
--- a/data/models/sao10k_l3-70b-euryale-v2.1.json
+++ b/data/models/sao10k_l3-70b-euryale-v2.1.json
@@ -5,7 +5,7 @@
     "developer": "Sao10K",
     "inference_platform": "unknown",
     "additional_details": {
-      "precision": "bfloat16",
+      "precision": "float16",
       "architecture": "LlamaForCausalLM",
       "params_billions": "70.554"
     }
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7384
+            "score": 0.7281
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6471
+            "score": 0.6503
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2137
+            "score": 0.2243
           }
         },
         {
@@ -116,7 +116,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4209
+            "score": 0.4196
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5104
+            "score": 0.5096
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7281
+            "score": 0.7384
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6503
+            "score": 0.6471
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2243
+            "score": 0.2137
           }
         },
         {
@@ -246,7 +246,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4196
+            "score": 0.4209
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5096
+            "score": 0.5104
           }
         }
       ],
diff --git a/data/models/shikaichen_ldl-reward-gemma-2-27b-v0.1.json b/data/models/shikaichen_ldl-reward-gemma-2-27b-v0.1.json
index 988f599afd76311b87e49f16160d0ca534436cdd..4a85b178092e7e5acaf395eb054cb8adc61e2891 100644
--- a/data/models/shikaichen_ldl-reward-gemma-2-27b-v0.1.json
+++ b/data/models/shikaichen_ldl-reward-gemma-2-27b-v0.1.json
@@ -9,10 +9,10 @@
   },
   "evaluations": [
     {
-      "evaluation_id": "reward-bench-2/ShikaiChen_LDL-Reward-Gemma-2-27B-v0.1/1766412838.146816",
+      "evaluation_id": "reward-bench/ShikaiChen_LDL-Reward-Gemma-2-27B-v0.1/1766412838.146816",
       "retrieved_timestamp": "1766412838.146816",
       "source_metadata": {
-        "source_name": "RewardBench 2",
+        "source_name": "RewardBench",
         "source_type": "documentation",
         "source_organization_name": "Allen Institute for AI",
         "source_organization_url": "https://allenai.org",
@@ -31,104 +31,128 @@
         {
           "evaluation_name": "Score",
           "metric_config": {
-            "evaluation_description": "Overall RewardBench 2 Score (mean of all metrics)",
+            "evaluation_description": "Overall RewardBench Score",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7249
+            "score": 0.9499
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Factuality",
+          "evaluation_name": "Chat",
           "metric_config": {
-            "evaluation_description": "Factuality score - measures factual accuracy",
+            "evaluation_description": "Chat accuracy - includes easy chat subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7558
+            "score": 0.9637
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Precise IF",
+          "evaluation_name": "Chat Hard",
           "metric_config": {
-            "evaluation_description": "Precise Instruction Following score",
+            "evaluation_description": "Chat Hard accuracy - includes hard chat subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.35
+            "score": 0.9079
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Math",
+          "evaluation_name": "Safety",
           "metric_config": {
-            "evaluation_description": "Math score - measures mathematical reasoning",
+            "evaluation_description": "Safety accuracy - includes safety subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6448
+            "score": 0.9378
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Safety",
+          "evaluation_name": "Reasoning",
           "metric_config": {
-            "evaluation_description": "Safety score - measures safety awareness",
+            "evaluation_description": "Reasoning accuracy - includes code and math subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9222
+            "score": 0.9903
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
-        },
+        }
+      ],
+      "detailed_evaluation_results": null,
+      "generation_config": null
+    },
+    {
+      "evaluation_id": "reward-bench-2/ShikaiChen_LDL-Reward-Gemma-2-27B-v0.1/1766412838.146816",
+      "retrieved_timestamp": "1766412838.146816",
+      "source_metadata": {
+        "source_name": "RewardBench 2",
+        "source_type": "documentation",
+        "source_organization_name": "Allen Institute for AI",
+        "source_organization_url": "https://allenai.org",
+        "evaluator_relationship": "third_party"
+      },
+      "eval_library": {
+        "name": "rewardbench",
+        "version": "0.1.3",
+        "additional_details": {
+          "subsets": "Chat, Chat Hard, Safety, Reasoning",
+          "hf_space": "allenai/reward-bench"
+        }
+      },
+      "benchmark": "reward-bench",
+      "evaluation_results": [
         {
-          "evaluation_name": "Focus",
+          "evaluation_name": "Score",
           "metric_config": {
-            "evaluation_description": "Focus score - measures response focus",
+            "evaluation_description": "Overall RewardBench 2 Score (mean of all metrics)",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9131
+            "score": 0.7249
           },
           "source_data": {
             "dataset_name": "RewardBench 2",
@@ -137,135 +161,111 @@
           }
         },
         {
-          "evaluation_name": "Ties",
+          "evaluation_name": "Factuality",
           "metric_config": {
-            "evaluation_description": "Ties score - ability to identify tie cases",
+            "evaluation_description": "Factuality score - measures factual accuracy",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7633
+            "score": 0.7558
           },
           "source_data": {
             "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
             "hf_repo": "allenai/reward-bench-2-results"
           }
-        }
-      ],
-      "detailed_evaluation_results": null,
-      "generation_config": null
-    },
-    {
-      "evaluation_id": "reward-bench/ShikaiChen_LDL-Reward-Gemma-2-27B-v0.1/1766412838.146816",
-      "retrieved_timestamp": "1766412838.146816",
-      "source_metadata": {
-        "source_name": "RewardBench",
-        "source_type": "documentation",
-        "source_organization_name": "Allen Institute for AI",
-        "source_organization_url": "https://allenai.org",
-        "evaluator_relationship": "third_party"
-      },
-      "eval_library": {
-        "name": "rewardbench",
-        "version": "0.1.3",
-        "additional_details": {
-          "subsets": "Chat, Chat Hard, Safety, Reasoning",
-          "hf_space": "allenai/reward-bench"
-        }
-      },
-      "benchmark": "reward-bench",
-      "evaluation_results": [
+        },
         {
-          "evaluation_name": "Score",
+          "evaluation_name": "Precise IF",
           "metric_config": {
-            "evaluation_description": "Overall RewardBench Score",
+            "evaluation_description": "Precise Instruction Following score",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9499
+            "score": 0.35
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Chat",
+          "evaluation_name": "Math",
           "metric_config": {
-            "evaluation_description": "Chat accuracy - includes easy chat subsets",
+            "evaluation_description": "Math score - measures mathematical reasoning",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9637
+            "score": 0.6448
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Chat Hard",
+          "evaluation_name": "Safety",
           "metric_config": {
-            "evaluation_description": "Chat Hard accuracy - includes hard chat subsets",
+            "evaluation_description": "Safety score - measures safety awareness",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9079
+            "score": 0.9222
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Safety",
+          "evaluation_name": "Focus",
           "metric_config": {
-            "evaluation_description": "Safety accuracy - includes safety subsets",
+            "evaluation_description": "Focus score - measures response focus",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9378
+            "score": 0.9131
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Reasoning",
+          "evaluation_name": "Ties",
           "metric_config": {
-            "evaluation_description": "Reasoning accuracy - includes code and math subsets",
+            "evaluation_description": "Ties score - ability to identify tie cases",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9903
+            "score": 0.7633
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         }
       ],
diff --git a/data/models/skywork_skywork-reward-gemma-2-27b-v0.2.json b/data/models/skywork_skywork-reward-gemma-2-27b-v0.2.json
index 52952d2b07ce3bbc9c007749585e45b758ae4213..4109d07feac30d842a656539e17ae764cf441c79 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/Skywork_Skywork-Reward-Gemma-2-27B-v0.2/1766412838.146816",
+      "evaluation_id": "reward-bench-2/Skywork_Skywork-Reward-Gemma-2-27B-v0.2/1766412838.146816",
       "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",
@@ -164,128 +164,104 @@
         {
           "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": 0.9426
+            "score": 0.7531
           },
           "source_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": 0.7674
           },
           "source_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": 0.8991
+            "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": "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": 0.9297
+            "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": "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": 0.9807
+            "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"
           }
-        }
-      ],
-      "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": "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": 0.7531
+            "score": 0.9172
           },
           "source_data": {
             "dataset_name": "RewardBench 2",
@@ -294,111 +270,135 @@
           }
         },
         {
-          "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": 0.7674
+            "score": 0.8182
           },
           "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": "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": 0.375
+            "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": "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": 0.6721
+            "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": 0.9689
+            "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": "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": 0.9172
+            "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": "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": 0.8182
+            "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"
           }
         }
       ],
diff --git a/data/models/tanliboy_lambda-gemma-2-9b-dpo.json b/data/models/tanliboy_lambda-gemma-2-9b-dpo.json
index 7fb384620bce09b34b0d31ff763d2b1e971d0558..5d50cd0f56f0ac33470efc8c81f51c02a702598e 100644
--- a/data/models/tanliboy_lambda-gemma-2-9b-dpo.json
+++ b/data/models/tanliboy_lambda-gemma-2-9b-dpo.json
@@ -5,7 +5,7 @@
     "developer": "tanliboy",
     "inference_platform": "unknown",
     "additional_details": {
-      "precision": "bfloat16",
+      "precision": "float16",
       "architecture": "Gemma2ForCausalLM",
       "params_billions": "9.242"
     }
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1829
+            "score": 0.4501
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5488
+            "score": 0.5472
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0
+            "score": 0.0944
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3104
+            "score": 0.3138
           }
         },
         {
@@ -116,7 +116,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4056
+            "score": 0.4017
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3805
+            "score": 0.3792
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4501
+            "score": 0.1829
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5472
+            "score": 0.5488
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0944
+            "score": 0.0
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3138
+            "score": 0.3104
           }
         },
         {
@@ -246,7 +246,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4017
+            "score": 0.4056
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3792
+            "score": 0.3805
           }
         }
       ],
diff --git a/data/models/valiantlabs_llama3.1-8b-shiningvaliant2.json b/data/models/valiantlabs_llama3.1-8b-shiningvaliant2.json
index 0736460b872bea97a209be68cef1f113fa7d9f3d..f3e37b204fa779a9e21a0521a813b464c3fe641b 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": "float16",
+      "precision": "bfloat16",
       "architecture": "LlamaForCausalLM",
       "params_billions": "8.03"
     }
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2678
+            "score": 0.6496
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4429
+            "score": 0.4774
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0521
+            "score": 0.0566
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.302
+            "score": 0.3104
           }
         },
         {
@@ -116,7 +116,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3959
+            "score": 0.3909
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2927
+            "score": 0.3382
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6496
+            "score": 0.2678
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4774
+            "score": 0.4429
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0566
+            "score": 0.0521
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3104
+            "score": 0.302
           }
         },
         {
@@ -246,7 +246,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3909
+            "score": 0.3959
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3382
+            "score": 0.2927
           }
         }
       ],
diff --git a/data/models/weqweasdas_hh_rlhf_rm_open_llama_3b.json b/data/models/weqweasdas_hh_rlhf_rm_open_llama_3b.json
index f9d2b14f0a0f79f11e39957c0f38b89aa1e78ac9..564c2ceeb0768d947ec7e8507c351558f76e3907 100644
--- a/data/models/weqweasdas_hh_rlhf_rm_open_llama_3b.json
+++ b/data/models/weqweasdas_hh_rlhf_rm_open_llama_3b.json
@@ -9,10 +9,10 @@
   },
   "evaluations": [
     {
-      "evaluation_id": "reward-bench/weqweasdas_hh_rlhf_rm_open_llama_3b/1766412838.146816",
+      "evaluation_id": "reward-bench-2/weqweasdas_hh_rlhf_rm_open_llama_3b/1766412838.146816",
       "retrieved_timestamp": "1766412838.146816",
       "source_metadata": {
-        "source_name": "RewardBench",
+        "source_name": "RewardBench 2",
         "source_type": "documentation",
         "source_organization_name": "Allen Institute for AI",
         "source_organization_url": "https://allenai.org",
@@ -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": 0.5027
+            "score": 0.2498
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Chat",
+          "evaluation_name": "Factuality",
           "metric_config": {
-            "evaluation_description": "Chat accuracy - includes easy chat subsets",
+            "evaluation_description": "Factuality score - measures factual accuracy",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.8184
+            "score": 0.3642
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Chat Hard",
+          "evaluation_name": "Precise IF",
           "metric_config": {
-            "evaluation_description": "Chat Hard accuracy - includes hard chat subsets",
+            "evaluation_description": "Precise Instruction Following score",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3728
+            "score": 0.275
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
+          }
+        },
+        {
+          "evaluation_name": "Math",
+          "metric_config": {
+            "evaluation_description": "Math score - measures mathematical reasoning",
+            "lower_is_better": false,
+            "score_type": "continuous",
+            "min_score": 0.0,
+            "max_score": 1.0
+          },
+          "score_details": {
+            "score": 0.3497
+          },
+          "source_data": {
+            "dataset_name": "RewardBench 2",
+            "source_type": "hf_dataset",
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
           "evaluation_name": "Safety",
           "metric_config": {
-            "evaluation_description": "Safety accuracy - includes safety subsets",
+            "evaluation_description": "Safety score - measures safety awareness",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4149
+            "score": 0.24
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Reasoning",
+          "evaluation_name": "Focus",
           "metric_config": {
-            "evaluation_description": "Reasoning accuracy - includes code and math subsets",
+            "evaluation_description": "Focus score - measures response focus",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3281
+            "score": 0.2384
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Prior Sets (0.5 weight)",
+          "evaluation_name": "Ties",
           "metric_config": {
-            "evaluation_description": "Prior Sets score (weighted 0.5) - includes test sets",
+            "evaluation_description": "Ties score - ability to identify tie cases",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6564
+            "score": 0.0315
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         }
       ],
@@ -141,10 +159,10 @@
       "generation_config": null
     },
     {
-      "evaluation_id": "reward-bench-2/weqweasdas_hh_rlhf_rm_open_llama_3b/1766412838.146816",
+      "evaluation_id": "reward-bench/weqweasdas_hh_rlhf_rm_open_llama_3b/1766412838.146816",
       "retrieved_timestamp": "1766412838.146816",
       "source_metadata": {
-        "source_name": "RewardBench 2",
+        "source_name": "RewardBench",
         "source_type": "documentation",
         "source_organization_name": "Allen Institute for AI",
         "source_organization_url": "https://allenai.org",
@@ -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": 0.2498
-          },
-          "source_data": {
-            "dataset_name": "RewardBench 2",
-            "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
-          }
-        },
-        {
-          "evaluation_name": "Factuality",
-          "metric_config": {
-            "evaluation_description": "Factuality score - measures factual accuracy",
+            "evaluation_description": "Overall RewardBench Score",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3642
+            "score": 0.5027
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Precise IF",
+          "evaluation_name": "Chat",
           "metric_config": {
-            "evaluation_description": "Precise Instruction Following score",
+            "evaluation_description": "Chat accuracy - includes easy chat subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.275
+            "score": 0.8184
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Math",
+          "evaluation_name": "Chat Hard",
           "metric_config": {
-            "evaluation_description": "Math score - measures mathematical reasoning",
+            "evaluation_description": "Chat Hard accuracy - includes hard chat subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3497
+            "score": 0.3728
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
           "evaluation_name": "Safety",
           "metric_config": {
-            "evaluation_description": "Safety score - measures safety awareness",
+            "evaluation_description": "Safety accuracy - includes safety subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.24
+            "score": 0.4149
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Focus",
+          "evaluation_name": "Reasoning",
           "metric_config": {
-            "evaluation_description": "Focus score - measures response focus",
+            "evaluation_description": "Reasoning accuracy - includes code and math subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2384
+            "score": 0.3281
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Ties",
+          "evaluation_name": "Prior Sets (0.5 weight)",
           "metric_config": {
-            "evaluation_description": "Ties score - ability to identify tie cases",
+            "evaluation_description": "Prior Sets score (weighted 0.5) - includes test sets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0315
+            "score": 0.6564
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         }
       ],
diff --git a/data/models/weqweasdas_rm-gemma-7b.json b/data/models/weqweasdas_rm-gemma-7b.json
index 9c3f18f2e5d3851df32fe75b7866a4a718dea91c..6b6f7087683616d43cac5b096d07a117476b2184 100644
--- a/data/models/weqweasdas_rm-gemma-7b.json
+++ b/data/models/weqweasdas_rm-gemma-7b.json
@@ -9,10 +9,10 @@
   },
   "evaluations": [
     {
-      "evaluation_id": "reward-bench/weqweasdas_RM-Gemma-7B/1766412838.146816",
+      "evaluation_id": "reward-bench-2/weqweasdas_RM-Gemma-7B/1766412838.146816",
       "retrieved_timestamp": "1766412838.146816",
       "source_metadata": {
-        "source_name": "RewardBench",
+        "source_name": "RewardBench 2",
         "source_type": "documentation",
         "source_organization_name": "Allen Institute for AI",
         "source_organization_url": "https://allenai.org",
@@ -31,109 +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": 0.6967
+            "score": 0.4826
           },
           "source_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": 0.4926
           },
           "source_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": 0.4978
+            "score": 0.3937
           },
           "source_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": 0.5784
+            "score": 0.4822
           },
           "source_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": 0.7362
+            "score": 0.497
           },
           "source_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": 0.7069
+            "score": 0.4232
           },
           "source_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/weqweasdas_RM-Gemma-7B/1766412838.146816",
+      "evaluation_id": "reward-bench/weqweasdas_RM-Gemma-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",
@@ -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": 0.4826
-          },
-          "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": 0.4926
+            "score": 0.6967
           },
           "source_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": 0.3937
+            "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": 0.6066
+            "score": 0.4978
           },
           "source_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": 0.4822
+            "score": 0.5784
           },
           "source_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": 0.497
+            "score": 0.7362
           },
           "source_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": 0.4232
+            "score": 0.7069
           },
           "source_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/xai_grok-3-mini.json b/data/models/xai_grok-3-mini.json
index 7fda2d0643a4e1f5eb9d98f1dc44e9ec85970d5d..6f7e913322e4d12afd1b4e9815b3c829b5eb051d 100644
--- a/data/models/xai_grok-3-mini.json
+++ b/data/models/xai_grok-3-mini.json
@@ -10,8 +10,8 @@
   },
   "evaluations": [
     {
-      "evaluation_id": "global-mmlu-lite/xai_grok-3-mini/1773936496.366405",
-      "retrieved_timestamp": "1773936496.366405",
+      "evaluation_id": "global-mmlu-lite/xai_grok-3-mini/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-3-mini/1773936583.743359",
-      "retrieved_timestamp": "1773936583.743359",
+      "evaluation_id": "global-mmlu-lite/xai_grok-3-mini/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 1a7ae0a5e37faeab9841b8816b2f9d9332f7d639..2396de921bef3d760583d06f283159a7a4b7cc87 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": "Terminus 2",
-      "agent_organization": "Terminal Bench"
+      "agent_name": "OpenHands",
+      "agent_organization": "OpenHands"
     }
   },
   "evaluations": [
     {
-      "evaluation_id": "terminal-bench-2.0/terminus-2__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",
@@ -34,7 +34,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-10-31",
+          "evaluation_timestamp": "2025-11-02",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -43,17 +43,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 23.1,
+            "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 \"Terminus 2\" -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": [
                   {
@@ -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 \"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": [
               {
@@ -84,7 +84,7 @@
       }
     },
     {
-      "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",
@@ -108,7 +108,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-11-02",
+          "evaluation_timestamp": "2025-10-31",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -117,17 +117,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 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": [
                   {
@@ -144,7 +144,7 @@
       "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": [
               {
diff --git a/data/models/xai_grok-code-fast-1.json b/data/models/xai_grok-code-fast-1.json
index 80a497dcbe0e067252e23ff5d2567dcecf97e827..3dead5de67b9b087729b3bc778973bf9f0bdd596 100644
--- a/data/models/xai_grok-code-fast-1.json
+++ b/data/models/xai_grok-code-fast-1.json
@@ -4,13 +4,13 @@
     "id": "xai/grok-code-fast-1",
     "developer": "xAI",
     "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__grok-code-fast-1/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/terminus-2__grok-code-fast-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": "2025-11-03",
+          "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": 25.8,
+            "score": 14.2,
             "uncertainty": {
               "standard_error": {
-                "value": 2.6
+                "value": 2.5
               },
               "num_samples": 435
             }
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Mini-SWE-Agent\" -m \"Grok Code Fast 1\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"Grok Code Fast 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 \"Mini-SWE-Agent\" -m \"Grok Code Fast 1\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"Grok Code Fast 1\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -84,7 +84,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/terminus-2__grok-code-fast-1/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/mini-swe-agent__grok-code-fast-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": "2025-11-03",
           "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": 14.2,
+            "score": 25.8,
             "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 \"Grok Code Fast 1\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Mini-SWE-Agent\" -m \"Grok Code Fast 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 \"Grok Code Fast 1\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Mini-SWE-Agent\" -m \"Grok Code Fast 1\" -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 1a70a6eb9b375af7d3ae622e407043222ccb78a0..baae674a05af479a549c721b22d1c0240e173193 100644
--- a/data/models/yam-peleg_hebrew-mistral-7b-200k.json
+++ b/data/models/yam-peleg_hebrew-mistral-7b-200k.json
@@ -5,7 +5,7 @@
     "developer": "yam-peleg",
     "inference_platform": "unknown",
     "additional_details": {
-      "precision": "bfloat16",
+      "precision": "float16",
       "architecture": "MistralForCausalLM",
       "params_billions": "7.504"
     }
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.177
+            "score": 0.1856
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3411
+            "score": 0.4149
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.031
+            "score": 0.0234
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2534
+            "score": 0.276
           }
         },
         {
@@ -116,7 +116,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.374
+            "score": 0.3765
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2529
+            "score": 0.2573
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1856
+            "score": 0.177
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4149
+            "score": 0.3411
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0234
+            "score": 0.031
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.276
+            "score": 0.2534
           }
         },
         {
@@ -246,7 +246,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3765
+            "score": 0.374
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2573
+            "score": 0.2529
           }
         }
       ],