diff --git a/data/benchmarks/appworld_test_normal.json b/data/benchmarks/appworld_test_normal.json
index 4b1f2e226ce0f177163e0b4f9252a3d5461ce07f..c94d49539b453c8b9bbc41ff7e62e5792c6b9b48 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": 0.66
+        "appworld/test_normal": 0.68
       }
     },
     {
@@ -21,7 +21,7 @@
       "name": "gpt-5.2-2025-12-11",
       "developer": "OpenAI",
       "scores": {
-        "appworld/test_normal": 0.071
+        "appworld/test_normal": 0.0
       }
     }
   ]
diff --git a/data/benchmarks/browsecompplus.json b/data/benchmarks/browsecompplus.json
index 613b29235acc848a4b6fbc21b6e89e5e195bd256..74d10ea2ba0e91972d3d0e7424a2805813842fd2 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": 0.46
+        "browsecompplus": 0.43
       }
     }
   ]
diff --git a/data/benchmarks/hfopenllm_v2.json b/data/benchmarks/hfopenllm_v2.json
index f63d6b4e97df8ea6a39802305cc7efdb2683daed..ad203e0b72f6caf04084e48c1b921149ab76e134 100644
--- a/data/benchmarks/hfopenllm_v2.json
+++ b/data/benchmarks/hfopenllm_v2.json
@@ -3047,12 +3047,12 @@
       "name": "AetherTOT",
       "developer": "Daemontatox",
       "scores": {
-        "IFEval": 0.4383,
-        "BBH": 0.5034,
-        "MATH Level 5": 0.1443,
+        "IFEval": 0.4398,
+        "BBH": 0.5066,
+        "MATH Level 5": 0.1488,
         "GPQA": 0.3238,
-        "MUSR": 0.4052,
-        "MMLU-PRO": 0.3778
+        "MUSR": 0.4079,
+        "MMLU-PRO": 0.3804
       }
     },
     {
@@ -3125,12 +3125,12 @@
       "name": "DocumentCogito",
       "developer": "Daemontatox",
       "scores": {
-        "IFEval": 0.5064,
-        "BBH": 0.5112,
-        "MATH Level 5": 0.1631,
-        "GPQA": 0.3163,
-        "MUSR": 0.3973,
-        "MMLU-PRO": 0.3802
+        "IFEval": 0.777,
+        "BBH": 0.5187,
+        "MATH Level 5": 0.2198,
+        "GPQA": 0.2936,
+        "MUSR": 0.3911,
+        "MMLU-PRO": 0.3738
       }
     },
     {
@@ -4009,12 +4009,12 @@
       "name": "Llama-3.2-1B-SPIN-iter0",
       "developer": "DavieLion",
       "scores": {
-        "IFEval": 0.1507,
-        "BBH": 0.293,
-        "MATH Level 5": 0.0,
-        "GPQA": 0.2534,
+        "IFEval": 0.1549,
+        "BBH": 0.2937,
+        "MATH Level 5": 0.006,
+        "GPQA": 0.2576,
         "MUSR": 0.3565,
-        "MMLU-PRO": 0.1125
+        "MMLU-PRO": 0.1128
       }
     },
     {
@@ -4321,12 +4321,12 @@
       "name": "Llama-3.1-8b-ITA",
       "developer": "DeepMount00",
       "scores": {
-        "IFEval": 0.5365,
-        "BBH": 0.517,
-        "MATH Level 5": 0.1707,
-        "GPQA": 0.3062,
-        "MUSR": 0.4487,
-        "MMLU-PRO": 0.396
+        "IFEval": 0.7917,
+        "BBH": 0.5109,
+        "MATH Level 5": 0.1088,
+        "GPQA": 0.2878,
+        "MUSR": 0.4136,
+        "MMLU-PRO": 0.3876
       }
     },
     {
@@ -7025,12 +7025,12 @@
       "name": "Fireball-Meta-Llama-3.1-8B-Instruct-Agent-0.003-128K-code-ds-auto",
       "developer": "EpistemeAI",
       "scores": {
-        "IFEval": 0.7305,
-        "BBH": 0.4649,
-        "MATH Level 5": 0.1397,
-        "GPQA": 0.2659,
-        "MUSR": 0.3209,
-        "MMLU-PRO": 0.348
+        "IFEval": 0.7207,
+        "BBH": 0.461,
+        "MATH Level 5": 0.1314,
+        "GPQA": 0.2701,
+        "MUSR": 0.3432,
+        "MMLU-PRO": 0.3354
       }
     },
     {
@@ -7675,12 +7675,12 @@
       "name": "Herplete-LLM-Llama-3.1-8b",
       "developer": "Etherll",
       "scores": {
-        "IFEval": 0.6106,
-        "BBH": 0.5347,
-        "MATH Level 5": 0.1548,
-        "GPQA": 0.3146,
-        "MUSR": 0.3991,
-        "MMLU-PRO": 0.3752
+        "IFEval": 0.4672,
+        "BBH": 0.5013,
+        "MATH Level 5": 0.0279,
+        "GPQA": 0.2861,
+        "MUSR": 0.386,
+        "MMLU-PRO": 0.3482
       }
     },
     {
@@ -8455,12 +8455,12 @@
       "name": "Josiefied-Qwen2.5-0.5B-Instruct-abliterated-v1",
       "developer": "Goekdeniz-Guelmez",
       "scores": {
-        "IFEval": 0.3417,
-        "BBH": 0.3292,
-        "MATH Level 5": 0.0023,
-        "GPQA": 0.2576,
-        "MUSR": 0.3249,
-        "MMLU-PRO": 0.1638
+        "IFEval": 0.3472,
+        "BBH": 0.3268,
+        "MATH Level 5": 0.0891,
+        "GPQA": 0.2517,
+        "MUSR": 0.3262,
+        "MMLU-PRO": 0.1641
       }
     },
     {
@@ -8572,12 +8572,12 @@
       "name": "josie-7b-v6.0-step2000",
       "developer": "Goekdeniz-Guelmez",
       "scores": {
-        "IFEval": 0.7628,
-        "BBH": 0.5098,
-        "MATH Level 5": 0.0,
-        "GPQA": 0.2802,
-        "MUSR": 0.4579,
-        "MMLU-PRO": 0.4033
+        "IFEval": 0.7598,
+        "BBH": 0.5107,
+        "MATH Level 5": 0.4237,
+        "GPQA": 0.2768,
+        "MUSR": 0.4539,
+        "MMLU-PRO": 0.4012
       }
     },
     {
@@ -8728,12 +8728,12 @@
       "name": "Gemma-Ko-Merge-PEFT",
       "developer": "Gunulhona",
       "scores": {
-        "IFEval": 0.288,
-        "BBH": 0.5154,
+        "IFEval": 0.4441,
+        "BBH": 0.4863,
         "MATH Level 5": 0.0,
-        "GPQA": 0.3247,
-        "MUSR": 0.408,
-        "MMLU-PRO": 0.3817
+        "GPQA": 0.307,
+        "MUSR": 0.3986,
+        "MMLU-PRO": 0.3098
       }
     },
     {
@@ -9170,12 +9170,12 @@
       "name": "SmolLM2-360M-Instruct",
       "developer": "HuggingFaceTB",
       "scores": {
-        "IFEval": 0.083,
-        "BBH": 0.3053,
-        "MATH Level 5": 0.0083,
-        "GPQA": 0.2651,
-        "MUSR": 0.3423,
-        "MMLU-PRO": 0.1126
+        "IFEval": 0.3842,
+        "BBH": 0.3144,
+        "MATH Level 5": 0.0151,
+        "GPQA": 0.255,
+        "MUSR": 0.3461,
+        "MMLU-PRO": 0.1117
       }
     },
     {
@@ -13057,12 +13057,12 @@
       "name": "SpydazWeb_AI_HumanAI_012_INSTRUCT_XA",
       "developer": "LeroyDyer",
       "scores": {
-        "IFEval": 0.3579,
-        "BBH": 0.4477,
-        "MATH Level 5": 0.0423,
-        "GPQA": 0.3096,
-        "MUSR": 0.4134,
-        "MMLU-PRO": 0.2376
+        "IFEval": 0.3798,
+        "BBH": 0.4483,
+        "MATH Level 5": 0.04,
+        "GPQA": 0.3129,
+        "MUSR": 0.4148,
+        "MMLU-PRO": 0.2389
       }
     },
     {
@@ -14305,12 +14305,12 @@
       "name": "Llama-3-8B-Magpie-Align-v0.1",
       "developer": "Magpie-Align",
       "scores": {
-        "IFEval": 0.4027,
-        "BBH": 0.4789,
-        "MATH Level 5": 0.0461,
-        "GPQA": 0.2768,
-        "MUSR": 0.3087,
-        "MMLU-PRO": 0.3001
+        "IFEval": 0.4118,
+        "BBH": 0.4811,
+        "MATH Level 5": 0.034,
+        "GPQA": 0.2752,
+        "MUSR": 0.3047,
+        "MMLU-PRO": 0.3006
       }
     },
     {
@@ -17204,12 +17204,12 @@
       "name": "code-yi",
       "developer": "Omkar1102",
       "scores": {
-        "IFEval": 0.2148,
-        "BBH": 0.276,
+        "IFEval": 0.2254,
+        "BBH": 0.275,
         "MATH Level 5": 0.0,
-        "GPQA": 0.2508,
-        "MUSR": 0.3802,
-        "MMLU-PRO": 0.1126
+        "GPQA": 0.2576,
+        "MUSR": 0.3762,
+        "MMLU-PRO": 0.1123
       }
     },
     {
@@ -18141,11 +18141,11 @@
       "developer": "PrimeIntellect",
       "scores": {
         "IFEval": 0.1757,
-        "BBH": 0.274,
+        "BBH": 0.276,
         "MATH Level 5": 0.0,
-        "GPQA": 0.25,
-        "MUSR": 0.3753,
-        "MMLU-PRO": 0.112
+        "GPQA": 0.2534,
+        "MUSR": 0.3339,
+        "MMLU-PRO": 0.1123
       }
     },
     {
@@ -19986,12 +19986,12 @@
       "name": "Replete-LLM-Qwen2-7b",
       "developer": "Replete-AI",
       "scores": {
-        "IFEval": 0.0905,
-        "BBH": 0.2985,
+        "IFEval": 0.0932,
+        "BBH": 0.2977,
         "MATH Level 5": 0.0,
-        "GPQA": 0.2534,
-        "MUSR": 0.3848,
-        "MMLU-PRO": 0.1158
+        "GPQA": 0.2475,
+        "MUSR": 0.3941,
+        "MMLU-PRO": 0.1157
       }
     },
     {
@@ -21130,12 +21130,12 @@
       "name": "L3-70B-Euryale-v2.1",
       "developer": "Sao10K",
       "scores": {
-        "IFEval": 0.7384,
-        "BBH": 0.6471,
-        "MATH Level 5": 0.2137,
+        "IFEval": 0.7281,
+        "BBH": 0.6503,
+        "MATH Level 5": 0.2243,
         "GPQA": 0.3314,
-        "MUSR": 0.4209,
-        "MMLU-PRO": 0.5104
+        "MUSR": 0.4196,
+        "MMLU-PRO": 0.5096
       }
     },
     {
@@ -25069,12 +25069,12 @@
       "name": "Llama3.1-8B-Cobalt",
       "developer": "ValiantLabs",
       "scores": {
-        "IFEval": 0.7168,
-        "BBH": 0.4911,
-        "MATH Level 5": 0.1533,
-        "GPQA": 0.2861,
-        "MUSR": 0.3512,
-        "MMLU-PRO": 0.3663
+        "IFEval": 0.3496,
+        "BBH": 0.4947,
+        "MATH Level 5": 0.1269,
+        "GPQA": 0.3037,
+        "MUSR": 0.3959,
+        "MMLU-PRO": 0.3644
       }
     },
     {
@@ -25121,12 +25121,12 @@
       "name": "Llama3.1-8B-ShiningValiant2",
       "developer": "ValiantLabs",
       "scores": {
-        "IFEval": 0.2678,
-        "BBH": 0.4429,
-        "MATH Level 5": 0.0521,
-        "GPQA": 0.302,
-        "MUSR": 0.3959,
-        "MMLU-PRO": 0.2927
+        "IFEval": 0.6496,
+        "BBH": 0.4774,
+        "MATH Level 5": 0.0566,
+        "GPQA": 0.3104,
+        "MUSR": 0.3909,
+        "MMLU-PRO": 0.3382
       }
     },
     {
@@ -25654,12 +25654,12 @@
       "name": "Qwen2.5-14B-YOYO-1010",
       "developer": "YOYO-AI",
       "scores": {
-        "IFEval": 0.7905,
-        "BBH": 0.6406,
-        "MATH Level 5": 0.0,
-        "GPQA": 0.3163,
-        "MUSR": 0.4181,
-        "MMLU-PRO": 0.4944
+        "IFEval": 0.5899,
+        "BBH": 0.654,
+        "MATH Level 5": 0.4509,
+        "GPQA": 0.3834,
+        "MUSR": 0.4744,
+        "MMLU-PRO": 0.5376
       }
     },
     {
@@ -26889,12 +26889,12 @@
       "name": "Llama-3.1-Storm-8B",
       "developer": "akjindal53244",
       "scores": {
-        "IFEval": 0.8051,
-        "BBH": 0.5189,
-        "MATH Level 5": 0.1722,
-        "GPQA": 0.3263,
+        "IFEval": 0.8033,
+        "BBH": 0.5196,
+        "MATH Level 5": 0.1624,
+        "GPQA": 0.3096,
         "MUSR": 0.4028,
-        "MMLU-PRO": 0.3803
+        "MMLU-PRO": 0.3812
       }
     },
     {
@@ -26954,12 +26954,12 @@
       "name": "Llama-3.1-Tulu-3-8B",
       "developer": "allenai",
       "scores": {
-        "IFEval": 0.8255,
-        "BBH": 0.4061,
-        "MATH Level 5": 0.2115,
-        "GPQA": 0.297,
+        "IFEval": 0.8267,
+        "BBH": 0.405,
+        "MATH Level 5": 0.1964,
+        "GPQA": 0.2987,
         "MUSR": 0.4175,
-        "MMLU-PRO": 0.2821
+        "MMLU-PRO": 0.2827
       }
     },
     {
@@ -28449,11 +28449,11 @@
       "name": "AMD-Llama-135m",
       "developer": "amd",
       "scores": {
-        "IFEval": 0.1842,
-        "BBH": 0.2974,
-        "MATH Level 5": 0.0053,
-        "GPQA": 0.2525,
-        "MUSR": 0.378,
+        "IFEval": 0.1918,
+        "BBH": 0.2969,
+        "MATH Level 5": 0.0076,
+        "GPQA": 0.2584,
+        "MUSR": 0.3846,
         "MMLU-PRO": 0.1169
       }
     },
@@ -28709,12 +28709,12 @@
       "name": "Arcee-Spark",
       "developer": "arcee-ai",
       "scores": {
-        "IFEval": 0.5718,
-        "BBH": 0.5481,
-        "MATH Level 5": 0.114,
-        "GPQA": 0.3062,
-        "MUSR": 0.4008,
-        "MMLU-PRO": 0.3813
+        "IFEval": 0.5621,
+        "BBH": 0.5489,
+        "MATH Level 5": 0.2953,
+        "GPQA": 0.307,
+        "MUSR": 0.4021,
+        "MMLU-PRO": 0.3822
       }
     },
     {
@@ -30360,12 +30360,12 @@
       "name": "Llama-3.2-3B-Deep-Test",
       "developer": "bunnycore",
       "scores": {
-        "IFEval": 0.1775,
-        "BBH": 0.295,
-        "MATH Level 5": 0.0,
-        "GPQA": 0.2517,
-        "MUSR": 0.3647,
-        "MMLU-PRO": 0.1049
+        "IFEval": 0.4652,
+        "BBH": 0.4531,
+        "MATH Level 5": 0.1284,
+        "GPQA": 0.2643,
+        "MUSR": 0.3394,
+        "MMLU-PRO": 0.3152
       }
     },
     {
@@ -31647,12 +31647,12 @@
       "name": "dolphin-2.9.2-Phi-3-Medium-abliterated",
       "developer": "cognitivecomputations",
       "scores": {
-        "IFEval": 0.4124,
-        "BBH": 0.6383,
-        "MATH Level 5": 0.182,
-        "GPQA": 0.3289,
-        "MUSR": 0.4349,
-        "MMLU-PRO": 0.4525
+        "IFEval": 0.3613,
+        "BBH": 0.6123,
+        "MATH Level 5": 0.1239,
+        "GPQA": 0.328,
+        "MUSR": 0.4112,
+        "MMLU-PRO": 0.4494
       }
     },
     {
@@ -34663,12 +34663,12 @@
       "name": "gemma-2-2b",
       "developer": "Google",
       "scores": {
-        "IFEval": 0.1993,
-        "BBH": 0.3656,
-        "MATH Level 5": 0.0287,
+        "IFEval": 0.2018,
+        "BBH": 0.3709,
+        "MATH Level 5": 0.0302,
         "GPQA": 0.2626,
-        "MUSR": 0.4232,
-        "MMLU-PRO": 0.218
+        "MUSR": 0.4219,
+        "MMLU-PRO": 0.2217
       }
     },
     {
@@ -37705,12 +37705,12 @@
       "name": "Kosmos-EVAA-Fusion-8B",
       "developer": "jaspionjader",
       "scores": {
-        "IFEval": 0.4418,
-        "BBH": 0.5406,
-        "MATH Level 5": 0.1352,
-        "GPQA": 0.3062,
+        "IFEval": 0.4345,
+        "BBH": 0.5419,
+        "MATH Level 5": 0.1292,
+        "GPQA": 0.3087,
         "MUSR": 0.4277,
-        "MMLU-PRO": 0.386
+        "MMLU-PRO": 0.3854
       }
     },
     {
@@ -42359,12 +42359,12 @@
       "name": "Mistral-v0.3-7B-ORPO",
       "developer": "llmat",
       "scores": {
-        "IFEval": 0.364,
-        "BBH": 0.4005,
-        "MATH Level 5": 0.0015,
-        "GPQA": 0.2693,
-        "MUSR": 0.3529,
-        "MMLU-PRO": 0.2301
+        "IFEval": 0.377,
+        "BBH": 0.3978,
+        "MATH Level 5": 0.0242,
+        "GPQA": 0.2668,
+        "MUSR": 0.3555,
+        "MMLU-PRO": 0.2278
       }
     },
     {
@@ -43893,12 +43893,12 @@
       "name": "Meta-Llama-3-8B-Instruct",
       "developer": "meta-llama",
       "scores": {
-        "IFEval": 0.7408,
-        "BBH": 0.4989,
-        "MATH Level 5": 0.0869,
-        "GPQA": 0.2592,
-        "MUSR": 0.3568,
-        "MMLU-PRO": 0.3664
+        "IFEval": 0.4782,
+        "BBH": 0.491,
+        "MATH Level 5": 0.0914,
+        "GPQA": 0.2928,
+        "MUSR": 0.3805,
+        "MMLU-PRO": 0.3591
       }
     },
     {
@@ -43984,12 +43984,12 @@
       "name": "Phi-3-mini-4k-instruct",
       "developer": "microsoft",
       "scores": {
-        "IFEval": 0.5477,
-        "BBH": 0.5491,
-        "MATH Level 5": 0.1639,
-        "GPQA": 0.3322,
-        "MUSR": 0.4284,
-        "MMLU-PRO": 0.4022
+        "IFEval": 0.5613,
+        "BBH": 0.5676,
+        "MATH Level 5": 0.1163,
+        "GPQA": 0.3196,
+        "MUSR": 0.395,
+        "MMLU-PRO": 0.3866
       }
     },
     {
@@ -45076,12 +45076,12 @@
       "name": "Mistral-Nemo-Kurdish-Instruct",
       "developer": "nazimali",
       "scores": {
-        "IFEval": 0.4964,
-        "BBH": 0.4699,
-        "MATH Level 5": 0.0045,
-        "GPQA": 0.2827,
-        "MUSR": 0.3979,
-        "MMLU-PRO": 0.3063
+        "IFEval": 0.486,
+        "BBH": 0.4721,
+        "MATH Level 5": 0.0846,
+        "GPQA": 0.2844,
+        "MUSR": 0.4006,
+        "MMLU-PRO": 0.3087
       }
     },
     {
@@ -47611,12 +47611,12 @@
       "name": "wide_3b_sft_stage1.1-ss1-with_generics_intr_math_stories.no_issue",
       "developer": "ontocord",
       "scores": {
-        "IFEval": 0.1128,
-        "BBH": 0.3171,
-        "MATH Level 5": 0.0113,
-        "GPQA": 0.2685,
-        "MUSR": 0.346,
-        "MMLU-PRO": 0.1129
+        "IFEval": 0.1162,
+        "BBH": 0.3184,
+        "MATH Level 5": 0.0076,
+        "GPQA": 0.2634,
+        "MUSR": 0.3447,
+        "MMLU-PRO": 0.1124
       }
     },
     {
@@ -50861,12 +50861,12 @@
       "name": "Oracle-14B",
       "developer": "qingy2019",
       "scores": {
-        "IFEval": 0.2358,
-        "BBH": 0.4612,
-        "MATH Level 5": 0.0642,
-        "GPQA": 0.2576,
-        "MUSR": 0.3717,
-        "MMLU-PRO": 0.2382
+        "IFEval": 0.2401,
+        "BBH": 0.4622,
+        "MATH Level 5": 0.0725,
+        "GPQA": 0.2609,
+        "MUSR": 0.3703,
+        "MMLU-PRO": 0.2379
       }
     },
     {
@@ -50874,12 +50874,12 @@
       "name": "Qwen2.5-Math-14B-Instruct",
       "developer": "qingy2019",
       "scores": {
-        "IFEval": 0.6066,
-        "BBH": 0.635,
-        "MATH Level 5": 0.3716,
-        "GPQA": 0.3725,
+        "IFEval": 0.6005,
+        "BBH": 0.6356,
+        "MATH Level 5": 0.2764,
+        "GPQA": 0.3691,
         "MUSR": 0.4757,
-        "MMLU-PRO": 0.5331
+        "MMLU-PRO": 0.5339
       }
     },
     {
@@ -51459,12 +51459,12 @@
       "name": "FineLlama-3.1-8B",
       "developer": "riaz",
       "scores": {
-        "IFEval": 0.4137,
-        "BBH": 0.4565,
-        "MATH Level 5": 0.0453,
-        "GPQA": 0.276,
-        "MUSR": 0.3776,
-        "MMLU-PRO": 0.2978
+        "IFEval": 0.4373,
+        "BBH": 0.4586,
+        "MATH Level 5": 0.0514,
+        "GPQA": 0.2752,
+        "MUSR": 0.3763,
+        "MMLU-PRO": 0.2964
       }
     },
     {
@@ -53201,12 +53201,12 @@
       "name": "Qwenvergence-14B-v3-Reason",
       "developer": "sometimesanotion",
       "scores": {
-        "IFEval": 0.5278,
-        "BBH": 0.6557,
-        "MATH Level 5": 0.3119,
-        "GPQA": 0.3842,
-        "MUSR": 0.4754,
-        "MMLU-PRO": 0.5396
+        "IFEval": 0.5367,
+        "BBH": 0.6561,
+        "MATH Level 5": 0.358,
+        "GPQA": 0.3867,
+        "MUSR": 0.474,
+        "MMLU-PRO": 0.5395
       }
     },
     {
@@ -53500,12 +53500,12 @@
       "name": "ChatWaifu_v2.0_22B",
       "developer": "spow12",
       "scores": {
-        "IFEval": 0.6511,
-        "BBH": 0.5926,
-        "MATH Level 5": 0.1858,
-        "GPQA": 0.3247,
+        "IFEval": 0.6517,
+        "BBH": 0.5908,
+        "MATH Level 5": 0.2032,
+        "GPQA": 0.3238,
         "MUSR": 0.3842,
-        "MMLU-PRO": 0.3836
+        "MMLU-PRO": 0.3812
       }
     },
     {
@@ -54345,12 +54345,12 @@
       "name": "lambda-gemma-2-9b-dpo",
       "developer": "tanliboy",
       "scores": {
-        "IFEval": 0.1829,
-        "BBH": 0.5488,
-        "MATH Level 5": 0.0,
-        "GPQA": 0.3104,
-        "MUSR": 0.4056,
-        "MMLU-PRO": 0.3805
+        "IFEval": 0.4501,
+        "BBH": 0.5472,
+        "MATH Level 5": 0.0944,
+        "GPQA": 0.3138,
+        "MUSR": 0.4017,
+        "MMLU-PRO": 0.3792
       }
     },
     {
@@ -56997,12 +56997,12 @@
       "name": "BagelMIsteryTour-v2-8x7B",
       "developer": "ycros",
       "scores": {
-        "IFEval": 0.6262,
-        "BBH": 0.5142,
-        "MATH Level 5": 0.0937,
-        "GPQA": 0.3079,
-        "MUSR": 0.4138,
-        "MMLU-PRO": 0.3481
+        "IFEval": 0.5994,
+        "BBH": 0.5159,
+        "MATH Level 5": 0.0785,
+        "GPQA": 0.3045,
+        "MUSR": 0.4203,
+        "MMLU-PRO": 0.3473
       }
     },
     {
diff --git a/data/benchmarks/livecodebenchpro.json b/data/benchmarks/livecodebenchpro.json
index 449e36cb0d36e98776192be2ede4fd274d74ec7e..f8f77204727bc54bca1bbaaa204ca44d2b265f12 100644
--- a/data/benchmarks/livecodebenchpro.json
+++ b/data/benchmarks/livecodebenchpro.json
@@ -255,9 +255,9 @@
       "name": "o4-mini-2025-04-16",
       "developer": "OpenAI",
       "scores": {
-        "Hard Problems": 0.014084507042253521,
-        "Medium Problems": 0.30985915492957744,
-        "Easy Problems": 0.8873239436619719
+        "Hard Problems": 0.0143,
+        "Medium Problems": 0.2923,
+        "Easy Problems": 0.8571
       }
     },
     {
diff --git a/data/benchmarks/reward-bench.json b/data/benchmarks/reward-bench.json
index 083fee6e840e33c85c4fe87b781938b7ad720c00..a29ee6207f83073111bedbdb1ff7d98e527e8df6 100644
--- a/data/benchmarks/reward-bench.json
+++ b/data/benchmarks/reward-bench.json
@@ -81,17 +81,17 @@
       "name": "CIR-AMS/BTRM_Qwen2_7b_0613",
       "developer": "CIR-AMS",
       "scores": {
-        "Score": 0.8172,
+        "Score": 0.5736,
+        "Chat": 0.9749,
+        "Chat Hard": 0.5724,
+        "Safety": 0.7178,
+        "Reasoning": 0.8775,
+        "Prior Sets (0.5 weight)": 0.7029,
         "Factuality": 0.5347,
         "Precise IF": 0.3563,
         "Math": 0.6066,
-        "Safety": 0.9014,
         "Focus": 0.5737,
-        "Ties": 0.6527,
-        "Chat": 0.9749,
-        "Chat Hard": 0.5724,
-        "Reasoning": 0.8775,
-        "Prior Sets (0.5 weight)": 0.7029
+        "Ties": 0.6527
       }
     },
     {
@@ -609,17 +609,17 @@
       "name": "PKU-Alignment/beaver-7b-v1.0-cost",
       "developer": "PKU-Alignment",
       "scores": {
-        "Score": 0.5798,
+        "Score": 0.3332,
+        "Chat": 0.6173,
+        "Chat Hard": 0.4232,
+        "Safety": 0.7589,
+        "Reasoning": 0.5482,
+        "Prior Sets (0.5 weight)": 0.57,
         "Factuality": 0.3263,
         "Precise IF": 0.2313,
         "Math": 0.3989,
-        "Safety": 0.7351,
         "Focus": 0.2939,
-        "Ties": -0.01,
-        "Chat": 0.6173,
-        "Chat Hard": 0.4232,
-        "Reasoning": 0.5482,
-        "Prior Sets (0.5 weight)": 0.57
+        "Ties": -0.01
       }
     },
     {
@@ -938,17 +938,17 @@
       "name": "Ray2333/GRM-llama3-8B-distill",
       "developer": "Ray2333",
       "scores": {
-        "Score": 0.589,
-        "Chat": 0.9832,
-        "Chat Hard": 0.6842,
-        "Safety": 0.7222,
-        "Reasoning": 0.9133,
-        "Prior Sets (0.5 weight)": 0.7209,
+        "Score": 0.8464,
         "Factuality": 0.5874,
         "Precise IF": 0.3875,
         "Math": 0.5902,
+        "Safety": 0.8676,
         "Focus": 0.6727,
-        "Ties": 0.5743
+        "Ties": 0.5743,
+        "Chat": 0.9832,
+        "Chat Hard": 0.6842,
+        "Reasoning": 0.9133,
+        "Prior Sets (0.5 weight)": 0.7209
       }
     },
     {
@@ -1139,16 +1139,16 @@
       "name": "Skywork/Skywork-Reward-Gemma-2-27B",
       "developer": "Skywork",
       "scores": {
-        "Score": 0.938,
+        "Score": 0.7576,
+        "Chat": 0.9581,
+        "Chat Hard": 0.9145,
+        "Safety": 0.9422,
+        "Reasoning": 0.9606,
         "Factuality": 0.7368,
         "Precise IF": 0.4031,
         "Math": 0.7049,
-        "Safety": 0.9189,
         "Focus": 0.9323,
-        "Ties": 0.8261,
-        "Chat": 0.9581,
-        "Chat Hard": 0.9145,
-        "Reasoning": 0.9606
+        "Ties": 0.8261
       }
     },
     {
@@ -1173,16 +1173,16 @@
       "name": "Skywork/Skywork-Reward-Llama-3.1-8B",
       "developer": "Skywork",
       "scores": {
-        "Score": 0.7314,
-        "Chat": 0.9581,
-        "Chat Hard": 0.8728,
-        "Safety": 0.9333,
-        "Reasoning": 0.962,
+        "Score": 0.9252,
         "Factuality": 0.6989,
         "Precise IF": 0.425,
         "Math": 0.6284,
+        "Safety": 0.9081,
         "Focus": 0.9616,
-        "Ties": 0.741
+        "Ties": 0.741,
+        "Chat": 0.9581,
+        "Chat Hard": 0.8728,
+        "Reasoning": 0.962
       }
     },
     {
@@ -1305,16 +1305,16 @@
       "name": "Skywork/Skywork-VL-Reward-7B",
       "developer": "Skywork",
       "scores": {
-        "Score": 0.9007,
+        "Score": 0.6885,
+        "Chat": 0.8994,
+        "Chat Hard": 0.875,
+        "Safety": 0.8911,
+        "Reasoning": 0.9176,
         "Factuality": 0.6063,
         "Precise IF": 0.35,
         "Math": 0.6339,
-        "Safety": 0.9108,
         "Focus": 0.8909,
-        "Ties": 0.7586,
-        "Chat": 0.8994,
-        "Chat Hard": 0.875,
-        "Reasoning": 0.9176
+        "Ties": 0.7586
       }
     },
     {
@@ -1379,10 +1379,10 @@
       "name": "ai2/tulu-2-7b-rm-v0-nectar-binarized-3.8m-check...",
       "developer": "AI2",
       "scores": {
-        "Score": 0.6924,
-        "Chat": 0.9441,
-        "Chat Hard": 0.3575,
-        "Safety": 0.7757
+        "Score": 0.6895,
+        "Chat": 0.9385,
+        "Chat Hard": 0.3706,
+        "Safety": 0.7595
       }
     },
     {
@@ -1477,17 +1477,17 @@
       "name": "allenai/Llama-3.1-Tulu-3-70B-SFT-RM-RB2",
       "developer": "allenai",
       "scores": {
-        "Score": 0.722,
-        "Chat": 0.9693,
-        "Chat Hard": 0.8268,
-        "Safety": 0.8689,
-        "Reasoning": 0.8583,
-        "Prior Sets (0.5 weight)": 0.0,
+        "Score": 0.8892,
         "Factuality": 0.8084,
         "Precise IF": 0.3688,
         "Math": 0.6776,
+        "Safety": 0.9027,
         "Focus": 0.7778,
-        "Ties": 0.8308
+        "Ties": 0.8308,
+        "Chat": 0.9693,
+        "Chat Hard": 0.8268,
+        "Reasoning": 0.8583,
+        "Prior Sets (0.5 weight)": 0.0
       }
     },
     {
@@ -1495,17 +1495,17 @@
       "name": "allenai/Llama-3.1-Tulu-3-8B-DPO-RM-RB2",
       "developer": "allenai",
       "scores": {
-        "Score": 0.8431,
+        "Score": 0.687,
+        "Chat": 0.9553,
+        "Chat Hard": 0.761,
+        "Safety": 0.86,
+        "Reasoning": 0.7898,
+        "Prior Sets (0.5 weight)": 0.0,
         "Factuality": 0.7516,
         "Precise IF": 0.3875,
         "Math": 0.6284,
-        "Safety": 0.8662,
         "Focus": 0.8545,
-        "Ties": 0.6397,
-        "Chat": 0.9553,
-        "Chat Hard": 0.761,
-        "Reasoning": 0.7898,
-        "Prior Sets (0.5 weight)": 0.0
+        "Ties": 0.6397
       }
     },
     {
@@ -3486,17 +3486,17 @@
       "name": "Claude 3 Haiku 20240307",
       "developer": "Anthropic",
       "scores": {
-        "Score": 0.3711,
-        "Chat": 0.9274,
-        "Chat Hard": 0.5197,
-        "Safety": 0.595,
-        "Reasoning": 0.706,
-        "Prior Sets (0.5 weight)": 0.6635,
+        "Score": 0.7289,
         "Factuality": 0.4042,
         "Precise IF": 0.2812,
         "Math": 0.3552,
+        "Safety": 0.7953,
         "Focus": 0.501,
-        "Ties": 0.0899
+        "Ties": 0.0899,
+        "Chat": 0.9274,
+        "Chat Hard": 0.5197,
+        "Reasoning": 0.706,
+        "Prior Sets (0.5 weight)": 0.6635
       }
     },
     {
@@ -3504,16 +3504,16 @@
       "name": "Claude 3 Opus 20240229",
       "developer": "Anthropic",
       "scores": {
-        "Score": 0.8008,
+        "Score": 0.5744,
+        "Chat": 0.9469,
+        "Chat Hard": 0.6031,
+        "Safety": 0.8378,
+        "Reasoning": 0.7868,
         "Factuality": 0.5389,
         "Precise IF": 0.3312,
         "Math": 0.5137,
-        "Safety": 0.8662,
         "Focus": 0.6646,
-        "Ties": 0.5601,
-        "Chat": 0.9469,
-        "Chat Hard": 0.6031,
-        "Reasoning": 0.7868
+        "Ties": 0.5601
       }
     },
     {
@@ -3801,16 +3801,16 @@
       "name": "internlm/internlm2-1_8b-reward",
       "developer": "internlm",
       "scores": {
-        "Score": 0.8217,
+        "Score": 0.3902,
+        "Chat": 0.9358,
+        "Chat Hard": 0.6623,
+        "Safety": 0.4711,
+        "Reasoning": 0.8724,
         "Factuality": 0.2758,
         "Precise IF": 0.3625,
         "Math": 0.4426,
-        "Safety": 0.8162,
         "Focus": 0.596,
-        "Ties": 0.1934,
-        "Chat": 0.9358,
-        "Chat Hard": 0.6623,
-        "Reasoning": 0.8724
+        "Ties": 0.1934
       }
     },
     {
@@ -4014,16 +4014,16 @@
       "name": "nicolinho/QRM-Gemma-2-27B",
       "developer": "nicolinho",
       "scores": {
-        "Score": 0.9444,
+        "Score": 0.7667,
+        "Chat": 0.9665,
+        "Chat Hard": 0.9013,
+        "Safety": 0.9578,
+        "Reasoning": 0.9826,
         "Factuality": 0.7853,
         "Precise IF": 0.3719,
         "Math": 0.6995,
-        "Safety": 0.927,
         "Focus": 0.9535,
-        "Ties": 0.8321,
-        "Chat": 0.9665,
-        "Chat Hard": 0.9013,
-        "Reasoning": 0.9826
+        "Ties": 0.8321
       }
     },
     {
@@ -4219,16 +4219,16 @@
       "name": "GPT-4o mini 2024-07-18",
       "developer": "OpenAI",
       "scores": {
-        "Score": 0.5796,
-        "Chat": 0.9497,
-        "Chat Hard": 0.6075,
-        "Safety": 0.7667,
-        "Reasoning": 0.8374,
+        "Score": 0.8007,
         "Factuality": 0.4105,
         "Precise IF": 0.3438,
         "Math": 0.5191,
+        "Safety": 0.8081,
         "Focus": 0.7414,
-        "Ties": 0.6962
+        "Ties": 0.6962,
+        "Chat": 0.9497,
+        "Chat Hard": 0.6075,
+        "Reasoning": 0.8374
       }
     },
     {
@@ -4249,17 +4249,17 @@
       "name": "openbmb/Eurus-RM-7b",
       "developer": "openbmb",
       "scores": {
-        "Score": 0.8159,
+        "Score": 0.5806,
+        "Chat": 0.9804,
+        "Chat Hard": 0.6557,
+        "Safety": 0.6267,
+        "Reasoning": 0.8633,
+        "Prior Sets (0.5 weight)": 0.7172,
         "Factuality": 0.6,
         "Precise IF": 0.3438,
         "Math": 0.5683,
-        "Safety": 0.8135,
         "Focus": 0.7475,
-        "Ties": 0.5972,
-        "Chat": 0.9804,
-        "Chat Hard": 0.6557,
-        "Reasoning": 0.8633,
-        "Prior Sets (0.5 weight)": 0.7172
+        "Ties": 0.5972
       }
     },
     {
@@ -4280,17 +4280,17 @@
       "name": "openbmb/UltraRM-13b",
       "developer": "openbmb",
       "scores": {
-        "Score": 0.4683,
-        "Chat": 0.9637,
-        "Chat Hard": 0.5548,
-        "Safety": 0.5089,
-        "Reasoning": 0.6244,
-        "Prior Sets (0.5 weight)": 0.7294,
+        "Score": 0.6903,
         "Factuality": 0.5063,
         "Precise IF": 0.3312,
         "Math": 0.5519,
+        "Safety": 0.5986,
         "Focus": 0.6081,
-        "Ties": 0.3036
+        "Ties": 0.3036,
+        "Chat": 0.9637,
+        "Chat Hard": 0.5548,
+        "Reasoning": 0.6244,
+        "Prior Sets (0.5 weight)": 0.7294
       }
     },
     {
@@ -4370,17 +4370,17 @@
       "name": "sfairXC/FsfairX-LLaMA3-RM-v0.1",
       "developer": "sfairXC",
       "scores": {
-        "Score": 0.8338,
+        "Score": 0.6292,
+        "Chat": 0.9944,
+        "Chat Hard": 0.6513,
+        "Safety": 0.7667,
+        "Reasoning": 0.8644,
+        "Prior Sets (0.5 weight)": 0.7492,
         "Factuality": 0.5916,
         "Precise IF": 0.4188,
         "Math": 0.6284,
-        "Safety": 0.8676,
         "Focus": 0.7051,
-        "Ties": 0.6647,
-        "Chat": 0.9944,
-        "Chat Hard": 0.6513,
-        "Reasoning": 0.8644,
-        "Prior Sets (0.5 weight)": 0.7492
+        "Ties": 0.6647
       }
     },
     {
@@ -4492,17 +4492,17 @@
       "name": "weqweasdas/RM-Gemma-2B",
       "developer": "weqweasdas",
       "scores": {
-        "Score": 0.3057,
-        "Chat": 0.9441,
-        "Chat Hard": 0.4079,
-        "Safety": 0.3311,
-        "Reasoning": 0.7637,
-        "Prior Sets (0.5 weight)": 0.6652,
+        "Score": 0.6549,
         "Factuality": 0.3705,
         "Precise IF": 0.2812,
         "Math": 0.4317,
+        "Safety": 0.4986,
         "Focus": 0.2343,
-        "Ties": 0.1851
+        "Ties": 0.1851,
+        "Chat": 0.9441,
+        "Chat Hard": 0.4079,
+        "Reasoning": 0.7637,
+        "Prior Sets (0.5 weight)": 0.6652
       }
     },
     {
@@ -4541,17 +4541,17 @@
       "name": "weqweasdas/RM-Mistral-7B",
       "developer": "weqweasdas",
       "scores": {
-        "Score": 0.596,
-        "Chat": 0.9665,
-        "Chat Hard": 0.6053,
-        "Safety": 0.6911,
-        "Reasoning": 0.7736,
-        "Prior Sets (0.5 weight)": 0.753,
+        "Score": 0.7982,
         "Factuality": 0.5937,
         "Precise IF": 0.3438,
         "Math": 0.5956,
+        "Safety": 0.8703,
         "Focus": 0.7293,
-        "Ties": 0.6226
+        "Ties": 0.6226,
+        "Chat": 0.9665,
+        "Chat Hard": 0.6053,
+        "Reasoning": 0.7736,
+        "Prior Sets (0.5 weight)": 0.753
       }
     },
     {
@@ -4559,17 +4559,17 @@
       "name": "weqweasdas/hh_rlhf_rm_open_llama_3b",
       "developer": "weqweasdas",
       "scores": {
-        "Score": 0.5027,
+        "Score": 0.2498,
+        "Chat": 0.8184,
+        "Chat Hard": 0.3728,
+        "Safety": 0.24,
+        "Reasoning": 0.3281,
+        "Prior Sets (0.5 weight)": 0.6564,
         "Factuality": 0.3642,
         "Precise IF": 0.275,
         "Math": 0.3497,
-        "Safety": 0.4149,
         "Focus": 0.2384,
-        "Ties": 0.0315,
-        "Chat": 0.8184,
-        "Chat Hard": 0.3728,
-        "Reasoning": 0.3281,
-        "Prior Sets (0.5 weight)": 0.6564
+        "Ties": 0.0315
       }
     }
   ]
diff --git a/data/benchmarks/swe-bench.json b/data/benchmarks/swe-bench.json
index 3b6c1cd3a38d41c01ec61c5d181997bdb0b7b011..093176be195c26e24230b48d3e9b488139a6d6bf 100644
--- a/data/benchmarks/swe-bench.json
+++ b/data/benchmarks/swe-bench.json
@@ -5,7 +5,7 @@
       "name": "claude-opus-4-5",
       "developer": "Anthropic",
       "scores": {
-        "swe-bench": 0.65
+        "swe-bench": 0.8072
       }
     },
     {
@@ -21,7 +21,7 @@
       "name": "gpt-5.2-2025-12-11",
       "developer": "OpenAI",
       "scores": {
-        "swe-bench": 0.57
+        "swe-bench": 0.5455
       }
     }
   ]
diff --git a/data/benchmarks/tau-bench-2_airline.json b/data/benchmarks/tau-bench-2_airline.json
index 3829696a07bc037642c69851a891e0aeb0e5febf..ebf0dad8ac51717ac2f9f1d57eb468b1c5031207 100644
--- a/data/benchmarks/tau-bench-2_airline.json
+++ b/data/benchmarks/tau-bench-2_airline.json
@@ -5,7 +5,7 @@
       "name": "claude-opus-4-5",
       "developer": "Anthropic",
       "scores": {
-        "tau-bench-2/airline": 0.72
+        "tau-bench-2/airline": 0.66
       }
     },
     {
@@ -13,7 +13,7 @@
       "name": "gemini-3-pro-preview",
       "developer": "Google",
       "scores": {
-        "tau-bench-2/airline": 0.68
+        "tau-bench-2/airline": 0.62
       }
     },
     {
diff --git a/data/benchmarks/tau-bench-2_retail.json b/data/benchmarks/tau-bench-2_retail.json
index 43bf4e72d939794b39171defb2c6b721324ab767..20515090a1536993197150db4c0d92e2f6d83d0d 100644
--- a/data/benchmarks/tau-bench-2_retail.json
+++ b/data/benchmarks/tau-bench-2_retail.json
@@ -5,7 +5,7 @@
       "name": "claude-opus-4-5",
       "developer": "Anthropic",
       "scores": {
-        "tau-bench-2/retail": 0.85
+        "tau-bench-2/retail": 0.83
       }
     },
     {
@@ -13,7 +13,7 @@
       "name": "gemini-3-pro-preview",
       "developer": "Google",
       "scores": {
-        "tau-bench-2/retail": 0.82
+        "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 05002e54c35c11c6e2530af6d100378b4038ab6c..0371242e1ef28be51ed37461c45171b5f6b938db 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": 0.73
+        "tau-bench-2/telecom": 0.6852
       }
     },
     {
@@ -21,7 +21,7 @@
       "name": "gpt-5.2-2025-12-11",
       "developer": "OpenAI",
       "scores": {
-        "tau-bench-2/telecom": 0.55
+        "tau-bench-2/telecom": 0.5354
       }
     }
   ]
diff --git a/data/benchmarks/terminal-bench-2.0.json b/data/benchmarks/terminal-bench-2.0.json
index 3f1515b599ae57812585a3e55eaf803056a58325..ee5c9bf500efbdc64465ca661d8781cc2133425b 100644
--- a/data/benchmarks/terminal-bench-2.0.json
+++ b/data/benchmarks/terminal-bench-2.0.json
@@ -5,7 +5,7 @@
       "name": "Qwen 3 Coder 480B",
       "developer": "Alibaba",
       "scores": {
-        "terminal-bench-2.0": 23.9
+        "terminal-bench-2.0": 27.2
       }
     },
     {
@@ -13,7 +13,7 @@
       "name": "Claude Haiku 4.5",
       "developer": "Anthropic",
       "scores": {
-        "terminal-bench-2.0": 13.9
+        "terminal-bench-2.0": 28.3
       }
     },
     {
@@ -21,7 +21,7 @@
       "name": "Claude Opus 4.1",
       "developer": "Anthropic",
       "scores": {
-        "terminal-bench-2.0": 36.9
+        "terminal-bench-2.0": 34.8
       }
     },
     {
@@ -37,7 +37,7 @@
       "name": "Claude Opus 4.6",
       "developer": "Anthropic",
       "scores": {
-        "terminal-bench-2.0": 74.7
+        "terminal-bench-2.0": 62.9
       }
     },
     {
@@ -61,7 +61,7 @@
       "name": "Gemini 2.5 Flash",
       "developer": "Google",
       "scores": {
-        "terminal-bench-2.0": 15.4
+        "terminal-bench-2.0": 17.1
       }
     },
     {
@@ -77,7 +77,7 @@
       "name": "Gemini 3 Flash",
       "developer": "Google",
       "scores": {
-        "terminal-bench-2.0": 51.0
+        "terminal-bench-2.0": 64.3
       }
     },
     {
@@ -85,7 +85,7 @@
       "name": "Gemini 3 Pro",
       "developer": "Google",
       "scores": {
-        "terminal-bench-2.0": 62.2
+        "terminal-bench-2.0": 61.8
       }
     },
     {
@@ -93,7 +93,7 @@
       "name": "Gemini 3.1 Pro",
       "developer": "Google",
       "scores": {
-        "terminal-bench-2.0": 74.8
+        "terminal-bench-2.0": 78.4
       }
     },
     {
@@ -109,7 +109,7 @@
       "name": "MiniMax M2.1",
       "developer": "MiniMax",
       "scores": {
-        "terminal-bench-2.0": 29.2
+        "terminal-bench-2.0": 36.6
       }
     },
     {
@@ -125,7 +125,7 @@
       "name": "Kimi K2 Instruct",
       "developer": "Moonshot AI",
       "scores": {
-        "terminal-bench-2.0": 27.8
+        "terminal-bench-2.0": 26.7
       }
     },
     {
@@ -157,7 +157,7 @@
       "name": "GPT-5",
       "developer": "OpenAI",
       "scores": {
-        "terminal-bench-2.0": 49.6
+        "terminal-bench-2.0": 35.2
       }
     },
     {
@@ -165,7 +165,7 @@
       "name": "GPT-5-Codex",
       "developer": "OpenAI",
       "scores": {
-        "terminal-bench-2.0": 43.4
+        "terminal-bench-2.0": 44.3
       }
     },
     {
@@ -173,7 +173,7 @@
       "name": "GPT-5-Mini",
       "developer": "OpenAI",
       "scores": {
-        "terminal-bench-2.0": 34.8
+        "terminal-bench-2.0": 24.0
       }
     },
     {
@@ -181,7 +181,7 @@
       "name": "GPT-5-Nano",
       "developer": "OpenAI",
       "scores": {
-        "terminal-bench-2.0": 7.0
+        "terminal-bench-2.0": 7.9
       }
     },
     {
@@ -221,7 +221,7 @@
       "name": "GPT-5.2",
       "developer": "OpenAI",
       "scores": {
-        "terminal-bench-2.0": 60.7
+        "terminal-bench-2.0": 54.0
       }
     },
     {
@@ -269,7 +269,7 @@
       "name": "Grok Code Fast 1",
       "developer": "xAI",
       "scores": {
-        "terminal-bench-2.0": 25.8
+        "terminal-bench-2.0": 14.2
       }
     },
     {
diff --git a/data/developers/ai2.json b/data/developers/ai2.json
index 6ae2e91a5d501e1d313c59819f3bee806d5615b0..498b6154facf655073d48826dd02116d29e34e45 100644
--- a/data/developers/ai2.json
+++ b/data/developers/ai2.json
@@ -43,10 +43,10 @@
       "developer": "AI2",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "reward-bench/Score": 0.6924,
-        "reward-bench/Chat": 0.9441,
-        "reward-bench/Chat Hard": 0.3575,
-        "reward-bench/Safety": 0.7757
+        "reward-bench/Score": 0.6895,
+        "reward-bench/Chat": 0.9385,
+        "reward-bench/Chat Hard": 0.3706,
+        "reward-bench/Safety": 0.7595
       }
     },
     {
diff --git a/data/developers/akjindal53244.json b/data/developers/akjindal53244.json
index 237ea0357d953fdc2d416f7c27241c406836e723..86acdd918ca996450aa81c0111cbad62da1b8b17 100644
--- a/data/developers/akjindal53244.json
+++ b/data/developers/akjindal53244.json
@@ -7,12 +7,12 @@
       "developer": "akjindal53244",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "hfopenllm_v2/IFEval": 0.8051,
-        "hfopenllm_v2/BBH": 0.5189,
-        "hfopenllm_v2/MATH Level 5": 0.1722,
-        "hfopenllm_v2/GPQA": 0.3263,
+        "hfopenllm_v2/IFEval": 0.8033,
+        "hfopenllm_v2/BBH": 0.5196,
+        "hfopenllm_v2/MATH Level 5": 0.1624,
+        "hfopenllm_v2/GPQA": 0.3096,
         "hfopenllm_v2/MUSR": 0.4028,
-        "hfopenllm_v2/MMLU-PRO": 0.3803
+        "hfopenllm_v2/MMLU-PRO": 0.3812
       }
     }
   ]
diff --git a/data/developers/alibaba.json b/data/developers/alibaba.json
index 759f3a2b29b65da87e85bd7df67845381cdc3145..844401e341e9e7b7e568fb2e5cdb8d2481e4039c 100644
--- a/data/developers/alibaba.json
+++ b/data/developers/alibaba.json
@@ -7,7 +7,7 @@
       "developer": "Alibaba",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "terminal-bench-2.0/terminal-bench-2.0": 23.9
+        "terminal-bench-2.0/terminal-bench-2.0": 27.2
       }
     },
     {
diff --git a/data/developers/allenai.json b/data/developers/allenai.json
index 733bf4fc5c0900a8884a7abb1f0b0f474d01c62a..335d05b967befc327e311cd92223e23391ec53c6 100644
--- a/data/developers/allenai.json
+++ b/data/developers/allenai.json
@@ -162,17 +162,17 @@
       "developer": "allenai",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "reward-bench/Score": 0.722,
-        "reward-bench/Chat": 0.9693,
-        "reward-bench/Chat Hard": 0.8268,
-        "reward-bench/Safety": 0.8689,
-        "reward-bench/Reasoning": 0.8583,
-        "reward-bench/Prior Sets (0.5 weight)": 0.0,
+        "reward-bench/Score": 0.8892,
         "reward-bench/Factuality": 0.8084,
         "reward-bench/Precise IF": 0.3688,
         "reward-bench/Math": 0.6776,
+        "reward-bench/Safety": 0.9027,
         "reward-bench/Focus": 0.7778,
-        "reward-bench/Ties": 0.8308
+        "reward-bench/Ties": 0.8308,
+        "reward-bench/Chat": 0.9693,
+        "reward-bench/Chat Hard": 0.8268,
+        "reward-bench/Reasoning": 0.8583,
+        "reward-bench/Prior Sets (0.5 weight)": 0.0
       }
     },
     {
@@ -181,12 +181,12 @@
       "developer": "allenai",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "hfopenllm_v2/IFEval": 0.8255,
-        "hfopenllm_v2/BBH": 0.4061,
-        "hfopenllm_v2/MATH Level 5": 0.2115,
-        "hfopenllm_v2/GPQA": 0.297,
+        "hfopenllm_v2/IFEval": 0.8267,
+        "hfopenllm_v2/BBH": 0.405,
+        "hfopenllm_v2/MATH Level 5": 0.1964,
+        "hfopenllm_v2/GPQA": 0.2987,
         "hfopenllm_v2/MUSR": 0.4175,
-        "hfopenllm_v2/MMLU-PRO": 0.2821
+        "hfopenllm_v2/MMLU-PRO": 0.2827
       }
     },
     {
@@ -209,17 +209,17 @@
       "developer": "allenai",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "reward-bench/Score": 0.8431,
+        "reward-bench/Score": 0.687,
+        "reward-bench/Chat": 0.9553,
+        "reward-bench/Chat Hard": 0.761,
+        "reward-bench/Safety": 0.86,
+        "reward-bench/Reasoning": 0.7898,
+        "reward-bench/Prior Sets (0.5 weight)": 0.0,
         "reward-bench/Factuality": 0.7516,
         "reward-bench/Precise IF": 0.3875,
         "reward-bench/Math": 0.6284,
-        "reward-bench/Safety": 0.8662,
         "reward-bench/Focus": 0.8545,
-        "reward-bench/Ties": 0.6397,
-        "reward-bench/Chat": 0.9553,
-        "reward-bench/Chat Hard": 0.761,
-        "reward-bench/Reasoning": 0.7898,
-        "reward-bench/Prior Sets (0.5 weight)": 0.0
+        "reward-bench/Ties": 0.6397
       }
     },
     {
diff --git a/data/developers/amd.json b/data/developers/amd.json
index ec85a4364a761e30f1999f359d0d247d8857e139..f58c5a6931b8f7bef3756ba18944919a5d99e792 100644
--- a/data/developers/amd.json
+++ b/data/developers/amd.json
@@ -7,11 +7,11 @@
       "developer": "amd",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "hfopenllm_v2/IFEval": 0.1842,
-        "hfopenllm_v2/BBH": 0.2974,
-        "hfopenllm_v2/MATH Level 5": 0.0053,
-        "hfopenllm_v2/GPQA": 0.2525,
-        "hfopenllm_v2/MUSR": 0.378,
+        "hfopenllm_v2/IFEval": 0.1918,
+        "hfopenllm_v2/BBH": 0.2969,
+        "hfopenllm_v2/MATH Level 5": 0.0076,
+        "hfopenllm_v2/GPQA": 0.2584,
+        "hfopenllm_v2/MUSR": 0.3846,
         "hfopenllm_v2/MMLU-PRO": 0.1169
       }
     }
diff --git a/data/developers/anthropic.json b/data/developers/anthropic.json
index 21c2bc0153b15a2859b6559b8628567638664450..8e4dd896b5ad3de59cdc15abc7af29c17ad664c2 100644
--- a/data/developers/anthropic.json
+++ b/data/developers/anthropic.json
@@ -371,17 +371,17 @@
         "helm_mmlu/Virology": 0.542,
         "helm_mmlu/World Religions": 0.871,
         "helm_mmlu/Mean win rate": 0.28,
-        "reward-bench/Score": 0.3711,
-        "reward-bench/Chat": 0.9274,
-        "reward-bench/Chat Hard": 0.5197,
-        "reward-bench/Safety": 0.595,
-        "reward-bench/Reasoning": 0.706,
-        "reward-bench/Prior Sets (0.5 weight)": 0.6635,
+        "reward-bench/Score": 0.7289,
         "reward-bench/Factuality": 0.4042,
         "reward-bench/Precise IF": 0.2812,
         "reward-bench/Math": 0.3552,
+        "reward-bench/Safety": 0.7953,
         "reward-bench/Focus": 0.501,
-        "reward-bench/Ties": 0.0899
+        "reward-bench/Ties": 0.0899,
+        "reward-bench/Chat": 0.9274,
+        "reward-bench/Chat Hard": 0.5197,
+        "reward-bench/Reasoning": 0.706,
+        "reward-bench/Prior Sets (0.5 weight)": 0.6635
       }
     },
     {
@@ -436,16 +436,16 @@
         "helm_mmlu/Virology": 0.578,
         "helm_mmlu/World Religions": 0.901,
         "helm_mmlu/Mean win rate": 0.014,
-        "reward-bench/Score": 0.8008,
+        "reward-bench/Score": 0.5744,
+        "reward-bench/Chat": 0.9469,
+        "reward-bench/Chat Hard": 0.6031,
+        "reward-bench/Safety": 0.8378,
+        "reward-bench/Reasoning": 0.7868,
         "reward-bench/Factuality": 0.5389,
         "reward-bench/Precise IF": 0.3312,
         "reward-bench/Math": 0.5137,
-        "reward-bench/Safety": 0.8662,
         "reward-bench/Focus": 0.6646,
-        "reward-bench/Ties": 0.5601,
-        "reward-bench/Chat": 0.9469,
-        "reward-bench/Chat Hard": 0.6031,
-        "reward-bench/Reasoning": 0.7868
+        "reward-bench/Ties": 0.5601
       }
     },
     {
@@ -525,7 +525,7 @@
       "developer": "Anthropic",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "terminal-bench-2.0/terminal-bench-2.0": 13.9
+        "terminal-bench-2.0/terminal-bench-2.0": 28.3
       }
     },
     {
@@ -650,11 +650,11 @@
       "developer": "Anthropic",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "appworld_test_normal/appworld/test_normal": 0.66,
+        "appworld_test_normal/appworld/test_normal": 0.68,
         "browsecompplus/browsecompplus": 0.49,
-        "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,
+        "swe-bench/swe-bench": 0.8072,
+        "tau-bench-2_airline/tau-bench-2/airline": 0.66,
+        "tau-bench-2_retail/tau-bench-2/retail": 0.83,
         "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": 36.9
+        "terminal-bench-2.0/terminal-bench-2.0": 34.8
       }
     },
     {
@@ -682,7 +682,7 @@
       "developer": "Anthropic",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "terminal-bench-2.0/terminal-bench-2.0": 74.7
+        "terminal-bench-2.0/terminal-bench-2.0": 62.9
       }
     },
     {
diff --git a/data/developers/arcee-ai.json b/data/developers/arcee-ai.json
index a67ed73a3aff7f3d10c24e6ce76a817fd626a3c8..fb3c26af6dfe804ff7a40fb7fe0b6065ba67af15 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": 0.5718,
-        "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
+        "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
       }
     },
     {
diff --git a/data/developers/bunnycore.json b/data/developers/bunnycore.json
index 153064e2dea6c3626cb6deb17e2d3191b25ec406..069b8a9f0214975725e28f414b82b07e73072c0f 100644
--- a/data/developers/bunnycore.json
+++ b/data/developers/bunnycore.json
@@ -287,12 +287,12 @@
       "developer": "bunnycore",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "hfopenllm_v2/IFEval": 0.1775,
-        "hfopenllm_v2/BBH": 0.295,
-        "hfopenllm_v2/MATH Level 5": 0.0,
-        "hfopenllm_v2/GPQA": 0.2517,
-        "hfopenllm_v2/MUSR": 0.3647,
-        "hfopenllm_v2/MMLU-PRO": 0.1049
+        "hfopenllm_v2/IFEval": 0.4652,
+        "hfopenllm_v2/BBH": 0.4531,
+        "hfopenllm_v2/MATH Level 5": 0.1284,
+        "hfopenllm_v2/GPQA": 0.2643,
+        "hfopenllm_v2/MUSR": 0.3394,
+        "hfopenllm_v2/MMLU-PRO": 0.3152
       }
     },
     {
diff --git a/data/developers/cir-ams.json b/data/developers/cir-ams.json
index df9dcecb6f8fae5d901c2496b58813341797427e..09d0cc390a2584b96dbfe9a5acec25171fe175fa 100644
--- a/data/developers/cir-ams.json
+++ b/data/developers/cir-ams.json
@@ -7,17 +7,17 @@
       "developer": "CIR-AMS",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "reward-bench/Score": 0.8172,
+        "reward-bench/Score": 0.5736,
+        "reward-bench/Chat": 0.9749,
+        "reward-bench/Chat Hard": 0.5724,
+        "reward-bench/Safety": 0.7178,
+        "reward-bench/Reasoning": 0.8775,
+        "reward-bench/Prior Sets (0.5 weight)": 0.7029,
         "reward-bench/Factuality": 0.5347,
         "reward-bench/Precise IF": 0.3563,
         "reward-bench/Math": 0.6066,
-        "reward-bench/Safety": 0.9014,
         "reward-bench/Focus": 0.5737,
-        "reward-bench/Ties": 0.6527,
-        "reward-bench/Chat": 0.9749,
-        "reward-bench/Chat Hard": 0.5724,
-        "reward-bench/Reasoning": 0.8775,
-        "reward-bench/Prior Sets (0.5 weight)": 0.7029
+        "reward-bench/Ties": 0.6527
       }
     }
   ]
diff --git a/data/developers/cognitivecomputations.json b/data/developers/cognitivecomputations.json
index 27ef3ede420acfeab83ed5bb754062e32374c41a..292d5e513d244c8ebb441a809017ff16919c9354 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": 0.4124,
-        "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
+        "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
       }
     },
     {
diff --git a/data/developers/daemontatox.json b/data/developers/daemontatox.json
index b8e6a28a7fbf1f38ce6fe03abcdad2859f985a0e..303c645fdab066808be1ab6783e6eea08f827b82 100644
--- a/data/developers/daemontatox.json
+++ b/data/developers/daemontatox.json
@@ -35,12 +35,12 @@
       "developer": "Daemontatox",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "hfopenllm_v2/IFEval": 0.4383,
-        "hfopenllm_v2/BBH": 0.5034,
-        "hfopenllm_v2/MATH Level 5": 0.1443,
+        "hfopenllm_v2/IFEval": 0.4398,
+        "hfopenllm_v2/BBH": 0.5066,
+        "hfopenllm_v2/MATH Level 5": 0.1488,
         "hfopenllm_v2/GPQA": 0.3238,
-        "hfopenllm_v2/MUSR": 0.4052,
-        "hfopenllm_v2/MMLU-PRO": 0.3778
+        "hfopenllm_v2/MUSR": 0.4079,
+        "hfopenllm_v2/MMLU-PRO": 0.3804
       }
     },
     {
@@ -119,12 +119,12 @@
       "developer": "Daemontatox",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "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
+        "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
       }
     },
     {
diff --git a/data/developers/davielion.json b/data/developers/davielion.json
index 5027340a9fce3c0b5162453c9d10516ec45234d2..d2a3ca1471ea06bca721c18d505591908b22252e 100644
--- a/data/developers/davielion.json
+++ b/data/developers/davielion.json
@@ -7,12 +7,12 @@
       "developer": "DavieLion",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "hfopenllm_v2/IFEval": 0.1507,
-        "hfopenllm_v2/BBH": 0.293,
-        "hfopenllm_v2/MATH Level 5": 0.0,
-        "hfopenllm_v2/GPQA": 0.2534,
+        "hfopenllm_v2/IFEval": 0.1549,
+        "hfopenllm_v2/BBH": 0.2937,
+        "hfopenllm_v2/MATH Level 5": 0.006,
+        "hfopenllm_v2/GPQA": 0.2576,
         "hfopenllm_v2/MUSR": 0.3565,
-        "hfopenllm_v2/MMLU-PRO": 0.1125
+        "hfopenllm_v2/MMLU-PRO": 0.1128
       }
     },
     {
diff --git a/data/developers/deepmount00.json b/data/developers/deepmount00.json
index e898074e4a61782e05002f7b47eb2ee0411313aa..5505c28134c7ac10ef3a27978dd2745253c793a1 100644
--- a/data/developers/deepmount00.json
+++ b/data/developers/deepmount00.json
@@ -63,12 +63,12 @@
       "developer": "DeepMount00",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "hfopenllm_v2/IFEval": 0.5365,
-        "hfopenllm_v2/BBH": 0.517,
-        "hfopenllm_v2/MATH Level 5": 0.1707,
-        "hfopenllm_v2/GPQA": 0.3062,
-        "hfopenllm_v2/MUSR": 0.4487,
-        "hfopenllm_v2/MMLU-PRO": 0.396
+        "hfopenllm_v2/IFEval": 0.7917,
+        "hfopenllm_v2/BBH": 0.5109,
+        "hfopenllm_v2/MATH Level 5": 0.1088,
+        "hfopenllm_v2/GPQA": 0.2878,
+        "hfopenllm_v2/MUSR": 0.4136,
+        "hfopenllm_v2/MMLU-PRO": 0.3876
       }
     },
     {
diff --git a/data/developers/epistemeai.json b/data/developers/epistemeai.json
index ae59684b2ae8edda61f6033386c80ae35c1570fc..11b25cd31eead1ba78e7fde536703493137e208b 100644
--- a/data/developers/epistemeai.json
+++ b/data/developers/epistemeai.json
@@ -231,12 +231,12 @@
       "developer": "EpistemeAI",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "hfopenllm_v2/IFEval": 0.7305,
-        "hfopenllm_v2/BBH": 0.4649,
-        "hfopenllm_v2/MATH Level 5": 0.1397,
-        "hfopenllm_v2/GPQA": 0.2659,
-        "hfopenllm_v2/MUSR": 0.3209,
-        "hfopenllm_v2/MMLU-PRO": 0.348
+        "hfopenllm_v2/IFEval": 0.7207,
+        "hfopenllm_v2/BBH": 0.461,
+        "hfopenllm_v2/MATH Level 5": 0.1314,
+        "hfopenllm_v2/GPQA": 0.2701,
+        "hfopenllm_v2/MUSR": 0.3432,
+        "hfopenllm_v2/MMLU-PRO": 0.3354
       }
     },
     {
diff --git a/data/developers/etherll.json b/data/developers/etherll.json
index 6a72dd37a279f4d76a8244a057714c910854bcd2..2be2455f8558b72fcbd342c72cc671c443f3155e 100644
--- a/data/developers/etherll.json
+++ b/data/developers/etherll.json
@@ -35,12 +35,12 @@
       "developer": "Etherll",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "hfopenllm_v2/IFEval": 0.6106,
-        "hfopenllm_v2/BBH": 0.5347,
-        "hfopenllm_v2/MATH Level 5": 0.1548,
-        "hfopenllm_v2/GPQA": 0.3146,
-        "hfopenllm_v2/MUSR": 0.3991,
-        "hfopenllm_v2/MMLU-PRO": 0.3752
+        "hfopenllm_v2/IFEval": 0.4672,
+        "hfopenllm_v2/BBH": 0.5013,
+        "hfopenllm_v2/MATH Level 5": 0.0279,
+        "hfopenllm_v2/GPQA": 0.2861,
+        "hfopenllm_v2/MUSR": 0.386,
+        "hfopenllm_v2/MMLU-PRO": 0.3482
       }
     },
     {
diff --git a/data/developers/goekdeniz-guelmez.json b/data/developers/goekdeniz-guelmez.json
index c6e66fe9b3a75e2d49b70b9c90b10752326b37c4..e903240eb11157a57a20b31274250b901066286d 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": 0.7628,
-        "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
+        "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
       }
     },
     {
@@ -63,12 +63,12 @@
       "developer": "Goekdeniz-Guelmez",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "hfopenllm_v2/IFEval": 0.3417,
-        "hfopenllm_v2/BBH": 0.3292,
-        "hfopenllm_v2/MATH Level 5": 0.0023,
-        "hfopenllm_v2/GPQA": 0.2576,
-        "hfopenllm_v2/MUSR": 0.3249,
-        "hfopenllm_v2/MMLU-PRO": 0.1638
+        "hfopenllm_v2/IFEval": 0.3472,
+        "hfopenllm_v2/BBH": 0.3268,
+        "hfopenllm_v2/MATH Level 5": 0.0891,
+        "hfopenllm_v2/GPQA": 0.2517,
+        "hfopenllm_v2/MUSR": 0.3262,
+        "hfopenllm_v2/MMLU-PRO": 0.1641
       }
     },
     {
diff --git a/data/developers/google.json b/data/developers/google.json
index 81f1df0599e79d5fa5b9eb113ec92dededc4447e..785568af1a47d9f2c7836777b5810f3a3f2fb1bd 100644
--- a/data/developers/google.json
+++ b/data/developers/google.json
@@ -157,6 +157,8 @@
       "developer": "Google",
       "evaluator_relationship": null,
       "benchmark_scores": {
+        "ace/Overall Score": 0.47,
+        "ace/Gaming Score": 0.509,
         "apex-agents/Overall Pass@1": 0.184,
         "apex-agents/Overall Pass@8": 0.373,
         "apex-agents/Overall Mean Score": 0.341,
@@ -164,8 +166,6 @@
         "apex-agents/Management Consulting Pass@1": 0.124,
         "apex-agents/Corporate Law Pass@1": 0.239,
         "apex-agents/Corporate Lawyer Mean Score": 0.487,
-        "ace/Overall Score": 0.47,
-        "ace/Gaming Score": 0.509,
         "apex-v1/Overall Score": 0.643,
         "apex-v1/Consulting Score": 0.64,
         "apex-v1/Investment Banking Score": 0.63
@@ -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": 15.4
+        "terminal-bench-2.0/terminal-bench-2.0": 17.1
       }
     },
     {
@@ -861,7 +861,7 @@
       "developer": "Google",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "terminal-bench-2.0/terminal-bench-2.0": 51.0
+        "terminal-bench-2.0/terminal-bench-2.0": 64.3
       }
     },
     {
@@ -870,7 +870,7 @@
       "developer": "Google",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "terminal-bench-2.0/terminal-bench-2.0": 62.2
+        "terminal-bench-2.0/terminal-bench-2.0": 61.8
       }
     },
     {
@@ -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": 0.68,
-        "tau-bench-2_retail/tau-bench-2/retail": 0.82,
-        "tau-bench-2_telecom/tau-bench-2/telecom": 0.73
+        "tau-bench-2_airline/tau-bench-2/airline": 0.62,
+        "tau-bench-2_retail/tau-bench-2/retail": 0.73,
+        "tau-bench-2_telecom/tau-bench-2/telecom": 0.6852
       }
     },
     {
@@ -912,7 +912,7 @@
       "developer": "Google",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "terminal-bench-2.0/terminal-bench-2.0": 74.8
+        "terminal-bench-2.0/terminal-bench-2.0": 78.4
       }
     },
     {
@@ -1028,12 +1028,12 @@
       "developer": "Google",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "hfopenllm_v2/IFEval": 0.1993,
-        "hfopenllm_v2/BBH": 0.3656,
-        "hfopenllm_v2/MATH Level 5": 0.0287,
+        "hfopenllm_v2/IFEval": 0.2018,
+        "hfopenllm_v2/BBH": 0.3709,
+        "hfopenllm_v2/MATH Level 5": 0.0302,
         "hfopenllm_v2/GPQA": 0.2626,
-        "hfopenllm_v2/MUSR": 0.4232,
-        "hfopenllm_v2/MMLU-PRO": 0.218
+        "hfopenllm_v2/MUSR": 0.4219,
+        "hfopenllm_v2/MMLU-PRO": 0.2217
       }
     },
     {
diff --git a/data/developers/gunulhona.json b/data/developers/gunulhona.json
index 3d63c85d80df83c6632e31f815d8dc78510d19a0..1eba4dc6aed35ea93d90c3c8c2e1a2676805ffa0 100644
--- a/data/developers/gunulhona.json
+++ b/data/developers/gunulhona.json
@@ -21,12 +21,12 @@
       "developer": "Gunulhona",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "hfopenllm_v2/IFEval": 0.288,
-        "hfopenllm_v2/BBH": 0.5154,
+        "hfopenllm_v2/IFEval": 0.4441,
+        "hfopenllm_v2/BBH": 0.4863,
         "hfopenllm_v2/MATH Level 5": 0.0,
-        "hfopenllm_v2/GPQA": 0.3247,
-        "hfopenllm_v2/MUSR": 0.408,
-        "hfopenllm_v2/MMLU-PRO": 0.3817
+        "hfopenllm_v2/GPQA": 0.307,
+        "hfopenllm_v2/MUSR": 0.3986,
+        "hfopenllm_v2/MMLU-PRO": 0.3098
       }
     }
   ]
diff --git a/data/developers/huggingfacetb.json b/data/developers/huggingfacetb.json
index bed31781473fb30427be579aab45ef01bf5054ce..60e6e856fd10ebf29a5d127dd18301cd9edf10dd 100644
--- a/data/developers/huggingfacetb.json
+++ b/data/developers/huggingfacetb.json
@@ -161,12 +161,12 @@
       "developer": "HuggingFaceTB",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "hfopenllm_v2/IFEval": 0.083,
-        "hfopenllm_v2/BBH": 0.3053,
-        "hfopenllm_v2/MATH Level 5": 0.0083,
-        "hfopenllm_v2/GPQA": 0.2651,
-        "hfopenllm_v2/MUSR": 0.3423,
-        "hfopenllm_v2/MMLU-PRO": 0.1126
+        "hfopenllm_v2/IFEval": 0.3842,
+        "hfopenllm_v2/BBH": 0.3144,
+        "hfopenllm_v2/MATH Level 5": 0.0151,
+        "hfopenllm_v2/GPQA": 0.255,
+        "hfopenllm_v2/MUSR": 0.3461,
+        "hfopenllm_v2/MMLU-PRO": 0.1117
       }
     }
   ]
diff --git a/data/developers/internlm.json b/data/developers/internlm.json
index 035007101b6dacaf9414107420239eb159a0ec86..fbcc7249ad65cfb92e1e09809d6765ef54a982e2 100644
--- a/data/developers/internlm.json
+++ b/data/developers/internlm.json
@@ -21,16 +21,16 @@
       "developer": "internlm",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "reward-bench/Score": 0.8217,
+        "reward-bench/Score": 0.3902,
+        "reward-bench/Chat": 0.9358,
+        "reward-bench/Chat Hard": 0.6623,
+        "reward-bench/Safety": 0.4711,
+        "reward-bench/Reasoning": 0.8724,
         "reward-bench/Factuality": 0.2758,
         "reward-bench/Precise IF": 0.3625,
         "reward-bench/Math": 0.4426,
-        "reward-bench/Safety": 0.8162,
         "reward-bench/Focus": 0.596,
-        "reward-bench/Ties": 0.1934,
-        "reward-bench/Chat": 0.9358,
-        "reward-bench/Chat Hard": 0.6623,
-        "reward-bench/Reasoning": 0.8724
+        "reward-bench/Ties": 0.1934
       }
     },
     {
diff --git a/data/developers/jaspionjader.json b/data/developers/jaspionjader.json
index 9d9d1e268e56a9945ae657deca0493de6a22ce3d..053d128582b4aa02040ae51cd0577288669f17e5 100644
--- a/data/developers/jaspionjader.json
+++ b/data/developers/jaspionjader.json
@@ -1477,12 +1477,12 @@
       "developer": "jaspionjader",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "hfopenllm_v2/IFEval": 0.4418,
-        "hfopenllm_v2/BBH": 0.5406,
-        "hfopenllm_v2/MATH Level 5": 0.1352,
-        "hfopenllm_v2/GPQA": 0.3062,
+        "hfopenllm_v2/IFEval": 0.4345,
+        "hfopenllm_v2/BBH": 0.5419,
+        "hfopenllm_v2/MATH Level 5": 0.1292,
+        "hfopenllm_v2/GPQA": 0.3087,
         "hfopenllm_v2/MUSR": 0.4277,
-        "hfopenllm_v2/MMLU-PRO": 0.386
+        "hfopenllm_v2/MMLU-PRO": 0.3854
       }
     },
     {
diff --git a/data/developers/leroydyer.json b/data/developers/leroydyer.json
index e1aa95462e1fed8d4e011735c7846112031a21a1..119d29bab457804b8d64637d339b1f72d7389de3 100644
--- a/data/developers/leroydyer.json
+++ b/data/developers/leroydyer.json
@@ -707,12 +707,12 @@
       "developer": "LeroyDyer",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "hfopenllm_v2/IFEval": 0.3579,
-        "hfopenllm_v2/BBH": 0.4477,
-        "hfopenllm_v2/MATH Level 5": 0.0423,
-        "hfopenllm_v2/GPQA": 0.3096,
-        "hfopenllm_v2/MUSR": 0.4134,
-        "hfopenllm_v2/MMLU-PRO": 0.2376
+        "hfopenllm_v2/IFEval": 0.3798,
+        "hfopenllm_v2/BBH": 0.4483,
+        "hfopenllm_v2/MATH Level 5": 0.04,
+        "hfopenllm_v2/GPQA": 0.3129,
+        "hfopenllm_v2/MUSR": 0.4148,
+        "hfopenllm_v2/MMLU-PRO": 0.2389
       }
     },
     {
diff --git a/data/developers/llmat.json b/data/developers/llmat.json
index 95633d3199310803501c256677a0fb788d0a08f7..d073eb81547c22e04e5363702192b3a9654d7362 100644
--- a/data/developers/llmat.json
+++ b/data/developers/llmat.json
@@ -7,12 +7,12 @@
       "developer": "llmat",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "hfopenllm_v2/IFEval": 0.364,
-        "hfopenllm_v2/BBH": 0.4005,
-        "hfopenllm_v2/MATH Level 5": 0.0015,
-        "hfopenllm_v2/GPQA": 0.2693,
-        "hfopenllm_v2/MUSR": 0.3529,
-        "hfopenllm_v2/MMLU-PRO": 0.2301
+        "hfopenllm_v2/IFEval": 0.377,
+        "hfopenllm_v2/BBH": 0.3978,
+        "hfopenllm_v2/MATH Level 5": 0.0242,
+        "hfopenllm_v2/GPQA": 0.2668,
+        "hfopenllm_v2/MUSR": 0.3555,
+        "hfopenllm_v2/MMLU-PRO": 0.2278
       }
     }
   ]
diff --git a/data/developers/magpie-align.json b/data/developers/magpie-align.json
index 0dc0a43e89bb456a61006caa30051add55effb08..155a416e715db19186e6af681f6736ea9ed101d1 100644
--- a/data/developers/magpie-align.json
+++ b/data/developers/magpie-align.json
@@ -35,12 +35,12 @@
       "developer": "Magpie-Align",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "hfopenllm_v2/IFEval": 0.4027,
-        "hfopenllm_v2/BBH": 0.4789,
-        "hfopenllm_v2/MATH Level 5": 0.0461,
-        "hfopenllm_v2/GPQA": 0.2768,
-        "hfopenllm_v2/MUSR": 0.3087,
-        "hfopenllm_v2/MMLU-PRO": 0.3001
+        "hfopenllm_v2/IFEval": 0.4118,
+        "hfopenllm_v2/BBH": 0.4811,
+        "hfopenllm_v2/MATH Level 5": 0.034,
+        "hfopenllm_v2/GPQA": 0.2752,
+        "hfopenllm_v2/MUSR": 0.3047,
+        "hfopenllm_v2/MMLU-PRO": 0.3006
       }
     },
     {
diff --git a/data/developers/meta-llama.json b/data/developers/meta-llama.json
index 76d923e16aab37465ed7dda94d7be71e39f4b29e..a28b7c096e670398e8b74d7b30002bc56044221b 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": 0.7408,
-        "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,
+        "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,
         "reward-bench/Score": 0.645,
         "reward-bench/Chat": 0.8547,
         "reward-bench/Chat Hard": 0.4156,
diff --git a/data/developers/microsoft.json b/data/developers/microsoft.json
index 5b22c3abc624b7d65a825afffb8ded406b5eb203..7ea0eb813b21f5c278a71169ee533064bbab2740 100644
--- a/data/developers/microsoft.json
+++ b/data/developers/microsoft.json
@@ -225,12 +225,12 @@
       "developer": "microsoft",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "hfopenllm_v2/IFEval": 0.5477,
-        "hfopenllm_v2/BBH": 0.5491,
-        "hfopenllm_v2/MATH Level 5": 0.1639,
-        "hfopenllm_v2/GPQA": 0.3322,
-        "hfopenllm_v2/MUSR": 0.4284,
-        "hfopenllm_v2/MMLU-PRO": 0.4022
+        "hfopenllm_v2/IFEval": 0.5613,
+        "hfopenllm_v2/BBH": 0.5676,
+        "hfopenllm_v2/MATH Level 5": 0.1163,
+        "hfopenllm_v2/GPQA": 0.3196,
+        "hfopenllm_v2/MUSR": 0.395,
+        "hfopenllm_v2/MMLU-PRO": 0.3866
       }
     },
     {
diff --git a/data/developers/minimax.json b/data/developers/minimax.json
index b575a16ccd7fb272ceb4b3067b0a9e48f65cff08..3eb98fb6a6609e5f1cc4d74a47ecc2b74aaa9bb0 100644
--- a/data/developers/minimax.json
+++ b/data/developers/minimax.json
@@ -25,7 +25,7 @@
       "developer": "MiniMax",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "terminal-bench-2.0/terminal-bench-2.0": 29.2
+        "terminal-bench-2.0/terminal-bench-2.0": 36.6
       }
     },
     {
diff --git a/data/developers/moonshot_ai.json b/data/developers/moonshot_ai.json
index 746185ce773a539bd025922ab856fdcf2f8a1d9f..d83f11402fcca0c39c33d09eed495f2aefd69384 100644
--- a/data/developers/moonshot_ai.json
+++ b/data/developers/moonshot_ai.json
@@ -7,7 +7,7 @@
       "developer": "Moonshot AI",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "terminal-bench-2.0/terminal-bench-2.0": 27.8
+        "terminal-bench-2.0/terminal-bench-2.0": 26.7
       }
     },
     {
diff --git a/data/developers/nazimali.json b/data/developers/nazimali.json
index 07c42beb48b2fc9e0ad1a1059178a9ce4071a591..34d47c9647d462b17a0fe6015c5c4f9fc00264e7 100644
--- a/data/developers/nazimali.json
+++ b/data/developers/nazimali.json
@@ -21,12 +21,12 @@
       "developer": "nazimali",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "hfopenllm_v2/IFEval": 0.4964,
-        "hfopenllm_v2/BBH": 0.4699,
-        "hfopenllm_v2/MATH Level 5": 0.0045,
-        "hfopenllm_v2/GPQA": 0.2827,
-        "hfopenllm_v2/MUSR": 0.3979,
-        "hfopenllm_v2/MMLU-PRO": 0.3063
+        "hfopenllm_v2/IFEval": 0.486,
+        "hfopenllm_v2/BBH": 0.4721,
+        "hfopenllm_v2/MATH Level 5": 0.0846,
+        "hfopenllm_v2/GPQA": 0.2844,
+        "hfopenllm_v2/MUSR": 0.4006,
+        "hfopenllm_v2/MMLU-PRO": 0.3087
       }
     }
   ]
diff --git a/data/developers/nicolinho.json b/data/developers/nicolinho.json
index bf9706fe4ed328188b0945860efeebf7183abc65..79bf445ae201aa8b9add0559d92e4abd4fd3bebb 100644
--- a/data/developers/nicolinho.json
+++ b/data/developers/nicolinho.json
@@ -7,16 +7,16 @@
       "developer": "nicolinho",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "reward-bench/Score": 0.9444,
+        "reward-bench/Score": 0.7667,
+        "reward-bench/Chat": 0.9665,
+        "reward-bench/Chat Hard": 0.9013,
+        "reward-bench/Safety": 0.9578,
+        "reward-bench/Reasoning": 0.9826,
         "reward-bench/Factuality": 0.7853,
         "reward-bench/Precise IF": 0.3719,
         "reward-bench/Math": 0.6995,
-        "reward-bench/Safety": 0.927,
         "reward-bench/Focus": 0.9535,
-        "reward-bench/Ties": 0.8321,
-        "reward-bench/Chat": 0.9665,
-        "reward-bench/Chat Hard": 0.9013,
-        "reward-bench/Reasoning": 0.9826
+        "reward-bench/Ties": 0.8321
       }
     },
     {
diff --git a/data/developers/omkar1102.json b/data/developers/omkar1102.json
index ca0270b469e58068ee5242b6801e2fbe782ddc0a..1d044781189744d770af993cfdb651c1e02eee6f 100644
--- a/data/developers/omkar1102.json
+++ b/data/developers/omkar1102.json
@@ -7,12 +7,12 @@
       "developer": "Omkar1102",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "hfopenllm_v2/IFEval": 0.2148,
-        "hfopenllm_v2/BBH": 0.276,
+        "hfopenllm_v2/IFEval": 0.2254,
+        "hfopenllm_v2/BBH": 0.275,
         "hfopenllm_v2/MATH Level 5": 0.0,
-        "hfopenllm_v2/GPQA": 0.2508,
-        "hfopenllm_v2/MUSR": 0.3802,
-        "hfopenllm_v2/MMLU-PRO": 0.1126
+        "hfopenllm_v2/GPQA": 0.2576,
+        "hfopenllm_v2/MUSR": 0.3762,
+        "hfopenllm_v2/MMLU-PRO": 0.1123
       }
     }
   ]
diff --git a/data/developers/ontocord.json b/data/developers/ontocord.json
index c16f4cbacdda3485b721f459b079923a6793a670..add41dbe183800ebed90c916e0b704c974dd50e7 100644
--- a/data/developers/ontocord.json
+++ b/data/developers/ontocord.json
@@ -273,12 +273,12 @@
       "developer": "ontocord",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "hfopenllm_v2/IFEval": 0.1128,
-        "hfopenllm_v2/BBH": 0.3171,
-        "hfopenllm_v2/MATH Level 5": 0.0113,
-        "hfopenllm_v2/GPQA": 0.2685,
-        "hfopenllm_v2/MUSR": 0.346,
-        "hfopenllm_v2/MMLU-PRO": 0.1129
+        "hfopenllm_v2/IFEval": 0.1162,
+        "hfopenllm_v2/BBH": 0.3184,
+        "hfopenllm_v2/MATH Level 5": 0.0076,
+        "hfopenllm_v2/GPQA": 0.2634,
+        "hfopenllm_v2/MUSR": 0.3447,
+        "hfopenllm_v2/MMLU-PRO": 0.1124
       }
     },
     {
diff --git a/data/developers/openai.json b/data/developers/openai.json
index 778495ca5d9933e50afc2a386628c3370e3c9523..7ffb402ef626c167784b6adff2263ee1471b3836 100644
--- a/data/developers/openai.json
+++ b/data/developers/openai.json
@@ -859,16 +859,16 @@
         "helm_mmlu/Virology": 0.536,
         "helm_mmlu/World Religions": 0.86,
         "helm_mmlu/Mean win rate": 0.774,
-        "reward-bench/Score": 0.5796,
-        "reward-bench/Chat": 0.9497,
-        "reward-bench/Chat Hard": 0.6075,
-        "reward-bench/Safety": 0.7667,
-        "reward-bench/Reasoning": 0.8374,
+        "reward-bench/Score": 0.8007,
         "reward-bench/Factuality": 0.4105,
         "reward-bench/Precise IF": 0.3438,
         "reward-bench/Math": 0.5191,
+        "reward-bench/Safety": 0.8081,
         "reward-bench/Focus": 0.7414,
-        "reward-bench/Ties": 0.6962
+        "reward-bench/Ties": 0.6962,
+        "reward-bench/Chat": 0.9497,
+        "reward-bench/Chat Hard": 0.6075,
+        "reward-bench/Reasoning": 0.8374
       }
     },
     {
@@ -877,7 +877,7 @@
       "developer": "OpenAI",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "terminal-bench-2.0/terminal-bench-2.0": 49.6
+        "terminal-bench-2.0/terminal-bench-2.0": 35.2
       }
     },
     {
@@ -922,7 +922,7 @@
       "developer": "OpenAI",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "terminal-bench-2.0/terminal-bench-2.0": 43.4
+        "terminal-bench-2.0/terminal-bench-2.0": 44.3
       }
     },
     {
@@ -931,7 +931,7 @@
       "developer": "OpenAI",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "terminal-bench-2.0/terminal-bench-2.0": 34.8
+        "terminal-bench-2.0/terminal-bench-2.0": 24.0
       }
     },
     {
@@ -954,7 +954,7 @@
       "developer": "OpenAI",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "terminal-bench-2.0/terminal-bench-2.0": 7.0
+        "terminal-bench-2.0/terminal-bench-2.0": 7.9
       }
     },
     {
@@ -1013,7 +1013,7 @@
       "developer": "OpenAI",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "terminal-bench-2.0/terminal-bench-2.0": 60.7
+        "terminal-bench-2.0/terminal-bench-2.0": 54.0
       }
     },
     {
@@ -1022,15 +1022,15 @@
       "developer": "OpenAI",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "appworld_test_normal/appworld/test_normal": 0.071,
-        "browsecompplus/browsecompplus": 0.46,
+        "appworld_test_normal/appworld/test_normal": 0.0,
+        "browsecompplus/browsecompplus": 0.43,
         "livecodebenchpro/Hard Problems": 0.1594,
         "livecodebenchpro/Medium Problems": 0.5211,
         "livecodebenchpro/Easy Problems": 0.9014,
-        "swe-bench/swe-bench": 0.57,
+        "swe-bench/swe-bench": 0.5455,
         "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
+        "tau-bench-2_telecom/tau-bench-2/telecom": 0.5354
       }
     },
     {
@@ -1233,9 +1233,9 @@
         "helm_capabilities/IFEval": 0.929,
         "helm_capabilities/WildBench": 0.854,
         "helm_capabilities/Omni-MATH": 0.72,
-        "livecodebenchpro/Hard Problems": 0.014084507042253521,
-        "livecodebenchpro/Medium Problems": 0.30985915492957744,
-        "livecodebenchpro/Easy Problems": 0.8873239436619719
+        "livecodebenchpro/Hard Problems": 0.0143,
+        "livecodebenchpro/Medium Problems": 0.2923,
+        "livecodebenchpro/Easy Problems": 0.8571
       }
     },
     {
diff --git a/data/developers/openbmb.json b/data/developers/openbmb.json
index d8dae84054074ce01b5c47fc58b69a148fdc99c0..dd2ac9b2651a2fee615e466e3b3da81ac3cfeef4 100644
--- a/data/developers/openbmb.json
+++ b/data/developers/openbmb.json
@@ -21,17 +21,17 @@
       "developer": "openbmb",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "reward-bench/Score": 0.8159,
+        "reward-bench/Score": 0.5806,
+        "reward-bench/Chat": 0.9804,
+        "reward-bench/Chat Hard": 0.6557,
+        "reward-bench/Safety": 0.6267,
+        "reward-bench/Reasoning": 0.8633,
+        "reward-bench/Prior Sets (0.5 weight)": 0.7172,
         "reward-bench/Factuality": 0.6,
         "reward-bench/Precise IF": 0.3438,
         "reward-bench/Math": 0.5683,
-        "reward-bench/Safety": 0.8135,
         "reward-bench/Focus": 0.7475,
-        "reward-bench/Ties": 0.5972,
-        "reward-bench/Chat": 0.9804,
-        "reward-bench/Chat Hard": 0.6557,
-        "reward-bench/Reasoning": 0.8633,
-        "reward-bench/Prior Sets (0.5 weight)": 0.7172
+        "reward-bench/Ties": 0.5972
       }
     },
     {
@@ -68,17 +68,17 @@
       "developer": "openbmb",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "reward-bench/Score": 0.4683,
-        "reward-bench/Chat": 0.9637,
-        "reward-bench/Chat Hard": 0.5548,
-        "reward-bench/Safety": 0.5089,
-        "reward-bench/Reasoning": 0.6244,
-        "reward-bench/Prior Sets (0.5 weight)": 0.7294,
+        "reward-bench/Score": 0.6903,
         "reward-bench/Factuality": 0.5063,
         "reward-bench/Precise IF": 0.3312,
         "reward-bench/Math": 0.5519,
+        "reward-bench/Safety": 0.5986,
         "reward-bench/Focus": 0.6081,
-        "reward-bench/Ties": 0.3036
+        "reward-bench/Ties": 0.3036,
+        "reward-bench/Chat": 0.9637,
+        "reward-bench/Chat Hard": 0.5548,
+        "reward-bench/Reasoning": 0.6244,
+        "reward-bench/Prior Sets (0.5 weight)": 0.7294
       }
     }
   ]
diff --git a/data/developers/pku-alignment.json b/data/developers/pku-alignment.json
index b42d9be156feba13e7cdbffbd62351a64e28c1fb..4cebe3d4c55c06b2bbbd44b7bb6fe487a030b922 100644
--- a/data/developers/pku-alignment.json
+++ b/data/developers/pku-alignment.json
@@ -7,17 +7,17 @@
       "developer": "PKU-Alignment",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "reward-bench/Score": 0.5798,
+        "reward-bench/Score": 0.3332,
+        "reward-bench/Chat": 0.6173,
+        "reward-bench/Chat Hard": 0.4232,
+        "reward-bench/Safety": 0.7589,
+        "reward-bench/Reasoning": 0.5482,
+        "reward-bench/Prior Sets (0.5 weight)": 0.57,
         "reward-bench/Factuality": 0.3263,
         "reward-bench/Precise IF": 0.2313,
         "reward-bench/Math": 0.3989,
-        "reward-bench/Safety": 0.7351,
         "reward-bench/Focus": 0.2939,
-        "reward-bench/Ties": -0.01,
-        "reward-bench/Chat": 0.6173,
-        "reward-bench/Chat Hard": 0.4232,
-        "reward-bench/Reasoning": 0.5482,
-        "reward-bench/Prior Sets (0.5 weight)": 0.57
+        "reward-bench/Ties": -0.01
       }
     },
     {
diff --git a/data/developers/primeintellect.json b/data/developers/primeintellect.json
index 160722785b06f80d9b220dee435fad1245d45495..674a0e3b141480d7e0d33d0a2fe9b205b710216f 100644
--- a/data/developers/primeintellect.json
+++ b/data/developers/primeintellect.json
@@ -8,11 +8,11 @@
       "evaluator_relationship": null,
       "benchmark_scores": {
         "hfopenllm_v2/IFEval": 0.1757,
-        "hfopenllm_v2/BBH": 0.274,
+        "hfopenllm_v2/BBH": 0.276,
         "hfopenllm_v2/MATH Level 5": 0.0,
-        "hfopenllm_v2/GPQA": 0.25,
-        "hfopenllm_v2/MUSR": 0.3753,
-        "hfopenllm_v2/MMLU-PRO": 0.112
+        "hfopenllm_v2/GPQA": 0.2534,
+        "hfopenllm_v2/MUSR": 0.3339,
+        "hfopenllm_v2/MMLU-PRO": 0.1123
       }
     },
     {
diff --git a/data/developers/qingy2019.json b/data/developers/qingy2019.json
index 3885f54f7f780ebe87cee5b8aacc1c1136f4441f..9e607d380bbf6837078a684f50c178b1c83bab9f 100644
--- a/data/developers/qingy2019.json
+++ b/data/developers/qingy2019.json
@@ -35,12 +35,12 @@
       "developer": "qingy2019",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "hfopenllm_v2/IFEval": 0.2358,
-        "hfopenllm_v2/BBH": 0.4612,
-        "hfopenllm_v2/MATH Level 5": 0.0642,
-        "hfopenllm_v2/GPQA": 0.2576,
-        "hfopenllm_v2/MUSR": 0.3717,
-        "hfopenllm_v2/MMLU-PRO": 0.2382
+        "hfopenllm_v2/IFEval": 0.2401,
+        "hfopenllm_v2/BBH": 0.4622,
+        "hfopenllm_v2/MATH Level 5": 0.0725,
+        "hfopenllm_v2/GPQA": 0.2609,
+        "hfopenllm_v2/MUSR": 0.3703,
+        "hfopenllm_v2/MMLU-PRO": 0.2379
       }
     },
     {
@@ -49,12 +49,12 @@
       "developer": "qingy2019",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "hfopenllm_v2/IFEval": 0.6066,
-        "hfopenllm_v2/BBH": 0.635,
-        "hfopenllm_v2/MATH Level 5": 0.3716,
-        "hfopenllm_v2/GPQA": 0.3725,
+        "hfopenllm_v2/IFEval": 0.6005,
+        "hfopenllm_v2/BBH": 0.6356,
+        "hfopenllm_v2/MATH Level 5": 0.2764,
+        "hfopenllm_v2/GPQA": 0.3691,
         "hfopenllm_v2/MUSR": 0.4757,
-        "hfopenllm_v2/MMLU-PRO": 0.5331
+        "hfopenllm_v2/MMLU-PRO": 0.5339
       }
     },
     {
diff --git a/data/developers/ray2333.json b/data/developers/ray2333.json
index 709d24161c8237750555868d00eabe667376cddb..e188da7e1b361f275f3618471481e7b52afe105b 100644
--- a/data/developers/ray2333.json
+++ b/data/developers/ray2333.json
@@ -79,17 +79,17 @@
       "developer": "Ray2333",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "reward-bench/Score": 0.589,
-        "reward-bench/Chat": 0.9832,
-        "reward-bench/Chat Hard": 0.6842,
-        "reward-bench/Safety": 0.7222,
-        "reward-bench/Reasoning": 0.9133,
-        "reward-bench/Prior Sets (0.5 weight)": 0.7209,
+        "reward-bench/Score": 0.8464,
         "reward-bench/Factuality": 0.5874,
         "reward-bench/Precise IF": 0.3875,
         "reward-bench/Math": 0.5902,
+        "reward-bench/Safety": 0.8676,
         "reward-bench/Focus": 0.6727,
-        "reward-bench/Ties": 0.5743
+        "reward-bench/Ties": 0.5743,
+        "reward-bench/Chat": 0.9832,
+        "reward-bench/Chat Hard": 0.6842,
+        "reward-bench/Reasoning": 0.9133,
+        "reward-bench/Prior Sets (0.5 weight)": 0.7209
       }
     },
     {
diff --git a/data/developers/replete-ai.json b/data/developers/replete-ai.json
index 0f038b31b0c0cf28a02b6c25fb4fd9bd374c118c..dbb06f00736a7fcddf76b24a5c7673e098ecab57 100644
--- a/data/developers/replete-ai.json
+++ b/data/developers/replete-ai.json
@@ -91,12 +91,12 @@
       "developer": "Replete-AI",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "hfopenllm_v2/IFEval": 0.0905,
-        "hfopenllm_v2/BBH": 0.2985,
+        "hfopenllm_v2/IFEval": 0.0932,
+        "hfopenllm_v2/BBH": 0.2977,
         "hfopenllm_v2/MATH Level 5": 0.0,
-        "hfopenllm_v2/GPQA": 0.2534,
-        "hfopenllm_v2/MUSR": 0.3848,
-        "hfopenllm_v2/MMLU-PRO": 0.1158
+        "hfopenllm_v2/GPQA": 0.2475,
+        "hfopenllm_v2/MUSR": 0.3941,
+        "hfopenllm_v2/MMLU-PRO": 0.1157
       }
     },
     {
diff --git a/data/developers/riaz.json b/data/developers/riaz.json
index 342d5654379425c9866753c909eb0413c18e5c77..d54f5bbaf70d322fa875b56275f987dd3ae70f34 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": 0.4137,
-        "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
+        "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
       }
     }
   ]
diff --git a/data/developers/sao10k.json b/data/developers/sao10k.json
index e66900f1906266fdf37e55995d3b04130f5b6fd2..6569058a39b468de833ea3ab9419e073af211e5a 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": 0.7384,
-        "hfopenllm_v2/BBH": 0.6471,
-        "hfopenllm_v2/MATH Level 5": 0.2137,
+        "hfopenllm_v2/IFEval": 0.7281,
+        "hfopenllm_v2/BBH": 0.6503,
+        "hfopenllm_v2/MATH Level 5": 0.2243,
         "hfopenllm_v2/GPQA": 0.3314,
-        "hfopenllm_v2/MUSR": 0.4209,
-        "hfopenllm_v2/MMLU-PRO": 0.5104
+        "hfopenllm_v2/MUSR": 0.4196,
+        "hfopenllm_v2/MMLU-PRO": 0.5096
       }
     },
     {
diff --git a/data/developers/sfairxc.json b/data/developers/sfairxc.json
index 0f83a5aa819fcf69906563e63fd5c5a7cc1f8ce0..f511504fa472f754b653d8fff6432038f2fa5642 100644
--- a/data/developers/sfairxc.json
+++ b/data/developers/sfairxc.json
@@ -7,17 +7,17 @@
       "developer": "sfairXC",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "reward-bench/Score": 0.8338,
+        "reward-bench/Score": 0.6292,
+        "reward-bench/Chat": 0.9944,
+        "reward-bench/Chat Hard": 0.6513,
+        "reward-bench/Safety": 0.7667,
+        "reward-bench/Reasoning": 0.8644,
+        "reward-bench/Prior Sets (0.5 weight)": 0.7492,
         "reward-bench/Factuality": 0.5916,
         "reward-bench/Precise IF": 0.4188,
         "reward-bench/Math": 0.6284,
-        "reward-bench/Safety": 0.8676,
         "reward-bench/Focus": 0.7051,
-        "reward-bench/Ties": 0.6647,
-        "reward-bench/Chat": 0.9944,
-        "reward-bench/Chat Hard": 0.6513,
-        "reward-bench/Reasoning": 0.8644,
-        "reward-bench/Prior Sets (0.5 weight)": 0.7492
+        "reward-bench/Ties": 0.6647
       }
     }
   ]
diff --git a/data/developers/skywork.json b/data/developers/skywork.json
index b75ac4fa3e86dd1c341887c14306e39e694944d2..310fc474921f3ff87a2e73d5f74077c21e25d2fe 100644
--- a/data/developers/skywork.json
+++ b/data/developers/skywork.json
@@ -47,16 +47,16 @@
       "developer": "Skywork",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "reward-bench/Score": 0.938,
+        "reward-bench/Score": 0.7576,
+        "reward-bench/Chat": 0.9581,
+        "reward-bench/Chat Hard": 0.9145,
+        "reward-bench/Safety": 0.9422,
+        "reward-bench/Reasoning": 0.9606,
         "reward-bench/Factuality": 0.7368,
         "reward-bench/Precise IF": 0.4031,
         "reward-bench/Math": 0.7049,
-        "reward-bench/Safety": 0.9189,
         "reward-bench/Focus": 0.9323,
-        "reward-bench/Ties": 0.8261,
-        "reward-bench/Chat": 0.9581,
-        "reward-bench/Chat Hard": 0.9145,
-        "reward-bench/Reasoning": 0.9606
+        "reward-bench/Ties": 0.8261
       }
     },
     {
@@ -89,16 +89,16 @@
       "developer": "Skywork",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "reward-bench/Score": 0.7314,
-        "reward-bench/Chat": 0.9581,
-        "reward-bench/Chat Hard": 0.8728,
-        "reward-bench/Safety": 0.9333,
-        "reward-bench/Reasoning": 0.962,
+        "reward-bench/Score": 0.9252,
         "reward-bench/Factuality": 0.6989,
         "reward-bench/Precise IF": 0.425,
         "reward-bench/Math": 0.6284,
+        "reward-bench/Safety": 0.9081,
         "reward-bench/Focus": 0.9616,
-        "reward-bench/Ties": 0.741
+        "reward-bench/Ties": 0.741,
+        "reward-bench/Chat": 0.9581,
+        "reward-bench/Chat Hard": 0.8728,
+        "reward-bench/Reasoning": 0.962
       }
     },
     {
@@ -230,16 +230,16 @@
       "developer": "Skywork",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "reward-bench/Score": 0.9007,
+        "reward-bench/Score": 0.6885,
+        "reward-bench/Chat": 0.8994,
+        "reward-bench/Chat Hard": 0.875,
+        "reward-bench/Safety": 0.8911,
+        "reward-bench/Reasoning": 0.9176,
         "reward-bench/Factuality": 0.6063,
         "reward-bench/Precise IF": 0.35,
         "reward-bench/Math": 0.6339,
-        "reward-bench/Safety": 0.9108,
         "reward-bench/Focus": 0.8909,
-        "reward-bench/Ties": 0.7586,
-        "reward-bench/Chat": 0.8994,
-        "reward-bench/Chat Hard": 0.875,
-        "reward-bench/Reasoning": 0.9176
+        "reward-bench/Ties": 0.7586
       }
     }
   ]
diff --git a/data/developers/sometimesanotion.json b/data/developers/sometimesanotion.json
index c020e85fc5c690d215cbd09f94a114e50c6a6936..b756bb971c60b6bcad2e85989edb63b8a758fe59 100644
--- a/data/developers/sometimesanotion.json
+++ b/data/developers/sometimesanotion.json
@@ -749,12 +749,12 @@
       "developer": "sometimesanotion",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "hfopenllm_v2/IFEval": 0.5278,
-        "hfopenllm_v2/BBH": 0.6557,
-        "hfopenllm_v2/MATH Level 5": 0.3119,
-        "hfopenllm_v2/GPQA": 0.3842,
-        "hfopenllm_v2/MUSR": 0.4754,
-        "hfopenllm_v2/MMLU-PRO": 0.5396
+        "hfopenllm_v2/IFEval": 0.5367,
+        "hfopenllm_v2/BBH": 0.6561,
+        "hfopenllm_v2/MATH Level 5": 0.358,
+        "hfopenllm_v2/GPQA": 0.3867,
+        "hfopenllm_v2/MUSR": 0.474,
+        "hfopenllm_v2/MMLU-PRO": 0.5395
       }
     },
     {
diff --git a/data/developers/spow12.json b/data/developers/spow12.json
index 39b5b7b70e78310868166d1a8d2f2ae80dc77b8f..fbe5ef8e79c87a1486a23e55dcad74bc6e42909c 100644
--- a/data/developers/spow12.json
+++ b/data/developers/spow12.json
@@ -49,12 +49,12 @@
       "developer": "spow12",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "hfopenllm_v2/IFEval": 0.6511,
-        "hfopenllm_v2/BBH": 0.5926,
-        "hfopenllm_v2/MATH Level 5": 0.1858,
-        "hfopenllm_v2/GPQA": 0.3247,
+        "hfopenllm_v2/IFEval": 0.6517,
+        "hfopenllm_v2/BBH": 0.5908,
+        "hfopenllm_v2/MATH Level 5": 0.2032,
+        "hfopenllm_v2/GPQA": 0.3238,
         "hfopenllm_v2/MUSR": 0.3842,
-        "hfopenllm_v2/MMLU-PRO": 0.3836
+        "hfopenllm_v2/MMLU-PRO": 0.3812
       }
     }
   ]
diff --git a/data/developers/tanliboy.json b/data/developers/tanliboy.json
index 7b17e651b33310ae087a6456408950e1456ff623..daa17945601d8528cbfc7c883e4dc4315ea363fc 100644
--- a/data/developers/tanliboy.json
+++ b/data/developers/tanliboy.json
@@ -7,12 +7,12 @@
       "developer": "tanliboy",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "hfopenllm_v2/IFEval": 0.1829,
-        "hfopenllm_v2/BBH": 0.5488,
-        "hfopenllm_v2/MATH Level 5": 0.0,
-        "hfopenllm_v2/GPQA": 0.3104,
-        "hfopenllm_v2/MUSR": 0.4056,
-        "hfopenllm_v2/MMLU-PRO": 0.3805
+        "hfopenllm_v2/IFEval": 0.4501,
+        "hfopenllm_v2/BBH": 0.5472,
+        "hfopenllm_v2/MATH Level 5": 0.0944,
+        "hfopenllm_v2/GPQA": 0.3138,
+        "hfopenllm_v2/MUSR": 0.4017,
+        "hfopenllm_v2/MMLU-PRO": 0.3792
       }
     },
     {
diff --git a/data/developers/valiantlabs.json b/data/developers/valiantlabs.json
index a0fc2b3d81b7ddfe31ae4c63f4f370e45c708501..d692f13110a559faa51989d7851579fce9b6dc8e 100644
--- a/data/developers/valiantlabs.json
+++ b/data/developers/valiantlabs.json
@@ -49,12 +49,12 @@
       "developer": "ValiantLabs",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "hfopenllm_v2/IFEval": 0.7168,
-        "hfopenllm_v2/BBH": 0.4911,
-        "hfopenllm_v2/MATH Level 5": 0.1533,
-        "hfopenllm_v2/GPQA": 0.2861,
-        "hfopenllm_v2/MUSR": 0.3512,
-        "hfopenllm_v2/MMLU-PRO": 0.3663
+        "hfopenllm_v2/IFEval": 0.3496,
+        "hfopenllm_v2/BBH": 0.4947,
+        "hfopenllm_v2/MATH Level 5": 0.1269,
+        "hfopenllm_v2/GPQA": 0.3037,
+        "hfopenllm_v2/MUSR": 0.3959,
+        "hfopenllm_v2/MMLU-PRO": 0.3644
       }
     },
     {
@@ -105,12 +105,12 @@
       "developer": "ValiantLabs",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "hfopenllm_v2/IFEval": 0.2678,
-        "hfopenllm_v2/BBH": 0.4429,
-        "hfopenllm_v2/MATH Level 5": 0.0521,
-        "hfopenllm_v2/GPQA": 0.302,
-        "hfopenllm_v2/MUSR": 0.3959,
-        "hfopenllm_v2/MMLU-PRO": 0.2927
+        "hfopenllm_v2/IFEval": 0.6496,
+        "hfopenllm_v2/BBH": 0.4774,
+        "hfopenllm_v2/MATH Level 5": 0.0566,
+        "hfopenllm_v2/GPQA": 0.3104,
+        "hfopenllm_v2/MUSR": 0.3909,
+        "hfopenllm_v2/MMLU-PRO": 0.3382
       }
     },
     {
diff --git a/data/developers/weqweasdas.json b/data/developers/weqweasdas.json
index e11faa49d0109edbe3a144d975a897042bc51bca..53701e6ba9018d055fac2463f132ffbb9e4ba26c 100644
--- a/data/developers/weqweasdas.json
+++ b/data/developers/weqweasdas.json
@@ -7,17 +7,17 @@
       "developer": "weqweasdas",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "reward-bench/Score": 0.5027,
+        "reward-bench/Score": 0.2498,
+        "reward-bench/Chat": 0.8184,
+        "reward-bench/Chat Hard": 0.3728,
+        "reward-bench/Safety": 0.24,
+        "reward-bench/Reasoning": 0.3281,
+        "reward-bench/Prior Sets (0.5 weight)": 0.6564,
         "reward-bench/Factuality": 0.3642,
         "reward-bench/Precise IF": 0.275,
         "reward-bench/Math": 0.3497,
-        "reward-bench/Safety": 0.4149,
         "reward-bench/Focus": 0.2384,
-        "reward-bench/Ties": 0.0315,
-        "reward-bench/Chat": 0.8184,
-        "reward-bench/Chat Hard": 0.3728,
-        "reward-bench/Reasoning": 0.3281,
-        "reward-bench/Prior Sets (0.5 weight)": 0.6564
+        "reward-bench/Ties": 0.0315
       }
     },
     {
@@ -26,17 +26,17 @@
       "developer": "weqweasdas",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "reward-bench/Score": 0.3057,
-        "reward-bench/Chat": 0.9441,
-        "reward-bench/Chat Hard": 0.4079,
-        "reward-bench/Safety": 0.3311,
-        "reward-bench/Reasoning": 0.7637,
-        "reward-bench/Prior Sets (0.5 weight)": 0.6652,
+        "reward-bench/Score": 0.6549,
         "reward-bench/Factuality": 0.3705,
         "reward-bench/Precise IF": 0.2812,
         "reward-bench/Math": 0.4317,
+        "reward-bench/Safety": 0.4986,
         "reward-bench/Focus": 0.2343,
-        "reward-bench/Ties": 0.1851
+        "reward-bench/Ties": 0.1851,
+        "reward-bench/Chat": 0.9441,
+        "reward-bench/Chat Hard": 0.4079,
+        "reward-bench/Reasoning": 0.7637,
+        "reward-bench/Prior Sets (0.5 weight)": 0.6652
       }
     },
     {
@@ -78,17 +78,17 @@
       "developer": "weqweasdas",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "reward-bench/Score": 0.596,
-        "reward-bench/Chat": 0.9665,
-        "reward-bench/Chat Hard": 0.6053,
-        "reward-bench/Safety": 0.6911,
-        "reward-bench/Reasoning": 0.7736,
-        "reward-bench/Prior Sets (0.5 weight)": 0.753,
+        "reward-bench/Score": 0.7982,
         "reward-bench/Factuality": 0.5937,
         "reward-bench/Precise IF": 0.3438,
         "reward-bench/Math": 0.5956,
+        "reward-bench/Safety": 0.8703,
         "reward-bench/Focus": 0.7293,
-        "reward-bench/Ties": 0.6226
+        "reward-bench/Ties": 0.6226,
+        "reward-bench/Chat": 0.9665,
+        "reward-bench/Chat Hard": 0.6053,
+        "reward-bench/Reasoning": 0.7736,
+        "reward-bench/Prior Sets (0.5 weight)": 0.753
       }
     }
   ]
diff --git a/data/developers/xai.json b/data/developers/xai.json
index 4539ab8505af399ecb6f06dee4d4f2618de3e3bc..d0ba30a6d3c372a4bdb6c48d3c0cb90677ed30d5 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": 25.8
+        "terminal-bench-2.0/terminal-bench-2.0": 14.2
       }
     }
   ]
diff --git a/data/developers/ycros.json b/data/developers/ycros.json
index e95400442aba80bbdb2ffa85224e7399ce946b0d..9b83f7f872f197f98fd71538cda202af618f5659 100644
--- a/data/developers/ycros.json
+++ b/data/developers/ycros.json
@@ -7,12 +7,12 @@
       "developer": "ycros",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "hfopenllm_v2/IFEval": 0.6262,
-        "hfopenllm_v2/BBH": 0.5142,
-        "hfopenllm_v2/MATH Level 5": 0.0937,
-        "hfopenllm_v2/GPQA": 0.3079,
-        "hfopenllm_v2/MUSR": 0.4138,
-        "hfopenllm_v2/MMLU-PRO": 0.3481
+        "hfopenllm_v2/IFEval": 0.5994,
+        "hfopenllm_v2/BBH": 0.5159,
+        "hfopenllm_v2/MATH Level 5": 0.0785,
+        "hfopenllm_v2/GPQA": 0.3045,
+        "hfopenllm_v2/MUSR": 0.4203,
+        "hfopenllm_v2/MMLU-PRO": 0.3473
       }
     }
   ]
diff --git a/data/developers/yoyo-ai.json b/data/developers/yoyo-ai.json
index d0e307257898b20d6b2c21faa52d04a28d7cca51..9dcbc81e86094f67bbf3f24e1917205fb4cc44f8 100644
--- a/data/developers/yoyo-ai.json
+++ b/data/developers/yoyo-ai.json
@@ -105,12 +105,12 @@
       "developer": "YOYO-AI",
       "evaluator_relationship": null,
       "benchmark_scores": {
-        "hfopenllm_v2/IFEval": 0.7905,
-        "hfopenllm_v2/BBH": 0.6406,
-        "hfopenllm_v2/MATH Level 5": 0.0,
-        "hfopenllm_v2/GPQA": 0.3163,
-        "hfopenllm_v2/MUSR": 0.4181,
-        "hfopenllm_v2/MMLU-PRO": 0.4944
+        "hfopenllm_v2/IFEval": 0.5899,
+        "hfopenllm_v2/BBH": 0.654,
+        "hfopenllm_v2/MATH Level 5": 0.4509,
+        "hfopenllm_v2/GPQA": 0.3834,
+        "hfopenllm_v2/MUSR": 0.4744,
+        "hfopenllm_v2/MMLU-PRO": 0.5376
       }
     },
     {
diff --git a/data/models.json b/data/models.json
index a5af0007574aa89e984bf7d8a4b2911e04bfd788..12fa873edd89b9fe064fc8ee02af3da9906fdc49 100644
--- a/data/models.json
+++ b/data/models.json
@@ -1391,10 +1391,10 @@
     "developer": "AI2",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "reward-bench/Score": 0.6924,
-      "reward-bench/Chat": 0.9441,
-      "reward-bench/Chat Hard": 0.3575,
-      "reward-bench/Safety": 0.7757
+      "reward-bench/Score": 0.6895,
+      "reward-bench/Chat": 0.9385,
+      "reward-bench/Chat Hard": 0.3706,
+      "reward-bench/Safety": 0.7595
     }
   },
   {
@@ -2036,12 +2036,12 @@
     "developer": "akjindal53244",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "hfopenllm_v2/IFEval": 0.8051,
-      "hfopenllm_v2/BBH": 0.5189,
-      "hfopenllm_v2/MATH Level 5": 0.1722,
-      "hfopenllm_v2/GPQA": 0.3263,
+      "hfopenllm_v2/IFEval": 0.8033,
+      "hfopenllm_v2/BBH": 0.5196,
+      "hfopenllm_v2/MATH Level 5": 0.1624,
+      "hfopenllm_v2/GPQA": 0.3096,
       "hfopenllm_v2/MUSR": 0.4028,
-      "hfopenllm_v2/MMLU-PRO": 0.3803
+      "hfopenllm_v2/MMLU-PRO": 0.3812
     }
   },
   {
@@ -2243,7 +2243,7 @@
     "developer": "Alibaba",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "terminal-bench-2.0/terminal-bench-2.0": 23.9
+      "terminal-bench-2.0/terminal-bench-2.0": 27.2
     }
   },
   {
@@ -2489,17 +2489,17 @@
     "developer": "allenai",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "reward-bench/Score": 0.722,
-      "reward-bench/Chat": 0.9693,
-      "reward-bench/Chat Hard": 0.8268,
-      "reward-bench/Safety": 0.8689,
-      "reward-bench/Reasoning": 0.8583,
-      "reward-bench/Prior Sets (0.5 weight)": 0.0,
+      "reward-bench/Score": 0.8892,
       "reward-bench/Factuality": 0.8084,
       "reward-bench/Precise IF": 0.3688,
       "reward-bench/Math": 0.6776,
+      "reward-bench/Safety": 0.9027,
       "reward-bench/Focus": 0.7778,
-      "reward-bench/Ties": 0.8308
+      "reward-bench/Ties": 0.8308,
+      "reward-bench/Chat": 0.9693,
+      "reward-bench/Chat Hard": 0.8268,
+      "reward-bench/Reasoning": 0.8583,
+      "reward-bench/Prior Sets (0.5 weight)": 0.0
     }
   },
   {
@@ -2508,12 +2508,12 @@
     "developer": "allenai",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "hfopenllm_v2/IFEval": 0.8255,
-      "hfopenllm_v2/BBH": 0.4061,
-      "hfopenllm_v2/MATH Level 5": 0.2115,
-      "hfopenllm_v2/GPQA": 0.297,
+      "hfopenllm_v2/IFEval": 0.8267,
+      "hfopenllm_v2/BBH": 0.405,
+      "hfopenllm_v2/MATH Level 5": 0.1964,
+      "hfopenllm_v2/GPQA": 0.2987,
       "hfopenllm_v2/MUSR": 0.4175,
-      "hfopenllm_v2/MMLU-PRO": 0.2821
+      "hfopenllm_v2/MMLU-PRO": 0.2827
     }
   },
   {
@@ -2536,17 +2536,17 @@
     "developer": "allenai",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "reward-bench/Score": 0.8431,
+      "reward-bench/Score": 0.687,
+      "reward-bench/Chat": 0.9553,
+      "reward-bench/Chat Hard": 0.761,
+      "reward-bench/Safety": 0.86,
+      "reward-bench/Reasoning": 0.7898,
+      "reward-bench/Prior Sets (0.5 weight)": 0.0,
       "reward-bench/Factuality": 0.7516,
       "reward-bench/Precise IF": 0.3875,
       "reward-bench/Math": 0.6284,
-      "reward-bench/Safety": 0.8662,
       "reward-bench/Focus": 0.8545,
-      "reward-bench/Ties": 0.6397,
-      "reward-bench/Chat": 0.9553,
-      "reward-bench/Chat Hard": 0.761,
-      "reward-bench/Reasoning": 0.7898,
-      "reward-bench/Prior Sets (0.5 weight)": 0.0
+      "reward-bench/Ties": 0.6397
     }
   },
   {
@@ -6556,11 +6556,11 @@
     "developer": "amd",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "hfopenllm_v2/IFEval": 0.1842,
-      "hfopenllm_v2/BBH": 0.2974,
-      "hfopenllm_v2/MATH Level 5": 0.0053,
-      "hfopenllm_v2/GPQA": 0.2525,
-      "hfopenllm_v2/MUSR": 0.378,
+      "hfopenllm_v2/IFEval": 0.1918,
+      "hfopenllm_v2/BBH": 0.2969,
+      "hfopenllm_v2/MATH Level 5": 0.0076,
+      "hfopenllm_v2/GPQA": 0.2584,
+      "hfopenllm_v2/MUSR": 0.3846,
       "hfopenllm_v2/MMLU-PRO": 0.1169
     }
   },
@@ -7167,17 +7167,17 @@
       "helm_mmlu/Virology": 0.542,
       "helm_mmlu/World Religions": 0.871,
       "helm_mmlu/Mean win rate": 0.28,
-      "reward-bench/Score": 0.3711,
-      "reward-bench/Chat": 0.9274,
-      "reward-bench/Chat Hard": 0.5197,
-      "reward-bench/Safety": 0.595,
-      "reward-bench/Reasoning": 0.706,
-      "reward-bench/Prior Sets (0.5 weight)": 0.6635,
+      "reward-bench/Score": 0.7289,
       "reward-bench/Factuality": 0.4042,
       "reward-bench/Precise IF": 0.2812,
       "reward-bench/Math": 0.3552,
+      "reward-bench/Safety": 0.7953,
       "reward-bench/Focus": 0.501,
-      "reward-bench/Ties": 0.0899
+      "reward-bench/Ties": 0.0899,
+      "reward-bench/Chat": 0.9274,
+      "reward-bench/Chat Hard": 0.5197,
+      "reward-bench/Reasoning": 0.706,
+      "reward-bench/Prior Sets (0.5 weight)": 0.6635
     }
   },
   {
@@ -7232,16 +7232,16 @@
       "helm_mmlu/Virology": 0.578,
       "helm_mmlu/World Religions": 0.901,
       "helm_mmlu/Mean win rate": 0.014,
-      "reward-bench/Score": 0.8008,
+      "reward-bench/Score": 0.5744,
+      "reward-bench/Chat": 0.9469,
+      "reward-bench/Chat Hard": 0.6031,
+      "reward-bench/Safety": 0.8378,
+      "reward-bench/Reasoning": 0.7868,
       "reward-bench/Factuality": 0.5389,
       "reward-bench/Precise IF": 0.3312,
       "reward-bench/Math": 0.5137,
-      "reward-bench/Safety": 0.8662,
       "reward-bench/Focus": 0.6646,
-      "reward-bench/Ties": 0.5601,
-      "reward-bench/Chat": 0.9469,
-      "reward-bench/Chat Hard": 0.6031,
-      "reward-bench/Reasoning": 0.7868
+      "reward-bench/Ties": 0.5601
     }
   },
   {
@@ -7321,7 +7321,7 @@
     "developer": "Anthropic",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "terminal-bench-2.0/terminal-bench-2.0": 13.9
+      "terminal-bench-2.0/terminal-bench-2.0": 28.3
     }
   },
   {
@@ -7446,11 +7446,11 @@
     "developer": "Anthropic",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "appworld_test_normal/appworld/test_normal": 0.66,
+      "appworld_test_normal/appworld/test_normal": 0.68,
       "browsecompplus/browsecompplus": 0.49,
-      "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,
+      "swe-bench/swe-bench": 0.8072,
+      "tau-bench-2_airline/tau-bench-2/airline": 0.66,
+      "tau-bench-2_retail/tau-bench-2/retail": 0.83,
       "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": 36.9
+      "terminal-bench-2.0/terminal-bench-2.0": 34.8
     }
   },
   {
@@ -7478,7 +7478,7 @@
     "developer": "Anthropic",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "terminal-bench-2.0/terminal-bench-2.0": 74.7
+      "terminal-bench-2.0/terminal-bench-2.0": 62.9
     }
   },
   {
@@ -7730,12 +7730,12 @@
     "developer": "arcee-ai",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "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
+      "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
     }
   },
   {
@@ -10599,12 +10599,12 @@
     "developer": "bunnycore",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "hfopenllm_v2/IFEval": 0.1775,
-      "hfopenllm_v2/BBH": 0.295,
-      "hfopenllm_v2/MATH Level 5": 0.0,
-      "hfopenllm_v2/GPQA": 0.2517,
-      "hfopenllm_v2/MUSR": 0.3647,
-      "hfopenllm_v2/MMLU-PRO": 0.1049
+      "hfopenllm_v2/IFEval": 0.4652,
+      "hfopenllm_v2/BBH": 0.4531,
+      "hfopenllm_v2/MATH Level 5": 0.1284,
+      "hfopenllm_v2/GPQA": 0.2643,
+      "hfopenllm_v2/MUSR": 0.3394,
+      "hfopenllm_v2/MMLU-PRO": 0.3152
     }
   },
   {
@@ -11828,17 +11828,17 @@
     "developer": "CIR-AMS",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "reward-bench/Score": 0.8172,
+      "reward-bench/Score": 0.5736,
+      "reward-bench/Chat": 0.9749,
+      "reward-bench/Chat Hard": 0.5724,
+      "reward-bench/Safety": 0.7178,
+      "reward-bench/Reasoning": 0.8775,
+      "reward-bench/Prior Sets (0.5 weight)": 0.7029,
       "reward-bench/Factuality": 0.5347,
       "reward-bench/Precise IF": 0.3563,
       "reward-bench/Math": 0.6066,
-      "reward-bench/Safety": 0.9014,
       "reward-bench/Focus": 0.5737,
-      "reward-bench/Ties": 0.6527,
-      "reward-bench/Chat": 0.9749,
-      "reward-bench/Chat Hard": 0.5724,
-      "reward-bench/Reasoning": 0.8775,
-      "reward-bench/Prior Sets (0.5 weight)": 0.7029
+      "reward-bench/Ties": 0.6527
     }
   },
   {
@@ -12127,12 +12127,12 @@
     "developer": "cognitivecomputations",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "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
+      "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
     }
   },
   {
@@ -14142,12 +14142,12 @@
     "developer": "Daemontatox",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "hfopenllm_v2/IFEval": 0.4383,
-      "hfopenllm_v2/BBH": 0.5034,
-      "hfopenllm_v2/MATH Level 5": 0.1443,
+      "hfopenllm_v2/IFEval": 0.4398,
+      "hfopenllm_v2/BBH": 0.5066,
+      "hfopenllm_v2/MATH Level 5": 0.1488,
       "hfopenllm_v2/GPQA": 0.3238,
-      "hfopenllm_v2/MUSR": 0.4052,
-      "hfopenllm_v2/MMLU-PRO": 0.3778
+      "hfopenllm_v2/MUSR": 0.4079,
+      "hfopenllm_v2/MMLU-PRO": 0.3804
     }
   },
   {
@@ -14226,12 +14226,12 @@
     "developer": "Daemontatox",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "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
+      "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
     }
   },
   {
@@ -15393,12 +15393,12 @@
     "developer": "DavieLion",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "hfopenllm_v2/IFEval": 0.1507,
-      "hfopenllm_v2/BBH": 0.293,
-      "hfopenllm_v2/MATH Level 5": 0.0,
-      "hfopenllm_v2/GPQA": 0.2534,
+      "hfopenllm_v2/IFEval": 0.1549,
+      "hfopenllm_v2/BBH": 0.2937,
+      "hfopenllm_v2/MATH Level 5": 0.006,
+      "hfopenllm_v2/GPQA": 0.2576,
       "hfopenllm_v2/MUSR": 0.3565,
-      "hfopenllm_v2/MMLU-PRO": 0.1125
+      "hfopenllm_v2/MMLU-PRO": 0.1128
     }
   },
   {
@@ -15729,12 +15729,12 @@
     "developer": "DeepMount00",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "hfopenllm_v2/IFEval": 0.5365,
-      "hfopenllm_v2/BBH": 0.517,
-      "hfopenllm_v2/MATH Level 5": 0.1707,
-      "hfopenllm_v2/GPQA": 0.3062,
-      "hfopenllm_v2/MUSR": 0.4487,
-      "hfopenllm_v2/MMLU-PRO": 0.396
+      "hfopenllm_v2/IFEval": 0.7917,
+      "hfopenllm_v2/BBH": 0.5109,
+      "hfopenllm_v2/MATH Level 5": 0.1088,
+      "hfopenllm_v2/GPQA": 0.2878,
+      "hfopenllm_v2/MUSR": 0.4136,
+      "hfopenllm_v2/MMLU-PRO": 0.3876
     }
   },
   {
@@ -20340,12 +20340,12 @@
     "developer": "EpistemeAI",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "hfopenllm_v2/IFEval": 0.7305,
-      "hfopenllm_v2/BBH": 0.4649,
-      "hfopenllm_v2/MATH Level 5": 0.1397,
-      "hfopenllm_v2/GPQA": 0.2659,
-      "hfopenllm_v2/MUSR": 0.3209,
-      "hfopenllm_v2/MMLU-PRO": 0.348
+      "hfopenllm_v2/IFEval": 0.7207,
+      "hfopenllm_v2/BBH": 0.461,
+      "hfopenllm_v2/MATH Level 5": 0.1314,
+      "hfopenllm_v2/GPQA": 0.2701,
+      "hfopenllm_v2/MUSR": 0.3432,
+      "hfopenllm_v2/MMLU-PRO": 0.3354
     }
   },
   {
@@ -21040,12 +21040,12 @@
     "developer": "Etherll",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "hfopenllm_v2/IFEval": 0.6106,
-      "hfopenllm_v2/BBH": 0.5347,
-      "hfopenllm_v2/MATH Level 5": 0.1548,
-      "hfopenllm_v2/GPQA": 0.3146,
-      "hfopenllm_v2/MUSR": 0.3991,
-      "hfopenllm_v2/MMLU-PRO": 0.3752
+      "hfopenllm_v2/IFEval": 0.4672,
+      "hfopenllm_v2/BBH": 0.5013,
+      "hfopenllm_v2/MATH Level 5": 0.0279,
+      "hfopenllm_v2/GPQA": 0.2861,
+      "hfopenllm_v2/MUSR": 0.386,
+      "hfopenllm_v2/MMLU-PRO": 0.3482
     }
   },
   {
@@ -23289,12 +23289,12 @@
     "developer": "Goekdeniz-Guelmez",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "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
+      "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
     }
   },
   {
@@ -23303,12 +23303,12 @@
     "developer": "Goekdeniz-Guelmez",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "hfopenllm_v2/IFEval": 0.3417,
-      "hfopenllm_v2/BBH": 0.3292,
-      "hfopenllm_v2/MATH Level 5": 0.0023,
-      "hfopenllm_v2/GPQA": 0.2576,
-      "hfopenllm_v2/MUSR": 0.3249,
-      "hfopenllm_v2/MMLU-PRO": 0.1638
+      "hfopenllm_v2/IFEval": 0.3472,
+      "hfopenllm_v2/BBH": 0.3268,
+      "hfopenllm_v2/MATH Level 5": 0.0891,
+      "hfopenllm_v2/GPQA": 0.2517,
+      "hfopenllm_v2/MUSR": 0.3262,
+      "hfopenllm_v2/MMLU-PRO": 0.1641
     }
   },
   {
@@ -23537,6 +23537,8 @@
     "developer": "Google",
     "evaluator_relationship": null,
     "benchmark_scores": {
+      "ace/Overall Score": 0.47,
+      "ace/Gaming Score": 0.509,
       "apex-agents/Overall Pass@1": 0.184,
       "apex-agents/Overall Pass@8": 0.373,
       "apex-agents/Overall Mean Score": 0.341,
@@ -23544,8 +23546,6 @@
       "apex-agents/Management Consulting Pass@1": 0.124,
       "apex-agents/Corporate Law Pass@1": 0.239,
       "apex-agents/Corporate Lawyer Mean Score": 0.487,
-      "ace/Overall Score": 0.47,
-      "ace/Gaming Score": 0.509,
       "apex-v1/Overall Score": 0.643,
       "apex-v1/Consulting Score": 0.64,
       "apex-v1/Investment Banking Score": 0.63
@@ -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": 15.4
+      "terminal-bench-2.0/terminal-bench-2.0": 17.1
     }
   },
   {
@@ -24241,7 +24241,7 @@
     "developer": "Google",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "terminal-bench-2.0/terminal-bench-2.0": 51.0
+      "terminal-bench-2.0/terminal-bench-2.0": 64.3
     }
   },
   {
@@ -24250,7 +24250,7 @@
     "developer": "Google",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "terminal-bench-2.0/terminal-bench-2.0": 62.2
+      "terminal-bench-2.0/terminal-bench-2.0": 61.8
     }
   },
   {
@@ -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": 0.68,
-      "tau-bench-2_retail/tau-bench-2/retail": 0.82,
-      "tau-bench-2_telecom/tau-bench-2/telecom": 0.73
+      "tau-bench-2_airline/tau-bench-2/airline": 0.62,
+      "tau-bench-2_retail/tau-bench-2/retail": 0.73,
+      "tau-bench-2_telecom/tau-bench-2/telecom": 0.6852
     }
   },
   {
@@ -24292,7 +24292,7 @@
     "developer": "Google",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "terminal-bench-2.0/terminal-bench-2.0": 74.8
+      "terminal-bench-2.0/terminal-bench-2.0": 78.4
     }
   },
   {
@@ -24408,12 +24408,12 @@
     "developer": "Google",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "hfopenllm_v2/IFEval": 0.1993,
-      "hfopenllm_v2/BBH": 0.3656,
-      "hfopenllm_v2/MATH Level 5": 0.0287,
+      "hfopenllm_v2/IFEval": 0.2018,
+      "hfopenllm_v2/BBH": 0.3709,
+      "hfopenllm_v2/MATH Level 5": 0.0302,
       "hfopenllm_v2/GPQA": 0.2626,
-      "hfopenllm_v2/MUSR": 0.4232,
-      "hfopenllm_v2/MMLU-PRO": 0.218
+      "hfopenllm_v2/MUSR": 0.4219,
+      "hfopenllm_v2/MMLU-PRO": 0.2217
     }
   },
   {
@@ -25558,12 +25558,12 @@
     "developer": "Gunulhona",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "hfopenllm_v2/IFEval": 0.288,
-      "hfopenllm_v2/BBH": 0.5154,
+      "hfopenllm_v2/IFEval": 0.4441,
+      "hfopenllm_v2/BBH": 0.4863,
       "hfopenllm_v2/MATH Level 5": 0.0,
-      "hfopenllm_v2/GPQA": 0.3247,
-      "hfopenllm_v2/MUSR": 0.408,
-      "hfopenllm_v2/MMLU-PRO": 0.3817
+      "hfopenllm_v2/GPQA": 0.307,
+      "hfopenllm_v2/MUSR": 0.3986,
+      "hfopenllm_v2/MMLU-PRO": 0.3098
     }
   },
   {
@@ -26814,12 +26814,12 @@
     "developer": "HuggingFaceTB",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "hfopenllm_v2/IFEval": 0.083,
-      "hfopenllm_v2/BBH": 0.3053,
-      "hfopenllm_v2/MATH Level 5": 0.0083,
-      "hfopenllm_v2/GPQA": 0.2651,
-      "hfopenllm_v2/MUSR": 0.3423,
-      "hfopenllm_v2/MMLU-PRO": 0.1126
+      "hfopenllm_v2/IFEval": 0.3842,
+      "hfopenllm_v2/BBH": 0.3144,
+      "hfopenllm_v2/MATH Level 5": 0.0151,
+      "hfopenllm_v2/GPQA": 0.255,
+      "hfopenllm_v2/MUSR": 0.3461,
+      "hfopenllm_v2/MMLU-PRO": 0.1117
     }
   },
   {
@@ -28651,16 +28651,16 @@
     "developer": "internlm",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "reward-bench/Score": 0.8217,
+      "reward-bench/Score": 0.3902,
+      "reward-bench/Chat": 0.9358,
+      "reward-bench/Chat Hard": 0.6623,
+      "reward-bench/Safety": 0.4711,
+      "reward-bench/Reasoning": 0.8724,
       "reward-bench/Factuality": 0.2758,
       "reward-bench/Precise IF": 0.3625,
       "reward-bench/Math": 0.4426,
-      "reward-bench/Safety": 0.8162,
       "reward-bench/Focus": 0.596,
-      "reward-bench/Ties": 0.1934,
-      "reward-bench/Chat": 0.9358,
-      "reward-bench/Chat Hard": 0.6623,
-      "reward-bench/Reasoning": 0.8724
+      "reward-bench/Ties": 0.1934
     }
   },
   {
@@ -30623,12 +30623,12 @@
     "developer": "jaspionjader",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "hfopenllm_v2/IFEval": 0.4418,
-      "hfopenllm_v2/BBH": 0.5406,
-      "hfopenllm_v2/MATH Level 5": 0.1352,
-      "hfopenllm_v2/GPQA": 0.3062,
+      "hfopenllm_v2/IFEval": 0.4345,
+      "hfopenllm_v2/BBH": 0.5419,
+      "hfopenllm_v2/MATH Level 5": 0.1292,
+      "hfopenllm_v2/GPQA": 0.3087,
       "hfopenllm_v2/MUSR": 0.4277,
-      "hfopenllm_v2/MMLU-PRO": 0.386
+      "hfopenllm_v2/MMLU-PRO": 0.3854
     }
   },
   {
@@ -38012,12 +38012,12 @@
     "developer": "LeroyDyer",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "hfopenllm_v2/IFEval": 0.3579,
-      "hfopenllm_v2/BBH": 0.4477,
-      "hfopenllm_v2/MATH Level 5": 0.0423,
-      "hfopenllm_v2/GPQA": 0.3096,
-      "hfopenllm_v2/MUSR": 0.4134,
-      "hfopenllm_v2/MMLU-PRO": 0.2376
+      "hfopenllm_v2/IFEval": 0.3798,
+      "hfopenllm_v2/BBH": 0.4483,
+      "hfopenllm_v2/MATH Level 5": 0.04,
+      "hfopenllm_v2/GPQA": 0.3129,
+      "hfopenllm_v2/MUSR": 0.4148,
+      "hfopenllm_v2/MMLU-PRO": 0.2389
     }
   },
   {
@@ -38936,12 +38936,12 @@
     "developer": "llmat",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "hfopenllm_v2/IFEval": 0.364,
-      "hfopenllm_v2/BBH": 0.4005,
-      "hfopenllm_v2/MATH Level 5": 0.0015,
-      "hfopenllm_v2/GPQA": 0.2693,
-      "hfopenllm_v2/MUSR": 0.3529,
-      "hfopenllm_v2/MMLU-PRO": 0.2301
+      "hfopenllm_v2/IFEval": 0.377,
+      "hfopenllm_v2/BBH": 0.3978,
+      "hfopenllm_v2/MATH Level 5": 0.0242,
+      "hfopenllm_v2/GPQA": 0.2668,
+      "hfopenllm_v2/MUSR": 0.3555,
+      "hfopenllm_v2/MMLU-PRO": 0.2278
     }
   },
   {
@@ -39741,12 +39741,12 @@
     "developer": "Magpie-Align",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "hfopenllm_v2/IFEval": 0.4027,
-      "hfopenllm_v2/BBH": 0.4789,
-      "hfopenllm_v2/MATH Level 5": 0.0461,
-      "hfopenllm_v2/GPQA": 0.2768,
-      "hfopenllm_v2/MUSR": 0.3087,
-      "hfopenllm_v2/MMLU-PRO": 0.3001
+      "hfopenllm_v2/IFEval": 0.4118,
+      "hfopenllm_v2/BBH": 0.4811,
+      "hfopenllm_v2/MATH Level 5": 0.034,
+      "hfopenllm_v2/GPQA": 0.2752,
+      "hfopenllm_v2/MUSR": 0.3047,
+      "hfopenllm_v2/MMLU-PRO": 0.3006
     }
   },
   {
@@ -42056,12 +42056,12 @@
     "developer": "meta-llama",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "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,
+      "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,
       "reward-bench/Score": 0.645,
       "reward-bench/Chat": 0.8547,
       "reward-bench/Chat Hard": 0.4156,
@@ -43235,12 +43235,12 @@
     "developer": "microsoft",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "hfopenllm_v2/IFEval": 0.5477,
-      "hfopenllm_v2/BBH": 0.5491,
-      "hfopenllm_v2/MATH Level 5": 0.1639,
-      "hfopenllm_v2/GPQA": 0.3322,
-      "hfopenllm_v2/MUSR": 0.4284,
-      "hfopenllm_v2/MMLU-PRO": 0.4022
+      "hfopenllm_v2/IFEval": 0.5613,
+      "hfopenllm_v2/BBH": 0.5676,
+      "hfopenllm_v2/MATH Level 5": 0.1163,
+      "hfopenllm_v2/GPQA": 0.3196,
+      "hfopenllm_v2/MUSR": 0.395,
+      "hfopenllm_v2/MMLU-PRO": 0.3866
     }
   },
   {
@@ -43667,7 +43667,7 @@
     "developer": "MiniMax",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "terminal-bench-2.0/terminal-bench-2.0": 29.2
+      "terminal-bench-2.0/terminal-bench-2.0": 36.6
     }
   },
   {
@@ -44996,7 +44996,7 @@
     "developer": "Moonshot AI",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "terminal-bench-2.0/terminal-bench-2.0": 27.8
+      "terminal-bench-2.0/terminal-bench-2.0": 26.7
     }
   },
   {
@@ -45633,12 +45633,12 @@
     "developer": "nazimali",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "hfopenllm_v2/IFEval": 0.4964,
-      "hfopenllm_v2/BBH": 0.4699,
-      "hfopenllm_v2/MATH Level 5": 0.0045,
-      "hfopenllm_v2/GPQA": 0.2827,
-      "hfopenllm_v2/MUSR": 0.3979,
-      "hfopenllm_v2/MMLU-PRO": 0.3063
+      "hfopenllm_v2/IFEval": 0.486,
+      "hfopenllm_v2/BBH": 0.4721,
+      "hfopenllm_v2/MATH Level 5": 0.0846,
+      "hfopenllm_v2/GPQA": 0.2844,
+      "hfopenllm_v2/MUSR": 0.4006,
+      "hfopenllm_v2/MMLU-PRO": 0.3087
     }
   },
   {
@@ -48273,16 +48273,16 @@
     "developer": "nicolinho",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "reward-bench/Score": 0.9444,
+      "reward-bench/Score": 0.7667,
+      "reward-bench/Chat": 0.9665,
+      "reward-bench/Chat Hard": 0.9013,
+      "reward-bench/Safety": 0.9578,
+      "reward-bench/Reasoning": 0.9826,
       "reward-bench/Factuality": 0.7853,
       "reward-bench/Precise IF": 0.3719,
       "reward-bench/Math": 0.6995,
-      "reward-bench/Safety": 0.927,
       "reward-bench/Focus": 0.9535,
-      "reward-bench/Ties": 0.8321,
-      "reward-bench/Chat": 0.9665,
-      "reward-bench/Chat Hard": 0.9013,
-      "reward-bench/Reasoning": 0.9826
+      "reward-bench/Ties": 0.8321
     }
   },
   {
@@ -50085,12 +50085,12 @@
     "developer": "Omkar1102",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "hfopenllm_v2/IFEval": 0.2148,
-      "hfopenllm_v2/BBH": 0.276,
+      "hfopenllm_v2/IFEval": 0.2254,
+      "hfopenllm_v2/BBH": 0.275,
       "hfopenllm_v2/MATH Level 5": 0.0,
-      "hfopenllm_v2/GPQA": 0.2508,
-      "hfopenllm_v2/MUSR": 0.3802,
-      "hfopenllm_v2/MMLU-PRO": 0.1126
+      "hfopenllm_v2/GPQA": 0.2576,
+      "hfopenllm_v2/MUSR": 0.3762,
+      "hfopenllm_v2/MMLU-PRO": 0.1123
     }
   },
   {
@@ -50393,12 +50393,12 @@
     "developer": "ontocord",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "hfopenllm_v2/IFEval": 0.1128,
-      "hfopenllm_v2/BBH": 0.3171,
-      "hfopenllm_v2/MATH Level 5": 0.0113,
-      "hfopenllm_v2/GPQA": 0.2685,
-      "hfopenllm_v2/MUSR": 0.346,
-      "hfopenllm_v2/MMLU-PRO": 0.1129
+      "hfopenllm_v2/IFEval": 0.1162,
+      "hfopenllm_v2/BBH": 0.3184,
+      "hfopenllm_v2/MATH Level 5": 0.0076,
+      "hfopenllm_v2/GPQA": 0.2634,
+      "hfopenllm_v2/MUSR": 0.3447,
+      "hfopenllm_v2/MMLU-PRO": 0.1124
     }
   },
   {
@@ -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": 0.5796,
-      "reward-bench/Chat": 0.9497,
-      "reward-bench/Chat Hard": 0.6075,
-      "reward-bench/Safety": 0.7667,
-      "reward-bench/Reasoning": 0.8374,
+      "reward-bench/Score": 0.8007,
       "reward-bench/Factuality": 0.4105,
       "reward-bench/Precise IF": 0.3438,
       "reward-bench/Math": 0.5191,
+      "reward-bench/Safety": 0.8081,
       "reward-bench/Focus": 0.7414,
-      "reward-bench/Ties": 0.6962
+      "reward-bench/Ties": 0.6962,
+      "reward-bench/Chat": 0.9497,
+      "reward-bench/Chat Hard": 0.6075,
+      "reward-bench/Reasoning": 0.8374
     }
   },
   {
@@ -51725,7 +51725,7 @@
     "developer": "OpenAI",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "terminal-bench-2.0/terminal-bench-2.0": 49.6
+      "terminal-bench-2.0/terminal-bench-2.0": 35.2
     }
   },
   {
@@ -51770,7 +51770,7 @@
     "developer": "OpenAI",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "terminal-bench-2.0/terminal-bench-2.0": 43.4
+      "terminal-bench-2.0/terminal-bench-2.0": 44.3
     }
   },
   {
@@ -51779,7 +51779,7 @@
     "developer": "OpenAI",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "terminal-bench-2.0/terminal-bench-2.0": 34.8
+      "terminal-bench-2.0/terminal-bench-2.0": 24.0
     }
   },
   {
@@ -51802,7 +51802,7 @@
     "developer": "OpenAI",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "terminal-bench-2.0/terminal-bench-2.0": 7.0
+      "terminal-bench-2.0/terminal-bench-2.0": 7.9
     }
   },
   {
@@ -51861,7 +51861,7 @@
     "developer": "OpenAI",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "terminal-bench-2.0/terminal-bench-2.0": 60.7
+      "terminal-bench-2.0/terminal-bench-2.0": 54.0
     }
   },
   {
@@ -51870,15 +51870,15 @@
     "developer": "OpenAI",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "appworld_test_normal/appworld/test_normal": 0.071,
-      "browsecompplus/browsecompplus": 0.46,
+      "appworld_test_normal/appworld/test_normal": 0.0,
+      "browsecompplus/browsecompplus": 0.43,
       "livecodebenchpro/Hard Problems": 0.1594,
       "livecodebenchpro/Medium Problems": 0.5211,
       "livecodebenchpro/Easy Problems": 0.9014,
-      "swe-bench/swe-bench": 0.57,
+      "swe-bench/swe-bench": 0.5455,
       "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
+      "tau-bench-2_telecom/tau-bench-2/telecom": 0.5354
     }
   },
   {
@@ -52081,9 +52081,9 @@
       "helm_capabilities/IFEval": 0.929,
       "helm_capabilities/WildBench": 0.854,
       "helm_capabilities/Omni-MATH": 0.72,
-      "livecodebenchpro/Hard Problems": 0.014084507042253521,
-      "livecodebenchpro/Medium Problems": 0.30985915492957744,
-      "livecodebenchpro/Easy Problems": 0.8873239436619719
+      "livecodebenchpro/Hard Problems": 0.0143,
+      "livecodebenchpro/Medium Problems": 0.2923,
+      "livecodebenchpro/Easy Problems": 0.8571
     }
   },
   {
@@ -52312,17 +52312,17 @@
     "developer": "openbmb",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "reward-bench/Score": 0.8159,
+      "reward-bench/Score": 0.5806,
+      "reward-bench/Chat": 0.9804,
+      "reward-bench/Chat Hard": 0.6557,
+      "reward-bench/Safety": 0.6267,
+      "reward-bench/Reasoning": 0.8633,
+      "reward-bench/Prior Sets (0.5 weight)": 0.7172,
       "reward-bench/Factuality": 0.6,
       "reward-bench/Precise IF": 0.3438,
       "reward-bench/Math": 0.5683,
-      "reward-bench/Safety": 0.8135,
       "reward-bench/Focus": 0.7475,
-      "reward-bench/Ties": 0.5972,
-      "reward-bench/Chat": 0.9804,
-      "reward-bench/Chat Hard": 0.6557,
-      "reward-bench/Reasoning": 0.8633,
-      "reward-bench/Prior Sets (0.5 weight)": 0.7172
+      "reward-bench/Ties": 0.5972
     }
   },
   {
@@ -52359,17 +52359,17 @@
     "developer": "openbmb",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "reward-bench/Score": 0.4683,
-      "reward-bench/Chat": 0.9637,
-      "reward-bench/Chat Hard": 0.5548,
-      "reward-bench/Safety": 0.5089,
-      "reward-bench/Reasoning": 0.6244,
-      "reward-bench/Prior Sets (0.5 weight)": 0.7294,
+      "reward-bench/Score": 0.6903,
       "reward-bench/Factuality": 0.5063,
       "reward-bench/Precise IF": 0.3312,
       "reward-bench/Math": 0.5519,
+      "reward-bench/Safety": 0.5986,
       "reward-bench/Focus": 0.6081,
-      "reward-bench/Ties": 0.3036
+      "reward-bench/Ties": 0.3036,
+      "reward-bench/Chat": 0.9637,
+      "reward-bench/Chat Hard": 0.5548,
+      "reward-bench/Reasoning": 0.6244,
+      "reward-bench/Prior Sets (0.5 weight)": 0.7294
     }
   },
   {
@@ -53830,17 +53830,17 @@
     "developer": "PKU-Alignment",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "reward-bench/Score": 0.5798,
+      "reward-bench/Score": 0.3332,
+      "reward-bench/Chat": 0.6173,
+      "reward-bench/Chat Hard": 0.4232,
+      "reward-bench/Safety": 0.7589,
+      "reward-bench/Reasoning": 0.5482,
+      "reward-bench/Prior Sets (0.5 weight)": 0.57,
       "reward-bench/Factuality": 0.3263,
       "reward-bench/Precise IF": 0.2313,
       "reward-bench/Math": 0.3989,
-      "reward-bench/Safety": 0.7351,
       "reward-bench/Focus": 0.2939,
-      "reward-bench/Ties": -0.01,
-      "reward-bench/Chat": 0.6173,
-      "reward-bench/Chat Hard": 0.4232,
-      "reward-bench/Reasoning": 0.5482,
-      "reward-bench/Prior Sets (0.5 weight)": 0.57
+      "reward-bench/Ties": -0.01
     }
   },
   {
@@ -54172,11 +54172,11 @@
     "evaluator_relationship": null,
     "benchmark_scores": {
       "hfopenllm_v2/IFEval": 0.1757,
-      "hfopenllm_v2/BBH": 0.274,
+      "hfopenllm_v2/BBH": 0.276,
       "hfopenllm_v2/MATH Level 5": 0.0,
-      "hfopenllm_v2/GPQA": 0.25,
-      "hfopenllm_v2/MUSR": 0.3753,
-      "hfopenllm_v2/MMLU-PRO": 0.112
+      "hfopenllm_v2/GPQA": 0.2534,
+      "hfopenllm_v2/MUSR": 0.3339,
+      "hfopenllm_v2/MMLU-PRO": 0.1123
     }
   },
   {
@@ -56591,12 +56591,12 @@
     "developer": "qingy2019",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "hfopenllm_v2/IFEval": 0.2358,
-      "hfopenllm_v2/BBH": 0.4612,
-      "hfopenllm_v2/MATH Level 5": 0.0642,
-      "hfopenllm_v2/GPQA": 0.2576,
-      "hfopenllm_v2/MUSR": 0.3717,
-      "hfopenllm_v2/MMLU-PRO": 0.2382
+      "hfopenllm_v2/IFEval": 0.2401,
+      "hfopenllm_v2/BBH": 0.4622,
+      "hfopenllm_v2/MATH Level 5": 0.0725,
+      "hfopenllm_v2/GPQA": 0.2609,
+      "hfopenllm_v2/MUSR": 0.3703,
+      "hfopenllm_v2/MMLU-PRO": 0.2379
     }
   },
   {
@@ -56605,12 +56605,12 @@
     "developer": "qingy2019",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "hfopenllm_v2/IFEval": 0.6066,
-      "hfopenllm_v2/BBH": 0.635,
-      "hfopenllm_v2/MATH Level 5": 0.3716,
-      "hfopenllm_v2/GPQA": 0.3725,
+      "hfopenllm_v2/IFEval": 0.6005,
+      "hfopenllm_v2/BBH": 0.6356,
+      "hfopenllm_v2/MATH Level 5": 0.2764,
+      "hfopenllm_v2/GPQA": 0.3691,
       "hfopenllm_v2/MUSR": 0.4757,
-      "hfopenllm_v2/MMLU-PRO": 0.5331
+      "hfopenllm_v2/MMLU-PRO": 0.5339
     }
   },
   {
@@ -59400,17 +59400,17 @@
     "developer": "Ray2333",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "reward-bench/Score": 0.589,
-      "reward-bench/Chat": 0.9832,
-      "reward-bench/Chat Hard": 0.6842,
-      "reward-bench/Safety": 0.7222,
-      "reward-bench/Reasoning": 0.9133,
-      "reward-bench/Prior Sets (0.5 weight)": 0.7209,
+      "reward-bench/Score": 0.8464,
       "reward-bench/Factuality": 0.5874,
       "reward-bench/Precise IF": 0.3875,
       "reward-bench/Math": 0.5902,
+      "reward-bench/Safety": 0.8676,
       "reward-bench/Focus": 0.6727,
-      "reward-bench/Ties": 0.5743
+      "reward-bench/Ties": 0.5743,
+      "reward-bench/Chat": 0.9832,
+      "reward-bench/Chat Hard": 0.6842,
+      "reward-bench/Reasoning": 0.9133,
+      "reward-bench/Prior Sets (0.5 weight)": 0.7209
     }
   },
   {
@@ -59721,12 +59721,12 @@
     "developer": "Replete-AI",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "hfopenllm_v2/IFEval": 0.0905,
-      "hfopenllm_v2/BBH": 0.2985,
+      "hfopenllm_v2/IFEval": 0.0932,
+      "hfopenllm_v2/BBH": 0.2977,
       "hfopenllm_v2/MATH Level 5": 0.0,
-      "hfopenllm_v2/GPQA": 0.2534,
-      "hfopenllm_v2/MUSR": 0.3848,
-      "hfopenllm_v2/MMLU-PRO": 0.1158
+      "hfopenllm_v2/GPQA": 0.2475,
+      "hfopenllm_v2/MUSR": 0.3941,
+      "hfopenllm_v2/MMLU-PRO": 0.1157
     }
   },
   {
@@ -59861,12 +59861,12 @@
     "developer": "riaz",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "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
+      "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
     }
   },
   {
@@ -61835,12 +61835,12 @@
     "developer": "Sao10K",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "hfopenllm_v2/IFEval": 0.7384,
-      "hfopenllm_v2/BBH": 0.6471,
-      "hfopenllm_v2/MATH Level 5": 0.2137,
+      "hfopenllm_v2/IFEval": 0.7281,
+      "hfopenllm_v2/BBH": 0.6503,
+      "hfopenllm_v2/MATH Level 5": 0.2243,
       "hfopenllm_v2/GPQA": 0.3314,
-      "hfopenllm_v2/MUSR": 0.4209,
-      "hfopenllm_v2/MMLU-PRO": 0.5104
+      "hfopenllm_v2/MUSR": 0.4196,
+      "hfopenllm_v2/MMLU-PRO": 0.5096
     }
   },
   {
@@ -62492,17 +62492,17 @@
     "developer": "sfairXC",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "reward-bench/Score": 0.8338,
+      "reward-bench/Score": 0.6292,
+      "reward-bench/Chat": 0.9944,
+      "reward-bench/Chat Hard": 0.6513,
+      "reward-bench/Safety": 0.7667,
+      "reward-bench/Reasoning": 0.8644,
+      "reward-bench/Prior Sets (0.5 weight)": 0.7492,
       "reward-bench/Factuality": 0.5916,
       "reward-bench/Precise IF": 0.4188,
       "reward-bench/Math": 0.6284,
-      "reward-bench/Safety": 0.8676,
       "reward-bench/Focus": 0.7051,
-      "reward-bench/Ties": 0.6647,
-      "reward-bench/Chat": 0.9944,
-      "reward-bench/Chat Hard": 0.6513,
-      "reward-bench/Reasoning": 0.8644,
-      "reward-bench/Prior Sets (0.5 weight)": 0.7492
+      "reward-bench/Ties": 0.6647
     }
   },
   {
@@ -63283,16 +63283,16 @@
     "developer": "Skywork",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "reward-bench/Score": 0.938,
+      "reward-bench/Score": 0.7576,
+      "reward-bench/Chat": 0.9581,
+      "reward-bench/Chat Hard": 0.9145,
+      "reward-bench/Safety": 0.9422,
+      "reward-bench/Reasoning": 0.9606,
       "reward-bench/Factuality": 0.7368,
       "reward-bench/Precise IF": 0.4031,
       "reward-bench/Math": 0.7049,
-      "reward-bench/Safety": 0.9189,
       "reward-bench/Focus": 0.9323,
-      "reward-bench/Ties": 0.8261,
-      "reward-bench/Chat": 0.9581,
-      "reward-bench/Chat Hard": 0.9145,
-      "reward-bench/Reasoning": 0.9606
+      "reward-bench/Ties": 0.8261
     }
   },
   {
@@ -63325,16 +63325,16 @@
     "developer": "Skywork",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "reward-bench/Score": 0.7314,
-      "reward-bench/Chat": 0.9581,
-      "reward-bench/Chat Hard": 0.8728,
-      "reward-bench/Safety": 0.9333,
-      "reward-bench/Reasoning": 0.962,
+      "reward-bench/Score": 0.9252,
       "reward-bench/Factuality": 0.6989,
       "reward-bench/Precise IF": 0.425,
       "reward-bench/Math": 0.6284,
+      "reward-bench/Safety": 0.9081,
       "reward-bench/Focus": 0.9616,
-      "reward-bench/Ties": 0.741
+      "reward-bench/Ties": 0.741,
+      "reward-bench/Chat": 0.9581,
+      "reward-bench/Chat Hard": 0.8728,
+      "reward-bench/Reasoning": 0.962
     }
   },
   {
@@ -63466,16 +63466,16 @@
     "developer": "Skywork",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "reward-bench/Score": 0.9007,
+      "reward-bench/Score": 0.6885,
+      "reward-bench/Chat": 0.8994,
+      "reward-bench/Chat Hard": 0.875,
+      "reward-bench/Safety": 0.8911,
+      "reward-bench/Reasoning": 0.9176,
       "reward-bench/Factuality": 0.6063,
       "reward-bench/Precise IF": 0.35,
       "reward-bench/Math": 0.6339,
-      "reward-bench/Safety": 0.9108,
       "reward-bench/Focus": 0.8909,
-      "reward-bench/Ties": 0.7586,
-      "reward-bench/Chat": 0.8994,
-      "reward-bench/Chat Hard": 0.875,
-      "reward-bench/Reasoning": 0.9176
+      "reward-bench/Ties": 0.7586
     }
   },
   {
@@ -64322,12 +64322,12 @@
     "developer": "sometimesanotion",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "hfopenllm_v2/IFEval": 0.5278,
-      "hfopenllm_v2/BBH": 0.6557,
-      "hfopenllm_v2/MATH Level 5": 0.3119,
-      "hfopenllm_v2/GPQA": 0.3842,
-      "hfopenllm_v2/MUSR": 0.4754,
-      "hfopenllm_v2/MMLU-PRO": 0.5396
+      "hfopenllm_v2/IFEval": 0.5367,
+      "hfopenllm_v2/BBH": 0.6561,
+      "hfopenllm_v2/MATH Level 5": 0.358,
+      "hfopenllm_v2/GPQA": 0.3867,
+      "hfopenllm_v2/MUSR": 0.474,
+      "hfopenllm_v2/MMLU-PRO": 0.5395
     }
   },
   {
@@ -64728,12 +64728,12 @@
     "developer": "spow12",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "hfopenllm_v2/IFEval": 0.6511,
-      "hfopenllm_v2/BBH": 0.5926,
-      "hfopenllm_v2/MATH Level 5": 0.1858,
-      "hfopenllm_v2/GPQA": 0.3247,
+      "hfopenllm_v2/IFEval": 0.6517,
+      "hfopenllm_v2/BBH": 0.5908,
+      "hfopenllm_v2/MATH Level 5": 0.2032,
+      "hfopenllm_v2/GPQA": 0.3238,
       "hfopenllm_v2/MUSR": 0.3842,
-      "hfopenllm_v2/MMLU-PRO": 0.3836
+      "hfopenllm_v2/MMLU-PRO": 0.3812
     }
   },
   {
@@ -66784,12 +66784,12 @@
     "developer": "tanliboy",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "hfopenllm_v2/IFEval": 0.1829,
-      "hfopenllm_v2/BBH": 0.5488,
-      "hfopenllm_v2/MATH Level 5": 0.0,
-      "hfopenllm_v2/GPQA": 0.3104,
-      "hfopenllm_v2/MUSR": 0.4056,
-      "hfopenllm_v2/MMLU-PRO": 0.3805
+      "hfopenllm_v2/IFEval": 0.4501,
+      "hfopenllm_v2/BBH": 0.5472,
+      "hfopenllm_v2/MATH Level 5": 0.0944,
+      "hfopenllm_v2/GPQA": 0.3138,
+      "hfopenllm_v2/MUSR": 0.4017,
+      "hfopenllm_v2/MMLU-PRO": 0.3792
     }
   },
   {
@@ -71000,12 +71000,12 @@
     "developer": "ValiantLabs",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "hfopenllm_v2/IFEval": 0.7168,
-      "hfopenllm_v2/BBH": 0.4911,
-      "hfopenllm_v2/MATH Level 5": 0.1533,
-      "hfopenllm_v2/GPQA": 0.2861,
-      "hfopenllm_v2/MUSR": 0.3512,
-      "hfopenllm_v2/MMLU-PRO": 0.3663
+      "hfopenllm_v2/IFEval": 0.3496,
+      "hfopenllm_v2/BBH": 0.4947,
+      "hfopenllm_v2/MATH Level 5": 0.1269,
+      "hfopenllm_v2/GPQA": 0.3037,
+      "hfopenllm_v2/MUSR": 0.3959,
+      "hfopenllm_v2/MMLU-PRO": 0.3644
     }
   },
   {
@@ -71056,12 +71056,12 @@
     "developer": "ValiantLabs",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "hfopenllm_v2/IFEval": 0.2678,
-      "hfopenllm_v2/BBH": 0.4429,
-      "hfopenllm_v2/MATH Level 5": 0.0521,
-      "hfopenllm_v2/GPQA": 0.302,
-      "hfopenllm_v2/MUSR": 0.3959,
-      "hfopenllm_v2/MMLU-PRO": 0.2927
+      "hfopenllm_v2/IFEval": 0.6496,
+      "hfopenllm_v2/BBH": 0.4774,
+      "hfopenllm_v2/MATH Level 5": 0.0566,
+      "hfopenllm_v2/GPQA": 0.3104,
+      "hfopenllm_v2/MUSR": 0.3909,
+      "hfopenllm_v2/MMLU-PRO": 0.3382
     }
   },
   {
@@ -71686,17 +71686,17 @@
     "developer": "weqweasdas",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "reward-bench/Score": 0.5027,
+      "reward-bench/Score": 0.2498,
+      "reward-bench/Chat": 0.8184,
+      "reward-bench/Chat Hard": 0.3728,
+      "reward-bench/Safety": 0.24,
+      "reward-bench/Reasoning": 0.3281,
+      "reward-bench/Prior Sets (0.5 weight)": 0.6564,
       "reward-bench/Factuality": 0.3642,
       "reward-bench/Precise IF": 0.275,
       "reward-bench/Math": 0.3497,
-      "reward-bench/Safety": 0.4149,
       "reward-bench/Focus": 0.2384,
-      "reward-bench/Ties": 0.0315,
-      "reward-bench/Chat": 0.8184,
-      "reward-bench/Chat Hard": 0.3728,
-      "reward-bench/Reasoning": 0.3281,
-      "reward-bench/Prior Sets (0.5 weight)": 0.6564
+      "reward-bench/Ties": 0.0315
     }
   },
   {
@@ -71705,17 +71705,17 @@
     "developer": "weqweasdas",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "reward-bench/Score": 0.3057,
-      "reward-bench/Chat": 0.9441,
-      "reward-bench/Chat Hard": 0.4079,
-      "reward-bench/Safety": 0.3311,
-      "reward-bench/Reasoning": 0.7637,
-      "reward-bench/Prior Sets (0.5 weight)": 0.6652,
+      "reward-bench/Score": 0.6549,
       "reward-bench/Factuality": 0.3705,
       "reward-bench/Precise IF": 0.2812,
       "reward-bench/Math": 0.4317,
+      "reward-bench/Safety": 0.4986,
       "reward-bench/Focus": 0.2343,
-      "reward-bench/Ties": 0.1851
+      "reward-bench/Ties": 0.1851,
+      "reward-bench/Chat": 0.9441,
+      "reward-bench/Chat Hard": 0.4079,
+      "reward-bench/Reasoning": 0.7637,
+      "reward-bench/Prior Sets (0.5 weight)": 0.6652
     }
   },
   {
@@ -71757,17 +71757,17 @@
     "developer": "weqweasdas",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "reward-bench/Score": 0.596,
-      "reward-bench/Chat": 0.9665,
-      "reward-bench/Chat Hard": 0.6053,
-      "reward-bench/Safety": 0.6911,
-      "reward-bench/Reasoning": 0.7736,
-      "reward-bench/Prior Sets (0.5 weight)": 0.753,
+      "reward-bench/Score": 0.7982,
       "reward-bench/Factuality": 0.5937,
       "reward-bench/Precise IF": 0.3438,
       "reward-bench/Math": 0.5956,
+      "reward-bench/Safety": 0.8703,
       "reward-bench/Focus": 0.7293,
-      "reward-bench/Ties": 0.6226
+      "reward-bench/Ties": 0.6226,
+      "reward-bench/Chat": 0.9665,
+      "reward-bench/Chat Hard": 0.6053,
+      "reward-bench/Reasoning": 0.7736,
+      "reward-bench/Prior Sets (0.5 weight)": 0.753
     }
   },
   {
@@ -72436,7 +72436,7 @@
     "developer": "xAI",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "terminal-bench-2.0/terminal-bench-2.0": 25.8
+      "terminal-bench-2.0/terminal-bench-2.0": 14.2
     }
   },
   {
@@ -73140,12 +73140,12 @@
     "developer": "ycros",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "hfopenllm_v2/IFEval": 0.6262,
-      "hfopenllm_v2/BBH": 0.5142,
-      "hfopenllm_v2/MATH Level 5": 0.0937,
-      "hfopenllm_v2/GPQA": 0.3079,
-      "hfopenllm_v2/MUSR": 0.4138,
-      "hfopenllm_v2/MMLU-PRO": 0.3481
+      "hfopenllm_v2/IFEval": 0.5994,
+      "hfopenllm_v2/BBH": 0.5159,
+      "hfopenllm_v2/MATH Level 5": 0.0785,
+      "hfopenllm_v2/GPQA": 0.3045,
+      "hfopenllm_v2/MUSR": 0.4203,
+      "hfopenllm_v2/MMLU-PRO": 0.3473
     }
   },
   {
@@ -73826,12 +73826,12 @@
     "developer": "YOYO-AI",
     "evaluator_relationship": null,
     "benchmark_scores": {
-      "hfopenllm_v2/IFEval": 0.7905,
-      "hfopenllm_v2/BBH": 0.6406,
-      "hfopenllm_v2/MATH Level 5": 0.0,
-      "hfopenllm_v2/GPQA": 0.3163,
-      "hfopenllm_v2/MUSR": 0.4181,
-      "hfopenllm_v2/MMLU-PRO": 0.4944
+      "hfopenllm_v2/IFEval": 0.5899,
+      "hfopenllm_v2/BBH": 0.654,
+      "hfopenllm_v2/MATH Level 5": 0.4509,
+      "hfopenllm_v2/GPQA": 0.3834,
+      "hfopenllm_v2/MUSR": 0.4744,
+      "hfopenllm_v2/MMLU-PRO": 0.5376
     }
   },
   {
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 e9d556b28d7550c1e76a8e996c98b852c7622823..036d2144a17c2773cc45b3fcdc429ec4c85d29b1 100644
--- a/data/models/ai2_tulu-2-7b-rm-v0-nectar-binarized-3.8m-check....json
+++ b/data/models/ai2_tulu-2-7b-rm-v0-nectar-binarized-3.8m-check....json
@@ -38,7 +38,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6905
+            "score": 0.7058
           },
           "source_data": {
             "dataset_name": "RewardBench",
@@ -56,7 +56,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9441
+            "score": 0.9525
           },
           "source_data": {
             "dataset_name": "RewardBench",
@@ -74,7 +74,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3596
+            "score": 0.3947
           },
           "source_data": {
             "dataset_name": "RewardBench",
@@ -92,7 +92,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7676
+            "score": 0.7703
           },
           "source_data": {
             "dataset_name": "RewardBench",
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6808
+            "score": 0.6905
           },
           "source_data": {
             "dataset_name": "RewardBench",
@@ -152,7 +152,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9302
+            "score": 0.9441
           },
           "source_data": {
             "dataset_name": "RewardBench",
@@ -188,7 +188,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7527
+            "score": 0.7676
           },
           "source_data": {
             "dataset_name": "RewardBench",
@@ -230,7 +230,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6895
+            "score": 0.7004
           },
           "source_data": {
             "dataset_name": "RewardBench",
@@ -248,7 +248,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9385
+            "score": 0.9413
           },
           "source_data": {
             "dataset_name": "RewardBench",
@@ -266,7 +266,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3706
+            "score": 0.3882
           },
           "source_data": {
             "dataset_name": "RewardBench",
@@ -284,7 +284,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7595
+            "score": 0.7716
           },
           "source_data": {
             "dataset_name": "RewardBench",
@@ -326,7 +326,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7004
+            "score": 0.6945
           },
           "source_data": {
             "dataset_name": "RewardBench",
@@ -344,7 +344,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9413
+            "score": 0.9385
           },
           "source_data": {
             "dataset_name": "RewardBench",
@@ -362,7 +362,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3882
+            "score": 0.3706
           },
           "source_data": {
             "dataset_name": "RewardBench",
@@ -380,7 +380,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7716
+            "score": 0.7743
           },
           "source_data": {
             "dataset_name": "RewardBench",
@@ -422,7 +422,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7019
+            "score": 0.6808
           },
           "source_data": {
             "dataset_name": "RewardBench",
@@ -440,7 +440,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9497
+            "score": 0.9302
           },
           "source_data": {
             "dataset_name": "RewardBench",
@@ -458,7 +458,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.375
+            "score": 0.3596
           },
           "source_data": {
             "dataset_name": "RewardBench",
@@ -476,7 +476,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7811
+            "score": 0.7527
           },
           "source_data": {
             "dataset_name": "RewardBench",
@@ -518,7 +518,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7058
+            "score": 0.7008
           },
           "source_data": {
             "dataset_name": "RewardBench",
@@ -536,7 +536,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9525
+            "score": 0.9385
           },
           "source_data": {
             "dataset_name": "RewardBench",
@@ -554,7 +554,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3947
+            "score": 0.3882
           },
           "source_data": {
             "dataset_name": "RewardBench",
@@ -572,7 +572,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7703
+            "score": 0.7757
           },
           "source_data": {
             "dataset_name": "RewardBench",
@@ -614,7 +614,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7008
+            "score": 0.7019
           },
           "source_data": {
             "dataset_name": "RewardBench",
@@ -632,7 +632,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9385
+            "score": 0.9497
           },
           "source_data": {
             "dataset_name": "RewardBench",
@@ -650,7 +650,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3882
+            "score": 0.375
           },
           "source_data": {
             "dataset_name": "RewardBench",
@@ -668,7 +668,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7757
+            "score": 0.7811
           },
           "source_data": {
             "dataset_name": "RewardBench",
@@ -710,7 +710,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6945
+            "score": 0.6924
           },
           "source_data": {
             "dataset_name": "RewardBench",
@@ -728,7 +728,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9385
+            "score": 0.9441
           },
           "source_data": {
             "dataset_name": "RewardBench",
@@ -746,7 +746,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3706
+            "score": 0.3575
           },
           "source_data": {
             "dataset_name": "RewardBench",
@@ -764,7 +764,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7743
+            "score": 0.7757
           },
           "source_data": {
             "dataset_name": "RewardBench",
@@ -806,7 +806,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6924
+            "score": 0.6895
           },
           "source_data": {
             "dataset_name": "RewardBench",
@@ -824,7 +824,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9441
+            "score": 0.9385
           },
           "source_data": {
             "dataset_name": "RewardBench",
@@ -842,7 +842,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3575
+            "score": 0.3706
           },
           "source_data": {
             "dataset_name": "RewardBench",
@@ -860,7 +860,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7757
+            "score": 0.7595
           },
           "source_data": {
             "dataset_name": "RewardBench",
diff --git a/data/models/akjindal53244_llama-3.1-storm-8b.json b/data/models/akjindal53244_llama-3.1-storm-8b.json
index 10080988b150f205c06f956e608326efa2dd3fb0..cd06cbbbbe2ccc306c529154ea621a16fb9ebcf6 100644
--- a/data/models/akjindal53244_llama-3.1-storm-8b.json
+++ b/data/models/akjindal53244_llama-3.1-storm-8b.json
@@ -5,7 +5,7 @@
     "developer": "akjindal53244",
     "inference_platform": "unknown",
     "additional_details": {
-      "precision": "bfloat16",
+      "precision": "float16",
       "architecture": "LlamaForCausalLM",
       "params_billions": "8.03"
     }
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.8033
+            "score": 0.8051
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5196
+            "score": 0.5189
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1624
+            "score": 0.1722
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3096
+            "score": 0.3263
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3812
+            "score": 0.3803
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.8051
+            "score": 0.8033
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5189
+            "score": 0.5196
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1722
+            "score": 0.1624
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3263
+            "score": 0.3096
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3803
+            "score": 0.3812
           }
         }
       ],
diff --git a/data/models/alibaba_qwen-3-coder-480b.json b/data/models/alibaba_qwen-3-coder-480b.json
index 78f6ba994c4cff4ccaf572ddc5297bedb19efb9b..76736ecf57c8a847549ed4d201c4f8542bcb4b8e 100644
--- a/data/models/alibaba_qwen-3-coder-480b.json
+++ b/data/models/alibaba_qwen-3-coder-480b.json
@@ -4,13 +4,13 @@
     "id": "alibaba/qwen-3-coder-480b",
     "developer": "Alibaba",
     "additional_details": {
-      "agent_name": "Dakou Agent",
-      "agent_organization": "iflow"
+      "agent_name": "Terminus 2",
+      "agent_organization": "Terminal Bench"
     }
   },
   "evaluations": [
     {
-      "evaluation_id": "terminal-bench-2.0/dakou-agent__qwen-3-coder-480b/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/terminus-2__qwen-3-coder-480b/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -34,7 +34,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-12-28",
+          "evaluation_timestamp": "2025-11-01",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -43,17 +43,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 27.2,
+            "score": 23.9,
             "uncertainty": {
               "standard_error": {
-                "value": 2.6
+                "value": 2.8
               },
               "num_samples": 435
             }
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Dakou Agent\" -m \"Qwen 3 Coder 480B\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"Qwen 3 Coder 480B\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -70,7 +70,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Dakou Agent\" -m \"Qwen 3 Coder 480B\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"Qwen 3 Coder 480B\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -158,7 +158,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/terminus-2__qwen-3-coder-480b/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/dakou-agent__qwen-3-coder-480b/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -182,7 +182,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-11-01",
+          "evaluation_timestamp": "2025-12-28",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -191,17 +191,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 23.9,
+            "score": 27.2,
             "uncertainty": {
               "standard_error": {
-                "value": 2.8
+                "value": 2.6
               },
               "num_samples": 435
             }
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"Qwen 3 Coder 480B\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Dakou Agent\" -m \"Qwen 3 Coder 480B\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -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 \"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": [
               {
diff --git a/data/models/allenai_llama-3.1-tulu-3-70b-sft-rm-rb2.json b/data/models/allenai_llama-3.1-tulu-3-70b-sft-rm-rb2.json
index 3c470e6abd70f5f2bc9a8be57cc36f939ca7753c..56c7eedcfadd2447274047e1824ef99e14cf4e28 100644
--- a/data/models/allenai_llama-3.1-tulu-3-70b-sft-rm-rb2.json
+++ b/data/models/allenai_llama-3.1-tulu-3-70b-sft-rm-rb2.json
@@ -9,10 +9,10 @@
   },
   "evaluations": [
     {
-      "evaluation_id": "reward-bench/allenai_Llama-3.1-Tulu-3-70B-SFT-RM-RB2/1766412838.146816",
+      "evaluation_id": "reward-bench-2/allenai_Llama-3.1-Tulu-3-70B-SFT-RM-RB2/1766412838.146816",
       "retrieved_timestamp": "1766412838.146816",
       "source_metadata": {
-        "source_name": "RewardBench",
+        "source_name": "RewardBench 2",
         "source_type": "documentation",
         "source_organization_name": "Allen Institute for AI",
         "source_organization_url": "https://allenai.org",
@@ -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": 0.8892
+            "score": 0.722
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Chat",
+          "evaluation_name": "Factuality",
           "metric_config": {
-            "evaluation_description": "Chat accuracy - includes easy chat subsets",
+            "evaluation_description": "Factuality score - measures factual accuracy",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9693
+            "score": 0.8084
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Chat Hard",
+          "evaluation_name": "Precise IF",
           "metric_config": {
-            "evaluation_description": "Chat Hard accuracy - includes hard chat subsets",
+            "evaluation_description": "Precise Instruction Following score",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.8268
+            "score": 0.3688
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
+          }
+        },
+        {
+          "evaluation_name": "Math",
+          "metric_config": {
+            "evaluation_description": "Math score - measures mathematical reasoning",
+            "lower_is_better": false,
+            "score_type": "continuous",
+            "min_score": 0.0,
+            "max_score": 1.0
+          },
+          "score_details": {
+            "score": 0.6776
+          },
+          "source_data": {
+            "dataset_name": "RewardBench 2",
+            "source_type": "hf_dataset",
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
           "evaluation_name": "Safety",
           "metric_config": {
-            "evaluation_description": "Safety accuracy - includes safety subsets",
+            "evaluation_description": "Safety score - measures safety awareness",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9027
+            "score": 0.8689
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Reasoning",
+          "evaluation_name": "Focus",
           "metric_config": {
-            "evaluation_description": "Reasoning accuracy - includes code and math subsets",
+            "evaluation_description": "Focus score - measures response focus",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.8583
+            "score": 0.7778
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Prior Sets (0.5 weight)",
+          "evaluation_name": "Ties",
           "metric_config": {
-            "evaluation_description": "Prior Sets score (weighted 0.5) - includes test sets",
+            "evaluation_description": "Ties score - ability to identify tie cases",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0
+            "score": 0.8308
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         }
       ],
@@ -141,10 +159,10 @@
       "generation_config": null
     },
     {
-      "evaluation_id": "reward-bench-2/allenai_Llama-3.1-Tulu-3-70B-SFT-RM-RB2/1766412838.146816",
+      "evaluation_id": "reward-bench/allenai_Llama-3.1-Tulu-3-70B-SFT-RM-RB2/1766412838.146816",
       "retrieved_timestamp": "1766412838.146816",
       "source_metadata": {
-        "source_name": "RewardBench 2",
+        "source_name": "RewardBench",
         "source_type": "documentation",
         "source_organization_name": "Allen Institute for AI",
         "source_organization_url": "https://allenai.org",
@@ -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": 0.722
-          },
-          "source_data": {
-            "dataset_name": "RewardBench 2",
-            "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
-          }
-        },
-        {
-          "evaluation_name": "Factuality",
-          "metric_config": {
-            "evaluation_description": "Factuality score - measures factual accuracy",
+            "evaluation_description": "Overall RewardBench Score",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.8084
+            "score": 0.8892
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Precise IF",
+          "evaluation_name": "Chat",
           "metric_config": {
-            "evaluation_description": "Precise Instruction Following score",
+            "evaluation_description": "Chat accuracy - includes easy chat subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3688
+            "score": 0.9693
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Math",
+          "evaluation_name": "Chat Hard",
           "metric_config": {
-            "evaluation_description": "Math score - measures mathematical reasoning",
+            "evaluation_description": "Chat Hard accuracy - includes hard chat subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6776
+            "score": 0.8268
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
           "evaluation_name": "Safety",
           "metric_config": {
-            "evaluation_description": "Safety score - measures safety awareness",
+            "evaluation_description": "Safety accuracy - includes safety subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.8689
+            "score": 0.9027
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Focus",
+          "evaluation_name": "Reasoning",
           "metric_config": {
-            "evaluation_description": "Focus score - measures response focus",
+            "evaluation_description": "Reasoning accuracy - includes code and math subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7778
+            "score": 0.8583
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Ties",
+          "evaluation_name": "Prior Sets (0.5 weight)",
           "metric_config": {
-            "evaluation_description": "Ties score - ability to identify tie cases",
+            "evaluation_description": "Prior Sets score (weighted 0.5) - includes test sets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.8308
+            "score": 0.0
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         }
       ],
diff --git a/data/models/allenai_llama-3.1-tulu-3-8b-dpo-rm-rb2.json b/data/models/allenai_llama-3.1-tulu-3-8b-dpo-rm-rb2.json
index 52eed39924ec31b815aba5be343333e3d61411ae..408cdcea425aaae910c976c1f57587d29fcf9c63 100644
--- a/data/models/allenai_llama-3.1-tulu-3-8b-dpo-rm-rb2.json
+++ b/data/models/allenai_llama-3.1-tulu-3-8b-dpo-rm-rb2.json
@@ -9,10 +9,10 @@
   },
   "evaluations": [
     {
-      "evaluation_id": "reward-bench-2/allenai_Llama-3.1-Tulu-3-8B-DPO-RM-RB2/1766412838.146816",
+      "evaluation_id": "reward-bench/allenai_Llama-3.1-Tulu-3-8B-DPO-RM-RB2/1766412838.146816",
       "retrieved_timestamp": "1766412838.146816",
       "source_metadata": {
-        "source_name": "RewardBench 2",
+        "source_name": "RewardBench",
         "source_type": "documentation",
         "source_organization_name": "Allen Institute for AI",
         "source_organization_url": "https://allenai.org",
@@ -31,127 +31,109 @@
         {
           "evaluation_name": "Score",
           "metric_config": {
-            "evaluation_description": "Overall RewardBench 2 Score (mean of all metrics)",
-            "lower_is_better": false,
-            "score_type": "continuous",
-            "min_score": 0.0,
-            "max_score": 1.0
-          },
-          "score_details": {
-            "score": 0.687
-          },
-          "source_data": {
-            "dataset_name": "RewardBench 2",
-            "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
-          }
-        },
-        {
-          "evaluation_name": "Factuality",
-          "metric_config": {
-            "evaluation_description": "Factuality score - measures factual accuracy",
+            "evaluation_description": "Overall RewardBench Score",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7516
+            "score": 0.8431
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Precise IF",
+          "evaluation_name": "Chat",
           "metric_config": {
-            "evaluation_description": "Precise Instruction Following score",
+            "evaluation_description": "Chat accuracy - includes easy chat subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3875
+            "score": 0.9553
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Math",
+          "evaluation_name": "Chat Hard",
           "metric_config": {
-            "evaluation_description": "Math score - measures mathematical reasoning",
+            "evaluation_description": "Chat Hard accuracy - includes hard chat subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6284
+            "score": 0.761
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
           "evaluation_name": "Safety",
           "metric_config": {
-            "evaluation_description": "Safety score - measures safety awareness",
+            "evaluation_description": "Safety accuracy - includes safety subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.86
+            "score": 0.8662
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Focus",
+          "evaluation_name": "Reasoning",
           "metric_config": {
-            "evaluation_description": "Focus score - measures response focus",
+            "evaluation_description": "Reasoning accuracy - includes code and math subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.8545
+            "score": 0.7898
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Ties",
+          "evaluation_name": "Prior Sets (0.5 weight)",
           "metric_config": {
-            "evaluation_description": "Ties score - ability to identify tie cases",
+            "evaluation_description": "Prior Sets score (weighted 0.5) - includes test sets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6397
+            "score": 0.0
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         }
       ],
@@ -159,10 +141,10 @@
       "generation_config": null
     },
     {
-      "evaluation_id": "reward-bench/allenai_Llama-3.1-Tulu-3-8B-DPO-RM-RB2/1766412838.146816",
+      "evaluation_id": "reward-bench-2/allenai_Llama-3.1-Tulu-3-8B-DPO-RM-RB2/1766412838.146816",
       "retrieved_timestamp": "1766412838.146816",
       "source_metadata": {
-        "source_name": "RewardBench",
+        "source_name": "RewardBench 2",
         "source_type": "documentation",
         "source_organization_name": "Allen Institute for AI",
         "source_organization_url": "https://allenai.org",
@@ -181,109 +163,127 @@
         {
           "evaluation_name": "Score",
           "metric_config": {
-            "evaluation_description": "Overall RewardBench Score",
+            "evaluation_description": "Overall RewardBench 2 Score (mean of all metrics)",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.8431
+            "score": 0.687
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Chat",
+          "evaluation_name": "Factuality",
           "metric_config": {
-            "evaluation_description": "Chat accuracy - includes easy chat subsets",
+            "evaluation_description": "Factuality score - measures factual accuracy",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9553
+            "score": 0.7516
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Chat Hard",
+          "evaluation_name": "Precise IF",
           "metric_config": {
-            "evaluation_description": "Chat Hard accuracy - includes hard chat subsets",
+            "evaluation_description": "Precise Instruction Following score",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.761
+            "score": 0.3875
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
+          }
+        },
+        {
+          "evaluation_name": "Math",
+          "metric_config": {
+            "evaluation_description": "Math score - measures mathematical reasoning",
+            "lower_is_better": false,
+            "score_type": "continuous",
+            "min_score": 0.0,
+            "max_score": 1.0
+          },
+          "score_details": {
+            "score": 0.6284
+          },
+          "source_data": {
+            "dataset_name": "RewardBench 2",
+            "source_type": "hf_dataset",
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
           "evaluation_name": "Safety",
           "metric_config": {
-            "evaluation_description": "Safety accuracy - includes safety subsets",
+            "evaluation_description": "Safety score - measures safety awareness",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.8662
+            "score": 0.86
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Reasoning",
+          "evaluation_name": "Focus",
           "metric_config": {
-            "evaluation_description": "Reasoning accuracy - includes code and math subsets",
+            "evaluation_description": "Focus score - measures response focus",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7898
+            "score": 0.8545
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Prior Sets (0.5 weight)",
+          "evaluation_name": "Ties",
           "metric_config": {
-            "evaluation_description": "Prior Sets score (weighted 0.5) - includes test sets",
+            "evaluation_description": "Ties score - ability to identify tie cases",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0
+            "score": 0.6397
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         }
       ],
diff --git a/data/models/allenai_llama-3.1-tulu-3-8b.json b/data/models/allenai_llama-3.1-tulu-3-8b.json
index 7de1c9431728784c04f1c32781631febc2ed7e32..53350f20b1f74556a0af6a9aa87ed77d181deaec 100644
--- a/data/models/allenai_llama-3.1-tulu-3-8b.json
+++ b/data/models/allenai_llama-3.1-tulu-3-8b.json
@@ -5,7 +5,7 @@
     "developer": "allenai",
     "inference_platform": "unknown",
     "additional_details": {
-      "precision": "bfloat16",
+      "precision": "float16",
       "architecture": "LlamaForCausalLM",
       "params_billions": "8.03"
     }
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.8267
+            "score": 0.8255
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.405
+            "score": 0.4061
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1964
+            "score": 0.2115
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2987
+            "score": 0.297
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2827
+            "score": 0.2821
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.8255
+            "score": 0.8267
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4061
+            "score": 0.405
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2115
+            "score": 0.1964
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.297
+            "score": 0.2987
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2821
+            "score": 0.2827
           }
         }
       ],
diff --git a/data/models/amd_amd-llama-135m.json b/data/models/amd_amd-llama-135m.json
index dfdcf8e7a431ddc8bdf51b6aa797b81cf0f89c9e..a445333e3dd0495a4c3e2fddf3e92a96b288f85c 100644
--- a/data/models/amd_amd-llama-135m.json
+++ b/data/models/amd_amd-llama-135m.json
@@ -5,9 +5,9 @@
     "developer": "amd",
     "inference_platform": "unknown",
     "additional_details": {
-      "precision": "bfloat16",
+      "precision": "float16",
       "architecture": "LlamaForCausalLM",
-      "params_billions": "0.134"
+      "params_billions": "0.135"
     }
   },
   "evaluations": [
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1918
+            "score": 0.1842
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2969
+            "score": 0.2974
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0076
+            "score": 0.0053
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2584
+            "score": 0.2525
           }
         },
         {
@@ -116,7 +116,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3846
+            "score": 0.378
           }
         },
         {
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1842
+            "score": 0.1918
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2974
+            "score": 0.2969
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0053
+            "score": 0.0076
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2525
+            "score": 0.2584
           }
         },
         {
@@ -246,7 +246,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.378
+            "score": 0.3846
           }
         },
         {
diff --git a/data/models/anthropic_claude-3-5-haiku-20241022.json b/data/models/anthropic_claude-3-5-haiku-20241022.json
index 9edb0c7484cd3b1eab61fa90716227281f955253..97ab32cadbb5e110dfa409cbea1ee9b8c38d6850 100644
--- a/data/models/anthropic_claude-3-5-haiku-20241022.json
+++ b/data/models/anthropic_claude-3-5-haiku-20241022.json
@@ -10,8 +10,8 @@
   },
   "evaluations": [
     {
-      "evaluation_id": "global-mmlu-lite/anthropic_claude-3-5-haiku-20241022/1773936583.743359",
-      "retrieved_timestamp": "1773936583.743359",
+      "evaluation_id": "global-mmlu-lite/anthropic_claude-3-5-haiku-20241022/1773936496.366405",
+      "retrieved_timestamp": "1773936496.366405",
       "source_metadata": {
         "source_name": "Global MMLU Lite Leaderboard",
         "source_type": "documentation",
@@ -525,8 +525,8 @@
       "generation_config": null
     },
     {
-      "evaluation_id": "global-mmlu-lite/anthropic_claude-3-5-haiku-20241022/1773936496.366405",
-      "retrieved_timestamp": "1773936496.366405",
+      "evaluation_id": "global-mmlu-lite/anthropic_claude-3-5-haiku-20241022/1773936583.743359",
+      "retrieved_timestamp": "1773936583.743359",
       "source_metadata": {
         "source_name": "Global MMLU Lite Leaderboard",
         "source_type": "documentation",
diff --git a/data/models/anthropic_claude-3-7-sonnet-20250219.json b/data/models/anthropic_claude-3-7-sonnet-20250219.json
index 26744b8fcce13c56de7ede1b941e4f633dfc781a..6e02a0c482b2aed6381eb4f121bd334b0959f1b6 100644
--- a/data/models/anthropic_claude-3-7-sonnet-20250219.json
+++ b/data/models/anthropic_claude-3-7-sonnet-20250219.json
@@ -10,8 +10,8 @@
   },
   "evaluations": [
     {
-      "evaluation_id": "global-mmlu-lite/anthropic_claude-3-7-sonnet-20250219/1773936583.743359",
-      "retrieved_timestamp": "1773936583.743359",
+      "evaluation_id": "global-mmlu-lite/anthropic_claude-3-7-sonnet-20250219/1773936496.366405",
+      "retrieved_timestamp": "1773936496.366405",
       "source_metadata": {
         "source_name": "Global MMLU Lite Leaderboard",
         "source_type": "documentation",
@@ -525,8 +525,8 @@
       "generation_config": null
     },
     {
-      "evaluation_id": "global-mmlu-lite/anthropic_claude-3-7-sonnet-20250219/1773936496.366405",
-      "retrieved_timestamp": "1773936496.366405",
+      "evaluation_id": "global-mmlu-lite/anthropic_claude-3-7-sonnet-20250219/1773936583.743359",
+      "retrieved_timestamp": "1773936583.743359",
       "source_metadata": {
         "source_name": "Global MMLU Lite Leaderboard",
         "source_type": "documentation",
diff --git a/data/models/anthropic_claude-3-haiku-20240307.json b/data/models/anthropic_claude-3-haiku-20240307.json
index 52bb9959dd5613be4f3fe143bd6f01f97e2632c2..4a2b563f634d87e24d77a5003bd4befff9181e63 100644
--- a/data/models/anthropic_claude-3-haiku-20240307.json
+++ b/data/models/anthropic_claude-3-haiku-20240307.json
@@ -1903,10 +1903,10 @@
       }
     },
     {
-      "evaluation_id": "reward-bench/Anthropic_claude-3-haiku-20240307/1766412838.146816",
+      "evaluation_id": "reward-bench-2/anthropic_claude-3-haiku-20240307/1766412838.146816",
       "retrieved_timestamp": "1766412838.146816",
       "source_metadata": {
-        "source_name": "RewardBench",
+        "source_name": "RewardBench 2",
         "source_type": "documentation",
         "source_organization_name": "Allen Institute for AI",
         "source_organization_url": "https://allenai.org",
@@ -1925,109 +1925,127 @@
         {
           "evaluation_name": "Score",
           "metric_config": {
-            "evaluation_description": "Overall RewardBench Score",
+            "evaluation_description": "Overall RewardBench 2 Score (mean of all metrics)",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7289
+            "score": 0.3711
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Chat",
+          "evaluation_name": "Factuality",
           "metric_config": {
-            "evaluation_description": "Chat accuracy - includes easy chat subsets",
+            "evaluation_description": "Factuality score - measures factual accuracy",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9274
+            "score": 0.4042
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Chat Hard",
+          "evaluation_name": "Precise IF",
           "metric_config": {
-            "evaluation_description": "Chat Hard accuracy - includes hard chat subsets",
+            "evaluation_description": "Precise Instruction Following score",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5197
+            "score": 0.2812
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
+          }
+        },
+        {
+          "evaluation_name": "Math",
+          "metric_config": {
+            "evaluation_description": "Math score - measures mathematical reasoning",
+            "lower_is_better": false,
+            "score_type": "continuous",
+            "min_score": 0.0,
+            "max_score": 1.0
+          },
+          "score_details": {
+            "score": 0.3552
+          },
+          "source_data": {
+            "dataset_name": "RewardBench 2",
+            "source_type": "hf_dataset",
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
           "evaluation_name": "Safety",
           "metric_config": {
-            "evaluation_description": "Safety accuracy - includes safety subsets",
+            "evaluation_description": "Safety score - measures safety awareness",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7953
+            "score": 0.595
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Reasoning",
+          "evaluation_name": "Focus",
           "metric_config": {
-            "evaluation_description": "Reasoning accuracy - includes code and math subsets",
+            "evaluation_description": "Focus score - measures response focus",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.706
+            "score": 0.501
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Prior Sets (0.5 weight)",
+          "evaluation_name": "Ties",
           "metric_config": {
-            "evaluation_description": "Prior Sets score (weighted 0.5) - includes test sets",
+            "evaluation_description": "Ties score - ability to identify tie cases",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6635
+            "score": 0.0899
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         }
       ],
@@ -2035,10 +2053,10 @@
       "generation_config": null
     },
     {
-      "evaluation_id": "reward-bench-2/anthropic_claude-3-haiku-20240307/1766412838.146816",
+      "evaluation_id": "reward-bench/Anthropic_claude-3-haiku-20240307/1766412838.146816",
       "retrieved_timestamp": "1766412838.146816",
       "source_metadata": {
-        "source_name": "RewardBench 2",
+        "source_name": "RewardBench",
         "source_type": "documentation",
         "source_organization_name": "Allen Institute for AI",
         "source_organization_url": "https://allenai.org",
@@ -2057,127 +2075,109 @@
         {
           "evaluation_name": "Score",
           "metric_config": {
-            "evaluation_description": "Overall RewardBench 2 Score (mean of all metrics)",
-            "lower_is_better": false,
-            "score_type": "continuous",
-            "min_score": 0.0,
-            "max_score": 1.0
-          },
-          "score_details": {
-            "score": 0.3711
-          },
-          "source_data": {
-            "dataset_name": "RewardBench 2",
-            "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
-          }
-        },
-        {
-          "evaluation_name": "Factuality",
-          "metric_config": {
-            "evaluation_description": "Factuality score - measures factual accuracy",
+            "evaluation_description": "Overall RewardBench Score",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4042
+            "score": 0.7289
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Precise IF",
+          "evaluation_name": "Chat",
           "metric_config": {
-            "evaluation_description": "Precise Instruction Following score",
+            "evaluation_description": "Chat accuracy - includes easy chat subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2812
+            "score": 0.9274
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Math",
+          "evaluation_name": "Chat Hard",
           "metric_config": {
-            "evaluation_description": "Math score - measures mathematical reasoning",
+            "evaluation_description": "Chat Hard accuracy - includes hard chat subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3552
+            "score": 0.5197
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
           "evaluation_name": "Safety",
           "metric_config": {
-            "evaluation_description": "Safety score - measures safety awareness",
+            "evaluation_description": "Safety accuracy - includes safety subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.595
+            "score": 0.7953
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Focus",
+          "evaluation_name": "Reasoning",
           "metric_config": {
-            "evaluation_description": "Focus score - measures response focus",
+            "evaluation_description": "Reasoning accuracy - includes code and math subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.501
+            "score": 0.706
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Ties",
+          "evaluation_name": "Prior Sets (0.5 weight)",
           "metric_config": {
-            "evaluation_description": "Ties score - ability to identify tie cases",
+            "evaluation_description": "Prior Sets score (weighted 0.5) - includes test sets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0899
+            "score": 0.6635
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         }
       ],
diff --git a/data/models/anthropic_claude-3-opus-20240229.json b/data/models/anthropic_claude-3-opus-20240229.json
index 150503f1a5f91571d10a33f8965d4bd84f3ccf46..8f8b70dd804fcbb225ceb8111209d93e20e8bd0b 100644
--- a/data/models/anthropic_claude-3-opus-20240229.json
+++ b/data/models/anthropic_claude-3-opus-20240229.json
@@ -1903,10 +1903,10 @@
       }
     },
     {
-      "evaluation_id": "reward-bench-2/anthropic_claude-3-opus-20240229/1766412838.146816",
+      "evaluation_id": "reward-bench/Anthropic_claude-3-opus-20240229/1766412838.146816",
       "retrieved_timestamp": "1766412838.146816",
       "source_metadata": {
-        "source_name": "RewardBench 2",
+        "source_name": "RewardBench",
         "source_type": "documentation",
         "source_organization_name": "Allen Institute for AI",
         "source_organization_url": "https://allenai.org",
@@ -1925,104 +1925,128 @@
         {
           "evaluation_name": "Score",
           "metric_config": {
-            "evaluation_description": "Overall RewardBench 2 Score (mean of all metrics)",
+            "evaluation_description": "Overall RewardBench Score",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5744
+            "score": 0.8008
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Factuality",
+          "evaluation_name": "Chat",
           "metric_config": {
-            "evaluation_description": "Factuality score - measures factual accuracy",
+            "evaluation_description": "Chat accuracy - includes easy chat subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5389
+            "score": 0.9469
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Precise IF",
+          "evaluation_name": "Chat Hard",
           "metric_config": {
-            "evaluation_description": "Precise Instruction Following score",
+            "evaluation_description": "Chat Hard accuracy - includes hard chat subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3312
+            "score": 0.6031
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Math",
+          "evaluation_name": "Safety",
           "metric_config": {
-            "evaluation_description": "Math score - measures mathematical reasoning",
+            "evaluation_description": "Safety accuracy - includes safety subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5137
+            "score": 0.8662
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Safety",
+          "evaluation_name": "Reasoning",
           "metric_config": {
-            "evaluation_description": "Safety score - measures safety awareness",
+            "evaluation_description": "Reasoning accuracy - includes code and math subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.8378
+            "score": 0.7868
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
-        },
+        }
+      ],
+      "detailed_evaluation_results": null,
+      "generation_config": null
+    },
+    {
+      "evaluation_id": "reward-bench-2/anthropic_claude-3-opus-20240229/1766412838.146816",
+      "retrieved_timestamp": "1766412838.146816",
+      "source_metadata": {
+        "source_name": "RewardBench 2",
+        "source_type": "documentation",
+        "source_organization_name": "Allen Institute for AI",
+        "source_organization_url": "https://allenai.org",
+        "evaluator_relationship": "third_party"
+      },
+      "eval_library": {
+        "name": "rewardbench",
+        "version": "0.1.3",
+        "additional_details": {
+          "subsets": "Chat, Chat Hard, Safety, Reasoning",
+          "hf_space": "allenai/reward-bench"
+        }
+      },
+      "benchmark": "reward-bench",
+      "evaluation_results": [
         {
-          "evaluation_name": "Focus",
+          "evaluation_name": "Score",
           "metric_config": {
-            "evaluation_description": "Focus score - measures response focus",
+            "evaluation_description": "Overall RewardBench 2 Score (mean of all metrics)",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6646
+            "score": 0.5744
           },
           "source_data": {
             "dataset_name": "RewardBench 2",
@@ -2031,135 +2055,111 @@
           }
         },
         {
-          "evaluation_name": "Ties",
+          "evaluation_name": "Factuality",
           "metric_config": {
-            "evaluation_description": "Ties score - ability to identify tie cases",
+            "evaluation_description": "Factuality score - measures factual accuracy",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5601
+            "score": 0.5389
           },
           "source_data": {
             "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
             "hf_repo": "allenai/reward-bench-2-results"
           }
-        }
-      ],
-      "detailed_evaluation_results": null,
-      "generation_config": null
-    },
-    {
-      "evaluation_id": "reward-bench/Anthropic_claude-3-opus-20240229/1766412838.146816",
-      "retrieved_timestamp": "1766412838.146816",
-      "source_metadata": {
-        "source_name": "RewardBench",
-        "source_type": "documentation",
-        "source_organization_name": "Allen Institute for AI",
-        "source_organization_url": "https://allenai.org",
-        "evaluator_relationship": "third_party"
-      },
-      "eval_library": {
-        "name": "rewardbench",
-        "version": "0.1.3",
-        "additional_details": {
-          "subsets": "Chat, Chat Hard, Safety, Reasoning",
-          "hf_space": "allenai/reward-bench"
-        }
-      },
-      "benchmark": "reward-bench",
-      "evaluation_results": [
+        },
         {
-          "evaluation_name": "Score",
+          "evaluation_name": "Precise IF",
           "metric_config": {
-            "evaluation_description": "Overall RewardBench Score",
+            "evaluation_description": "Precise Instruction Following score",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.8008
+            "score": 0.3312
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Chat",
+          "evaluation_name": "Math",
           "metric_config": {
-            "evaluation_description": "Chat accuracy - includes easy chat subsets",
+            "evaluation_description": "Math score - measures mathematical reasoning",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9469
+            "score": 0.5137
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Chat Hard",
+          "evaluation_name": "Safety",
           "metric_config": {
-            "evaluation_description": "Chat Hard accuracy - includes hard chat subsets",
+            "evaluation_description": "Safety score - measures safety awareness",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6031
+            "score": 0.8378
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Safety",
+          "evaluation_name": "Focus",
           "metric_config": {
-            "evaluation_description": "Safety accuracy - includes safety subsets",
+            "evaluation_description": "Focus score - measures response focus",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.8662
+            "score": 0.6646
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Reasoning",
+          "evaluation_name": "Ties",
           "metric_config": {
-            "evaluation_description": "Reasoning accuracy - includes code and math subsets",
+            "evaluation_description": "Ties score - ability to identify tie cases",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7868
+            "score": 0.5601
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         }
       ],
diff --git a/data/models/anthropic_claude-haiku-4.5.json b/data/models/anthropic_claude-haiku-4.5.json
index e7b7ed8c329f7f81d319b4442fafacedb7ba1133..5982de0c04db9149bd5fa6081ab9674c3bc855d7 100644
--- a/data/models/anthropic_claude-haiku-4.5.json
+++ b/data/models/anthropic_claude-haiku-4.5.json
@@ -4,13 +4,13 @@
     "id": "anthropic/claude-haiku-4.5",
     "developer": "Anthropic",
     "additional_details": {
-      "agent_name": "Mini-SWE-Agent",
-      "agent_organization": "Princeton"
+      "agent_name": "Goose",
+      "agent_organization": "Block"
     }
   },
   "evaluations": [
     {
-      "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",
@@ -34,7 +34,7 @@
               "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,
@@ -43,17 +43,17 @@
             "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": [
                   {
@@ -70,7 +70,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Mini-SWE-Agent\" -m \"Claude Haiku 4.5\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Goose\" -m \"Claude Haiku 4.5\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -84,7 +84,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/terminus-2__claude-haiku-4.5/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/openhands__claude-haiku-4.5/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -108,7 +108,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-10-31",
+          "evaluation_timestamp": "2025-11-02",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -117,17 +117,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 28.3,
+            "score": 13.9,
             "uncertainty": {
               "standard_error": {
-                "value": 2.9
+                "value": 2.7
               },
               "num_samples": 435
             }
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"Claude Haiku 4.5\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"OpenHands\" -m \"Claude Haiku 4.5\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -144,7 +144,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"Claude Haiku 4.5\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"OpenHands\" -m \"Claude Haiku 4.5\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -158,7 +158,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/goose__claude-haiku-4.5/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/mini-swe-agent__claude-haiku-4.5/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -182,7 +182,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-12-11",
+          "evaluation_timestamp": "2025-11-03",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -191,17 +191,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 35.5,
+            "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 \"Goose\" -m \"Claude Haiku 4.5\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Mini-SWE-Agent\" -m \"Claude Haiku 4.5\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -218,7 +218,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Goose\" -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": [
               {
@@ -306,7 +306,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/openhands__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",
@@ -330,7 +330,7 @@
               "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,
@@ -339,17 +339,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 13.9,
+            "score": 28.3,
             "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 \"OpenHands\" -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": [
                   {
@@ -366,7 +366,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"OpenHands\" -m \"Claude Haiku 4.5\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -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 ec98797a0bada43df823aeb8285704dc256b7f56..47edf5cb77433abffb4d65f42865bc3c46d880ed 100644
--- a/data/models/anthropic_claude-opus-4-5.json
+++ b/data/models/anthropic_claude-opus-4-5.json
@@ -4,13 +4,13 @@
     "id": "anthropic/claude-opus-4-5",
     "developer": "Anthropic",
     "additional_details": {
-      "agent_name": "LiteLLM Tool Calling with Shortlisting",
-      "agent_framework": "tool_calling_with_shortlisting"
+      "agent_name": "Claude Code CLI",
+      "agent_framework": "claude_code"
     }
   },
   "evaluations": [
     {
-      "evaluation_id": "appworld/test_normal/litellm-tool-calling-with-shortlisting__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",
@@ -42,23 +42,23 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.64,
+            "score": 0.66,
             "uncertainty": {
               "num_samples": 100
             },
             "details": {
-              "average_agent_cost": "3.43",
-              "total_run_cost": "343.32",
-              "average_steps": "20.06",
-              "percent_finished": "0.82"
+              "average_agent_cost": "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": "LiteLLM Tool Calling with Shortlisting",
-                  "agent_framework": "tool_calling_with_shortlisting"
+                  "agent_name": "Claude Code CLI",
+                  "agent_framework": "claude_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": "Claude Code CLI",
+              "agent_framework": "claude_code"
             }
           }
         }
@@ -282,7 +282,7 @@
       }
     },
     {
-      "evaluation_id": "browsecompplus/claude-code-cli__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",
@@ -295,42 +295,42 @@
         "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": 0.64,
             "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": "3.43",
+              "total_run_cost": "343.32",
+              "average_steps": "20.06",
+              "percent_finished": "0.82"
             }
           },
           "generation_config": {
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "Claude Code CLI",
-                  "agent_framework": "claude_code"
+                  "agent_name": "LiteLLM Tool Calling with Shortlisting",
+                  "agent_framework": "tool_calling_with_shortlisting"
                 }
               }
             }
@@ -342,15 +342,15 @@
         "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/litellm-tool-calling__anthropic_claude-opus-4-5/1774263615.0201504",
+      "evaluation_id": "browsecompplus/claude-code-cli__anthropic_claude-opus-4-5/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -382,23 +382,23 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.49,
+            "score": 0.5294,
             "uncertainty": {
-              "num_samples": 100
+              "num_samples": 51
             },
             "details": {
-              "average_agent_cost": "7.09",
-              "total_run_cost": "709.54",
-              "average_steps": "21.66",
-              "percent_finished": "0.93"
+              "average_agent_cost": "11.66",
+              "total_run_cost": "594.68",
+              "average_steps": "31.04",
+              "percent_finished": "0.8431"
             }
           },
           "generation_config": {
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "LiteLLM Tool Calling",
-                  "agent_framework": "tool_calling"
+                  "agent_name": "Claude Code CLI",
+                  "agent_framework": "claude_code"
                 }
               }
             }
@@ -410,15 +410,15 @@
         "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/openai-solo__anthropic_claude-opus-4-5/1774263615.0201504",
+      "evaluation_id": "browsecompplus/openai-solo__anthropic_claude-opus-4-5/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -431,34 +431,34 @@
         "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": 0.68,
+            "score": 0.61,
             "uncertainty": {
               "num_samples": 100
             },
             "details": {
-              "average_agent_cost": "22.76",
-              "total_run_cost": "2276.48",
-              "average_steps": "47.65",
-              "percent_finished": "0.77"
+              "average_agent_cost": "7.59",
+              "total_run_cost": "759.44",
+              "average_steps": "27.18",
+              "percent_finished": "1.0"
             }
           },
           "generation_config": {
@@ -486,7 +486,7 @@
       }
     },
     {
-      "evaluation_id": "browsecompplus/openai-solo__anthropic_claude-opus-4-5/1774263615.0201504",
+      "evaluation_id": "browsecompplus/litellm-tool-calling-with-shortlisting__anthropic_claude-opus-4-5/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -518,23 +518,23 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.61,
+            "score": 0.49,
             "uncertainty": {
               "num_samples": 100
             },
             "details": {
-              "average_agent_cost": "7.59",
-              "total_run_cost": "759.44",
-              "average_steps": "27.18",
-              "percent_finished": "1.0"
+              "average_agent_cost": "7.09",
+              "total_run_cost": "709.54",
+              "average_steps": "21.66",
+              "percent_finished": "0.93"
             }
           },
           "generation_config": {
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "OpenAI Solo",
-                  "agent_framework": "openai_solo"
+                  "agent_name": "LiteLLM Tool Calling with Shortlisting",
+                  "agent_framework": "tool_calling_with_shortlisting"
                 }
               }
             }
@@ -546,15 +546,15 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "OpenAI Solo",
-              "agent_framework": "openai_solo"
+              "agent_name": "LiteLLM Tool Calling with Shortlisting",
+              "agent_framework": "tool_calling_with_shortlisting"
             }
           }
         }
       }
     },
     {
-      "evaluation_id": "appworld/test_normal/claude-code-cli__anthropic_claude-opus-4-5/1774263615.0201504",
+      "evaluation_id": "appworld/test_normal/openai-solo__anthropic_claude-opus-4-5/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -586,23 +586,23 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.66,
+            "score": 0.68,
             "uncertainty": {
               "num_samples": 100
             },
             "details": {
-              "average_agent_cost": "13.08",
-              "total_run_cost": "1308.38",
-              "average_steps": "49.69",
-              "percent_finished": "0.74"
+              "average_agent_cost": "22.76",
+              "total_run_cost": "2276.48",
+              "average_steps": "47.65",
+              "percent_finished": "0.77"
             }
           },
           "generation_config": {
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "Claude Code CLI",
-                  "agent_framework": "claude_code"
+                  "agent_name": "OpenAI Solo",
+                  "agent_framework": "openai_solo"
                 }
               }
             }
@@ -614,15 +614,15 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "Claude Code CLI",
-              "agent_framework": "claude_code"
+              "agent_name": "OpenAI Solo",
+              "agent_framework": "openai_solo"
             }
           }
         }
       }
     },
     {
-      "evaluation_id": "browsecompplus/litellm-tool-calling-with-shortlisting__anthropic_claude-opus-4-5/1774263615.0201504",
+      "evaluation_id": "browsecompplus/litellm-tool-calling__anthropic_claude-opus-4-5/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -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"
                 }
               }
             }
@@ -682,15 +682,15 @@
         "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/openai-solo__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",
@@ -722,14 +722,14 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.8072,
+            "score": 0.6061,
             "uncertainty": {
-              "num_samples": 83
+              "num_samples": 99
             },
             "details": {
-              "average_agent_cost": "2.96",
-              "total_run_cost": "245.78",
-              "average_steps": "34.1",
+              "average_agent_cost": "3.97",
+              "total_run_cost": "393.16",
+              "average_steps": "43.44",
               "percent_finished": "1.0"
             }
           },
@@ -737,8 +737,8 @@
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "OpenAI Solo",
-                  "agent_framework": "openai_solo"
+                  "agent_name": "LiteLLM Tool Calling",
+                  "agent_framework": "tool_calling"
                 }
               }
             }
@@ -750,15 +750,15 @@
         "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__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",
@@ -805,8 +805,8 @@
             "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"
                 }
               }
             }
@@ -818,8 +818,8 @@
         "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"
             }
           }
         }
@@ -894,7 +894,7 @@
       }
     },
     {
-      "evaluation_id": "swe-bench/litellm-tool-calling-with-shortlisting__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 +926,14 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6061,
+            "score": 0.65,
             "uncertainty": {
-              "num_samples": 99
+              "num_samples": 100
             },
             "details": {
-              "average_agent_cost": "3.97",
-              "total_run_cost": "393.16",
-              "average_steps": "43.44",
+              "average_agent_cost": "4.85",
+              "total_run_cost": "485.22",
+              "average_steps": "39.13",
               "percent_finished": "1.0"
             }
           },
@@ -941,8 +941,8 @@
             "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"
                 }
               }
             }
@@ -954,15 +954,15 @@
         "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": "swe-bench/smolagents-code__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",
@@ -994,14 +994,14 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.65,
+            "score": 0.8072,
             "uncertainty": {
-              "num_samples": 100
+              "num_samples": 83
             },
             "details": {
-              "average_agent_cost": "4.85",
-              "total_run_cost": "485.22",
-              "average_steps": "39.13",
+              "average_agent_cost": "2.96",
+              "total_run_cost": "245.78",
+              "average_steps": "34.1",
               "percent_finished": "1.0"
             }
           },
@@ -1009,8 +1009,8 @@
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "SmolAgents Code",
-                  "agent_framework": "smolagents_code"
+                  "agent_name": "OpenAI Solo",
+                  "agent_framework": "openai_solo"
                 }
               }
             }
@@ -1022,8 +1022,8 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "SmolAgents Code",
-              "agent_framework": "smolagents_code"
+              "agent_name": "OpenAI Solo",
+              "agent_framework": "openai_solo"
             }
           }
         }
@@ -1098,7 +1098,7 @@
       }
     },
     {
-      "evaluation_id": "tau-bench-2/airline/claude-code-cli__anthropic_claude-opus-4-5/1774263615.0201504",
+      "evaluation_id": "tau-bench-2/airline/litellm-tool-calling__anthropic_claude-opus-4-5/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -1135,9 +1135,9 @@
               "num_samples": 50
             },
             "details": {
-              "average_agent_cost": "1.3",
-              "total_run_cost": "65.66",
-              "average_steps": "11.5",
+              "average_agent_cost": "0.47",
+              "total_run_cost": "24.23",
+              "average_steps": "10.0",
               "percent_finished": "1.0"
             }
           },
@@ -1145,8 +1145,8 @@
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "Claude Code CLI",
-                  "agent_framework": "claude_code"
+                  "agent_name": "LiteLLM Tool Calling",
+                  "agent_framework": "tool_calling"
                 }
               }
             }
@@ -1158,15 +1158,15 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "Claude Code CLI",
-              "agent_framework": "claude_code"
+              "agent_name": "LiteLLM Tool Calling",
+              "agent_framework": "tool_calling"
             }
           }
         }
       }
     },
     {
-      "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",
@@ -1198,14 +1198,14 @@
             "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"
             }
           },
@@ -1213,8 +1213,8 @@
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "LiteLLM Tool Calling",
-                  "agent_framework": "tool_calling"
+                  "agent_name": "SmolAgents Code",
+                  "agent_framework": "smolagents_code"
                 }
               }
             }
@@ -1226,8 +1226,8 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "LiteLLM Tool Calling",
-              "agent_framework": "tool_calling"
+              "agent_name": "SmolAgents Code",
+              "agent_framework": "smolagents_code"
             }
           }
         }
@@ -1302,7 +1302,7 @@
       }
     },
     {
-      "evaluation_id": "tau-bench-2/airline/smolagents-code__anthropic_claude-opus-4-5/1774263615.0201504",
+      "evaluation_id": "tau-bench-2/airline/claude-code-cli__anthropic_claude-opus-4-5/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -1334,14 +1334,14 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.72,
+            "score": 0.66,
             "uncertainty": {
               "num_samples": 50
             },
             "details": {
-              "average_agent_cost": "0.78",
-              "total_run_cost": "39.67",
-              "average_steps": "11.88",
+              "average_agent_cost": "1.3",
+              "total_run_cost": "65.66",
+              "average_steps": "11.5",
               "percent_finished": "1.0"
             }
           },
@@ -1349,8 +1349,8 @@
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "SmolAgents Code",
-                  "agent_framework": "smolagents_code"
+                  "agent_name": "Claude Code CLI",
+                  "agent_framework": "claude_code"
                 }
               }
             }
@@ -1362,8 +1362,8 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "SmolAgents Code",
-              "agent_framework": "smolagents_code"
+              "agent_name": "Claude Code CLI",
+              "agent_framework": "claude_code"
             }
           }
         }
@@ -1438,7 +1438,7 @@
       }
     },
     {
-      "evaluation_id": "tau-bench-2/retail/claude-code-cli__anthropic_claude-opus-4-5/1774263615.0201504",
+      "evaluation_id": "tau-bench-2/retail/openai-solo__anthropic_claude-opus-4-5/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -1470,13 +1470,13 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.83,
+            "score": 0.85,
             "uncertainty": {
               "num_samples": 100
             },
             "details": {
-              "average_agent_cost": "1.6",
-              "total_run_cost": "161.14",
+              "average_agent_cost": "0.55",
+              "total_run_cost": "56.18",
               "average_steps": "12.54",
               "percent_finished": "1.0"
             }
@@ -1485,8 +1485,8 @@
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "Claude Code CLI",
-                  "agent_framework": "claude_code"
+                  "agent_name": "OpenAI Solo",
+                  "agent_framework": "openai_solo"
                 }
               }
             }
@@ -1498,8 +1498,8 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "Claude Code CLI",
-              "agent_framework": "claude_code"
+              "agent_name": "OpenAI Solo",
+              "agent_framework": "openai_solo"
             }
           }
         }
@@ -1642,7 +1642,7 @@
       }
     },
     {
-      "evaluation_id": "tau-bench-2/retail/openai-solo__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",
@@ -1674,13 +1674,13 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.85,
+            "score": 0.83,
             "uncertainty": {
               "num_samples": 100
             },
             "details": {
-              "average_agent_cost": "0.55",
-              "total_run_cost": "56.18",
+              "average_agent_cost": "1.6",
+              "total_run_cost": "161.14",
               "average_steps": "12.54",
               "percent_finished": "1.0"
             }
@@ -1689,8 +1689,8 @@
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "OpenAI Solo",
-                  "agent_framework": "openai_solo"
+                  "agent_name": "Claude Code CLI",
+                  "agent_framework": "claude_code"
                 }
               }
             }
@@ -1702,8 +1702,8 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "OpenAI Solo",
-              "agent_framework": "openai_solo"
+              "agent_name": "Claude Code CLI",
+              "agent_framework": "claude_code"
             }
           }
         }
@@ -1778,7 +1778,7 @@
       }
     },
     {
-      "evaluation_id": "tau-bench-2/telecom/litellm-tool-calling__anthropic_claude-opus-4-5/1774263615.0201504",
+      "evaluation_id": "tau-bench-2/telecom/claude-code-cli__anthropic_claude-opus-4-5/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -1815,9 +1815,9 @@
               "num_samples": 100
             },
             "details": {
-              "average_agent_cost": "0.92",
-              "total_run_cost": "102.01",
-              "average_steps": "17.22",
+              "average_agent_cost": "2.45",
+              "total_run_cost": "255.97",
+              "average_steps": "18.71",
               "percent_finished": "1.0"
             }
           },
@@ -1825,8 +1825,8 @@
             "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"
                 }
               }
             }
@@ -1838,15 +1838,15 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "LiteLLM Tool Calling",
-              "agent_framework": "tool_calling"
+              "agent_name": "Claude Code CLI",
+              "agent_framework": "claude_code"
             }
           }
         }
       }
     },
     {
-      "evaluation_id": "tau-bench-2/telecom/claude-code-cli__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",
@@ -1883,9 +1883,9 @@
               "num_samples": 100
             },
             "details": {
-              "average_agent_cost": "2.45",
-              "total_run_cost": "255.97",
-              "average_steps": "18.71",
+              "average_agent_cost": "0.92",
+              "total_run_cost": "102.01",
+              "average_steps": "17.22",
               "percent_finished": "1.0"
             }
           },
@@ -1893,8 +1893,8 @@
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "Claude Code CLI",
-                  "agent_framework": "claude_code"
+                  "agent_name": "LiteLLM Tool Calling",
+                  "agent_framework": "tool_calling"
                 }
               }
             }
@@ -1906,8 +1906,8 @@
         "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/anthropic_claude-opus-4.1.json b/data/models/anthropic_claude-opus-4.1.json
index 643c986c59e6df513c07edafb084900951fa2ab2..f450f39387f472cdddd30c8581d35da9f459d5c6 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": "Claude Code",
-      "agent_organization": "Anthropic"
+      "agent_name": "Mini-SWE-Agent",
+      "agent_organization": "Princeton"
     }
   },
   "evaluations": [
     {
-      "evaluation_id": "terminal-bench-2.0/claude-code__claude-opus-4.1/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/mini-swe-agent__claude-opus-4.1/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -34,7 +34,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-11-04",
+          "evaluation_timestamp": "2025-11-03",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -43,17 +43,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 34.8,
+            "score": 35.1,
             "uncertainty": {
               "standard_error": {
-                "value": 2.9
+                "value": 2.5
               },
               "num_samples": 435
             }
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Claude Code\" -m \"Claude Opus 4.1\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Mini-SWE-Agent\" -m \"Claude Opus 4.1\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -70,7 +70,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Claude Code\" -m \"Claude Opus 4.1\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Mini-SWE-Agent\" -m \"Claude Opus 4.1\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -84,7 +84,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/mini-swe-agent__claude-opus-4.1/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/openhands__claude-opus-4.1/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -108,7 +108,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-11-03",
+          "evaluation_timestamp": "2025-11-02",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -117,17 +117,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 35.1,
+            "score": 36.9,
             "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 \"Mini-SWE-Agent\" -m \"Claude Opus 4.1\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"OpenHands\" -m \"Claude Opus 4.1\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -144,7 +144,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Mini-SWE-Agent\" -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": [
               {
@@ -232,7 +232,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/openhands__claude-opus-4.1/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/claude-code__claude-opus-4.1/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -256,7 +256,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-11-02",
+          "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": 36.9,
+            "score": 34.8,
             "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 \"OpenHands\" -m \"Claude Opus 4.1\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Claude Code\" -m \"Claude Opus 4.1\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -292,7 +292,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"OpenHands\" -m \"Claude Opus 4.1\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Claude Code\" -m \"Claude Opus 4.1\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
diff --git a/data/models/anthropic_claude-opus-4.5.json b/data/models/anthropic_claude-opus-4.5.json
index 04c518e21852763638180858614bb6ac2be608de..09776a3455f602e0127758380687247631f384a0 100644
--- a/data/models/anthropic_claude-opus-4.5.json
+++ b/data/models/anthropic_claude-opus-4.5.json
@@ -4,13 +4,13 @@
     "id": "anthropic/claude-opus-4.5",
     "developer": "Anthropic",
     "additional_details": {
-      "agent_name": "OpenCode",
-      "agent_organization": "Anomaly Innovations"
+      "agent_name": "Mux",
+      "agent_organization": "Coder"
     }
   },
   "evaluations": [
     {
-      "evaluation_id": "terminal-bench-2.0/opencode__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",
@@ -34,7 +34,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2026-01-12",
+          "evaluation_timestamp": "2026-01-17",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -43,11 +43,11 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 51.7
+            "score": 58.4
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"OpenCode\" -m \"Claude Opus 4.5\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Mux\" -m \"Claude Opus 4.5\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -64,7 +64,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"OpenCode\" -m \"Claude Opus 4.5\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Mux\" -m \"Claude Opus 4.5\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -78,7 +78,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/terminus-2__claude-opus-4.5/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/opencode__claude-opus-4.5/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -102,7 +102,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-11-22",
+          "evaluation_timestamp": "2026-01-12",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -111,17 +111,11 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 57.8,
-            "uncertainty": {
-              "standard_error": {
-                "value": 2.5
-              },
-              "num_samples": 435
-            }
+            "score": 51.7
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"Claude Opus 4.5\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"OpenCode\" -m \"Claude Opus 4.5\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -138,7 +132,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"Claude Opus 4.5\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"OpenCode\" -m \"Claude Opus 4.5\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -152,7 +146,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/mux__claude-opus-4.5/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/droid__claude-opus-4.5/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -176,7 +170,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2026-01-17",
+          "evaluation_timestamp": "2025-12-11",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -185,11 +179,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 58.4
+            "score": 63.1,
+            "uncertainty": {
+              "standard_error": {
+                "value": 2.7
+              },
+              "num_samples": 435
+            }
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Mux\" -m \"Claude Opus 4.5\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Droid\" -m \"Claude Opus 4.5\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -206,7 +206,7 @@
       "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 \"Droid\" -m \"Claude Opus 4.5\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -220,7 +220,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/letta-code__claude-opus-4.5/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/goose__claude-opus-4.5/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -244,7 +244,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-12-17",
+          "evaluation_timestamp": "2025-12-11",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -253,17 +253,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 59.1,
+            "score": 54.3,
             "uncertainty": {
               "standard_error": {
-                "value": 2.4
+                "value": 2.6
               },
               "num_samples": 435
             }
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Letta Code\" -m \"Claude Opus 4.5\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Goose\" -m \"Claude Opus 4.5\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -280,7 +280,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Letta Code\" -m \"Claude Opus 4.5\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Goose\" -m \"Claude Opus 4.5\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -294,7 +294,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/goose__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",
@@ -318,7 +318,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-12-11",
+          "evaluation_timestamp": "2025-11-22",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -327,17 +327,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 54.3,
+            "score": 57.8,
             "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 \"Goose\" -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": [
                   {
@@ -354,7 +354,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Goose\" -m \"Claude Opus 4.5\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"Claude Opus 4.5\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -368,7 +368,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/droid__claude-opus-4.5/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/claude-code__claude-opus-4.5/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -392,7 +392,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-12-11",
+          "evaluation_timestamp": "2025-12-18",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -401,17 +401,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 63.1,
+            "score": 52.1,
             "uncertainty": {
               "standard_error": {
-                "value": 2.7
+                "value": 2.5
               },
               "num_samples": 435
             }
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Droid\" -m \"Claude Opus 4.5\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Claude Code\" -m \"Claude Opus 4.5\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -428,7 +428,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Droid\" -m \"Claude Opus 4.5\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Claude Code\" -m \"Claude Opus 4.5\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -442,7 +442,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/claude-code__claude-opus-4.5/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/letta-code__claude-opus-4.5/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -466,7 +466,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-12-18",
+          "evaluation_timestamp": "2025-12-17",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -475,17 +475,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 52.1,
+            "score": 59.1,
             "uncertainty": {
               "standard_error": {
-                "value": 2.5
+                "value": 2.4
               },
               "num_samples": 435
             }
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Claude Code\" -m \"Claude Opus 4.5\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Letta Code\" -m \"Claude Opus 4.5\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -502,7 +502,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Claude Code\" -m \"Claude Opus 4.5\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Letta Code\" -m \"Claude Opus 4.5\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
diff --git a/data/models/anthropic_claude-opus-4.6.json b/data/models/anthropic_claude-opus-4.6.json
index a41a27dbfdbf4960b47a33e1930b531d6b54f85b..cfa834e822d48dbd1b3a3875068947d83a36cefa 100644
--- a/data/models/anthropic_claude-opus-4.6.json
+++ b/data/models/anthropic_claude-opus-4.6.json
@@ -84,7 +84,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/crux__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",
@@ -108,7 +108,7 @@
               "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,
@@ -117,11 +117,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 66.9
+            "score": 71.9,
+            "uncertainty": {
+              "standard_error": {
+                "value": 2.7
+              },
+              "num_samples": 435
+            }
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Crux\" -m \"Claude Opus 4.6\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"TongAgents\" -m \"Claude Opus 4.6\" -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 \"Crux\" -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": [
               {
@@ -226,7 +232,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/claude-code__claude-opus-4.6/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/crux__claude-opus-4.6/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -250,7 +256,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2026-02-07",
+          "evaluation_timestamp": "2026-02-23",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -259,17 +265,11 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 58.0,
-            "uncertainty": {
-              "standard_error": {
-                "value": 2.9
-              },
-              "num_samples": 435
-            }
+            "score": 66.9
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Claude Code\" -m \"Claude Opus 4.6\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Crux\" -m \"Claude Opus 4.6\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -286,7 +286,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Claude Code\" -m \"Claude Opus 4.6\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Crux\" -m \"Claude Opus 4.6\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -300,7 +300,7 @@
       }
     },
     {
-      "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",
@@ -324,7 +324,7 @@
               "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,
@@ -333,17 +333,17 @@
             "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": [
                   {
@@ -360,7 +360,7 @@
       "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": [
               {
@@ -374,7 +374,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/tongagents__claude-opus-4.6/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/terminus-kira__claude-opus-4.6/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -407,17 +407,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 71.9,
+            "score": 74.7,
             "uncertainty": {
               "standard_error": {
-                "value": 2.7
+                "value": 2.6
               },
               "num_samples": 435
             }
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"TongAgents\" -m \"Claude Opus 4.6\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus-KIRA\" -m \"Claude Opus 4.6\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -434,7 +434,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"TongAgents\" -m \"Claude Opus 4.6\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus-KIRA\" -m \"Claude Opus 4.6\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -448,7 +448,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/terminus-kira__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",
@@ -472,7 +472,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2026-02-22",
+          "evaluation_timestamp": "2026-02-06",
           "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": 74.7,
+            "score": 62.9,
             "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-KIRA\" -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": [
                   {
@@ -508,7 +508,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus-KIRA\" -m \"Claude Opus 4.6\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"Claude Opus 4.6\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
diff --git a/data/models/anthropic_claude-sonnet-4-20250514.json b/data/models/anthropic_claude-sonnet-4-20250514.json
index 17485295f0940239338e7d9ae5edbc1db77fa9eb..a43572d10d77d034b8cc0b4e9e80cb595c19f907 100644
--- a/data/models/anthropic_claude-sonnet-4-20250514.json
+++ b/data/models/anthropic_claude-sonnet-4-20250514.json
@@ -10,8 +10,8 @@
   },
   "evaluations": [
     {
-      "evaluation_id": "global-mmlu-lite/anthropic_claude-sonnet-4-20250514/1773936583.743359",
-      "retrieved_timestamp": "1773936583.743359",
+      "evaluation_id": "global-mmlu-lite/anthropic_claude-sonnet-4-20250514/1773936496.366405",
+      "retrieved_timestamp": "1773936496.366405",
       "source_metadata": {
         "source_name": "Global MMLU Lite Leaderboard",
         "source_type": "documentation",
@@ -525,8 +525,8 @@
       "generation_config": null
     },
     {
-      "evaluation_id": "global-mmlu-lite/anthropic_claude-sonnet-4-20250514/1773936496.366405",
-      "retrieved_timestamp": "1773936496.366405",
+      "evaluation_id": "global-mmlu-lite/anthropic_claude-sonnet-4-20250514/1773936583.743359",
+      "retrieved_timestamp": "1773936583.743359",
       "source_metadata": {
         "source_name": "Global MMLU Lite Leaderboard",
         "source_type": "documentation",
diff --git a/data/models/anthropic_claude-sonnet-4.5.json b/data/models/anthropic_claude-sonnet-4.5.json
index 53dd8e2195a24f3d530bf69beec973cc6e94f1f4..ec3107a4e456d4dbbeb4419bd2e927231666a677 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": "CAMEL-AI",
-      "agent_organization": "CAMEL-AI"
+      "agent_name": "Terminus 2",
+      "agent_organization": "Terminal Bench"
     }
   },
   "evaluations": [
     {
-      "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",
@@ -34,7 +34,7 @@
               "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,
@@ -43,17 +43,17 @@
             "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": [
                   {
@@ -70,7 +70,7 @@
       "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": [
               {
@@ -84,7 +84,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/terminus-2__claude-sonnet-4.5/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/camel-ai__claude-sonnet-4.5/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -108,7 +108,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-10-31",
+          "evaluation_timestamp": "2025-12-24",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -117,17 +117,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 42.8,
+            "score": 46.5,
             "uncertainty": {
               "standard_error": {
-                "value": 2.8
+                "value": 2.4
               },
               "num_samples": 435
             }
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"Claude Sonnet 4.5\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"CAMEL-AI\" -m \"Claude Sonnet 4.5\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -144,7 +144,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"Claude Sonnet 4.5\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"CAMEL-AI\" -m \"Claude Sonnet 4.5\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -232,7 +232,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/mini-swe-agent__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",
@@ -256,7 +256,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-11-03",
+          "evaluation_timestamp": "2026-01-04",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -265,17 +265,11 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 42.5,
-            "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 \"Mini-SWE-Agent\" -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": [
                   {
@@ -292,7 +286,7 @@
       "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 \"MAYA\" -m \"Claude Sonnet 4.5\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -306,7 +300,7 @@
       }
     },
     {
-      "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",
@@ -330,7 +324,7 @@
               "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,
@@ -339,11 +333,17 @@
             "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": [
                   {
@@ -360,7 +360,7 @@
       "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": [
               {
@@ -374,7 +374,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/goose__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",
@@ -398,7 +398,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-12-11",
+          "evaluation_timestamp": "2025-11-03",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -407,17 +407,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 43.1,
+            "score": 42.5,
             "uncertainty": {
               "standard_error": {
-                "value": 2.6
+                "value": 2.8
               },
               "num_samples": 435
             }
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Goose\" -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": [
                   {
@@ -434,7 +434,7 @@
       "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 \"Mini-SWE-Agent\" -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 611dbc409a44fd2eadd33b4e30a3048a3002308e..e194ce4efc974318b0bb01e7560254bdd047ab55 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": "bfloat16",
+      "precision": "float16",
       "architecture": "Qwen2ForCausalLM",
       "params_billions": "7.616"
     }
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5621
+            "score": 0.5718
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5489
+            "score": 0.5481
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2953
+            "score": 0.114
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.307
+            "score": 0.3062
           }
         },
         {
@@ -116,7 +116,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4021
+            "score": 0.4008
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3822
+            "score": 0.3813
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5718
+            "score": 0.5621
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5481
+            "score": 0.5489
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.114
+            "score": 0.2953
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3062
+            "score": 0.307
           }
         },
         {
@@ -246,7 +246,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4008
+            "score": 0.4021
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3813
+            "score": 0.3822
           }
         }
       ],
diff --git a/data/models/bunnycore_llama-3.2-3b-deep-test.json b/data/models/bunnycore_llama-3.2-3b-deep-test.json
index 05cbb770cffa010b799551a630bc7b1089a91900..c829321bc4e1b62229f276602c62e6f6bd9a3faf 100644
--- a/data/models/bunnycore_llama-3.2-3b-deep-test.json
+++ b/data/models/bunnycore_llama-3.2-3b-deep-test.json
@@ -5,9 +5,9 @@
     "developer": "bunnycore",
     "inference_platform": "unknown",
     "additional_details": {
-      "precision": "float16",
+      "precision": "bfloat16",
       "architecture": "LlamaForCausalLM",
-      "params_billions": "3.607"
+      "params_billions": "1.803"
     }
   },
   "evaluations": [
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4652
+            "score": 0.1775
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4531
+            "score": 0.295
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1284
+            "score": 0.0
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2643
+            "score": 0.2517
           }
         },
         {
@@ -116,7 +116,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3394
+            "score": 0.3647
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3152
+            "score": 0.1049
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1775
+            "score": 0.4652
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.295
+            "score": 0.4531
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0
+            "score": 0.1284
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2517
+            "score": 0.2643
           }
         },
         {
@@ -246,7 +246,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3647
+            "score": 0.3394
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1049
+            "score": 0.3152
           }
         }
       ],
diff --git a/data/models/cir-ams_btrm_qwen2_7b_0613.json b/data/models/cir-ams_btrm_qwen2_7b_0613.json
index 9fb827ce32fb32044e2247d7f86c70d1bc13d414..84a36ab2262aa5d4869e5d141d383b85699971f1 100644
--- a/data/models/cir-ams_btrm_qwen2_7b_0613.json
+++ b/data/models/cir-ams_btrm_qwen2_7b_0613.json
@@ -9,10 +9,10 @@
   },
   "evaluations": [
     {
-      "evaluation_id": "reward-bench-2/CIR-AMS_BTRM_Qwen2_7b_0613/1766412838.146816",
+      "evaluation_id": "reward-bench/CIR-AMS_BTRM_Qwen2_7b_0613/1766412838.146816",
       "retrieved_timestamp": "1766412838.146816",
       "source_metadata": {
-        "source_name": "RewardBench 2",
+        "source_name": "RewardBench",
         "source_type": "documentation",
         "source_organization_name": "Allen Institute for AI",
         "source_organization_url": "https://allenai.org",
@@ -31,127 +31,109 @@
         {
           "evaluation_name": "Score",
           "metric_config": {
-            "evaluation_description": "Overall RewardBench 2 Score (mean of all metrics)",
-            "lower_is_better": false,
-            "score_type": "continuous",
-            "min_score": 0.0,
-            "max_score": 1.0
-          },
-          "score_details": {
-            "score": 0.5736
-          },
-          "source_data": {
-            "dataset_name": "RewardBench 2",
-            "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
-          }
-        },
-        {
-          "evaluation_name": "Factuality",
-          "metric_config": {
-            "evaluation_description": "Factuality score - measures factual accuracy",
+            "evaluation_description": "Overall RewardBench Score",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5347
+            "score": 0.8172
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Precise IF",
+          "evaluation_name": "Chat",
           "metric_config": {
-            "evaluation_description": "Precise Instruction Following score",
+            "evaluation_description": "Chat accuracy - includes easy chat subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3563
+            "score": 0.9749
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Math",
+          "evaluation_name": "Chat Hard",
           "metric_config": {
-            "evaluation_description": "Math score - measures mathematical reasoning",
+            "evaluation_description": "Chat Hard accuracy - includes hard chat subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6066
+            "score": 0.5724
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
           "evaluation_name": "Safety",
           "metric_config": {
-            "evaluation_description": "Safety score - measures safety awareness",
+            "evaluation_description": "Safety accuracy - includes safety subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7178
+            "score": 0.9014
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Focus",
+          "evaluation_name": "Reasoning",
           "metric_config": {
-            "evaluation_description": "Focus score - measures response focus",
+            "evaluation_description": "Reasoning accuracy - includes code and math subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5737
+            "score": 0.8775
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Ties",
+          "evaluation_name": "Prior Sets (0.5 weight)",
           "metric_config": {
-            "evaluation_description": "Ties score - ability to identify tie cases",
+            "evaluation_description": "Prior Sets score (weighted 0.5) - includes test sets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6527
+            "score": 0.7029
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         }
       ],
@@ -159,10 +141,10 @@
       "generation_config": null
     },
     {
-      "evaluation_id": "reward-bench/CIR-AMS_BTRM_Qwen2_7b_0613/1766412838.146816",
+      "evaluation_id": "reward-bench-2/CIR-AMS_BTRM_Qwen2_7b_0613/1766412838.146816",
       "retrieved_timestamp": "1766412838.146816",
       "source_metadata": {
-        "source_name": "RewardBench",
+        "source_name": "RewardBench 2",
         "source_type": "documentation",
         "source_organization_name": "Allen Institute for AI",
         "source_organization_url": "https://allenai.org",
@@ -181,109 +163,127 @@
         {
           "evaluation_name": "Score",
           "metric_config": {
-            "evaluation_description": "Overall RewardBench Score",
+            "evaluation_description": "Overall RewardBench 2 Score (mean of all metrics)",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.8172
+            "score": 0.5736
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Chat",
+          "evaluation_name": "Factuality",
           "metric_config": {
-            "evaluation_description": "Chat accuracy - includes easy chat subsets",
+            "evaluation_description": "Factuality score - measures factual accuracy",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9749
+            "score": 0.5347
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Chat Hard",
+          "evaluation_name": "Precise IF",
           "metric_config": {
-            "evaluation_description": "Chat Hard accuracy - includes hard chat subsets",
+            "evaluation_description": "Precise Instruction Following score",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5724
+            "score": 0.3563
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
+          }
+        },
+        {
+          "evaluation_name": "Math",
+          "metric_config": {
+            "evaluation_description": "Math score - measures mathematical reasoning",
+            "lower_is_better": false,
+            "score_type": "continuous",
+            "min_score": 0.0,
+            "max_score": 1.0
+          },
+          "score_details": {
+            "score": 0.6066
+          },
+          "source_data": {
+            "dataset_name": "RewardBench 2",
+            "source_type": "hf_dataset",
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
           "evaluation_name": "Safety",
           "metric_config": {
-            "evaluation_description": "Safety accuracy - includes safety subsets",
+            "evaluation_description": "Safety score - measures safety awareness",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9014
+            "score": 0.7178
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Reasoning",
+          "evaluation_name": "Focus",
           "metric_config": {
-            "evaluation_description": "Reasoning accuracy - includes code and math subsets",
+            "evaluation_description": "Focus score - measures response focus",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.8775
+            "score": 0.5737
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Prior Sets (0.5 weight)",
+          "evaluation_name": "Ties",
           "metric_config": {
-            "evaluation_description": "Prior Sets score (weighted 0.5) - includes test sets",
+            "evaluation_description": "Ties score - ability to identify tie cases",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7029
+            "score": 0.6527
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         }
       ],
diff --git a/data/models/cognitivecomputations_dolphin-2.9.2-phi-3-medium-abliterated.json b/data/models/cognitivecomputations_dolphin-2.9.2-phi-3-medium-abliterated.json
index 9b7cc35f188c98dba3f0427de09e77d4b26cfc40..62d09c3db567da9932caf7141d7a1389c1aafea9 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": "float16",
+      "precision": "bfloat16",
       "architecture": "MistralForCausalLM",
       "params_billions": "13.96"
     }
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3613
+            "score": 0.4124
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6123
+            "score": 0.6383
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1239
+            "score": 0.182
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.328
+            "score": 0.3289
           }
         },
         {
@@ -116,7 +116,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4112
+            "score": 0.4349
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4494
+            "score": 0.4525
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4124
+            "score": 0.3613
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6383
+            "score": 0.6123
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.182
+            "score": 0.1239
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3289
+            "score": 0.328
           }
         },
         {
@@ -246,7 +246,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4349
+            "score": 0.4112
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4525
+            "score": 0.4494
           }
         }
       ],
diff --git a/data/models/cohere_command-a-03-2025.json b/data/models/cohere_command-a-03-2025.json
index aedaf4e5f944a400d87afc543fa422bde24be135..205f7c496ed81b612dd2b182b3cf2e9fd9ac9c54 100644
--- a/data/models/cohere_command-a-03-2025.json
+++ b/data/models/cohere_command-a-03-2025.json
@@ -10,8 +10,8 @@
   },
   "evaluations": [
     {
-      "evaluation_id": "global-mmlu-lite/cohere_command-a-03-2025/1773936496.366405",
-      "retrieved_timestamp": "1773936496.366405",
+      "evaluation_id": "global-mmlu-lite/cohere_command-a-03-2025/1773936583.743359",
+      "retrieved_timestamp": "1773936583.743359",
       "source_metadata": {
         "source_name": "Global MMLU Lite Leaderboard",
         "source_type": "documentation",
@@ -525,8 +525,8 @@
       "generation_config": null
     },
     {
-      "evaluation_id": "global-mmlu-lite/cohere_command-a-03-2025/1773936583.743359",
-      "retrieved_timestamp": "1773936583.743359",
+      "evaluation_id": "global-mmlu-lite/cohere_command-a-03-2025/1773936496.366405",
+      "retrieved_timestamp": "1773936496.366405",
       "source_metadata": {
         "source_name": "Global MMLU Lite Leaderboard",
         "source_type": "documentation",
diff --git a/data/models/daemontatox_aethertot.json b/data/models/daemontatox_aethertot.json
index 36cfe9d7e08d8778379976a94c061a705e069a23..b20831e7b0add6cd1b35d7cacb70896114ddccd2 100644
--- a/data/models/daemontatox_aethertot.json
+++ b/data/models/daemontatox_aethertot.json
@@ -5,7 +5,7 @@
     "developer": "Daemontatox",
     "inference_platform": "unknown",
     "additional_details": {
-      "precision": "float16",
+      "precision": "bfloat16",
       "architecture": "MllamaForConditionalGeneration",
       "params_billions": "10.67"
     }
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4398
+            "score": 0.4383
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5066
+            "score": 0.5034
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1488
+            "score": 0.1443
           }
         },
         {
@@ -116,7 +116,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4079
+            "score": 0.4052
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3804
+            "score": 0.3778
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4383
+            "score": 0.4398
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5034
+            "score": 0.5066
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1443
+            "score": 0.1488
           }
         },
         {
@@ -246,7 +246,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4052
+            "score": 0.4079
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3778
+            "score": 0.3804
           }
         }
       ],
diff --git a/data/models/daemontatox_documentcogito.json b/data/models/daemontatox_documentcogito.json
index 6383820e3f19a97d2a08bca3546e5cca52a154e3..157a2466b6d71022e4fcfd8ace48804c5b301a99 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": "float16",
+      "precision": "bfloat16",
       "architecture": "MllamaForConditionalGeneration",
       "params_billions": "10.67"
     }
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.777
+            "score": 0.5064
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5187
+            "score": 0.5112
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2198
+            "score": 0.1631
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2936
+            "score": 0.3163
           }
         },
         {
@@ -116,7 +116,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3911
+            "score": 0.3973
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3738
+            "score": 0.3802
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5064
+            "score": 0.777
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5112
+            "score": 0.5187
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1631
+            "score": 0.2198
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3163
+            "score": 0.2936
           }
         },
         {
@@ -246,7 +246,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3973
+            "score": 0.3911
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3802
+            "score": 0.3738
           }
         }
       ],
diff --git a/data/models/davielion_llama-3.2-1b-spin-iter0.json b/data/models/davielion_llama-3.2-1b-spin-iter0.json
index 849a1d52d59a5f16eab6aaa35f259f630d9dc175..2ea14b6e6da41d61b06880761473f45de63d9756 100644
--- a/data/models/davielion_llama-3.2-1b-spin-iter0.json
+++ b/data/models/davielion_llama-3.2-1b-spin-iter0.json
@@ -5,7 +5,7 @@
     "developer": "DavieLion",
     "inference_platform": "unknown",
     "additional_details": {
-      "precision": "bfloat16",
+      "precision": "float16",
       "architecture": "LlamaForCausalLM",
       "params_billions": "1.236"
     }
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1549
+            "score": 0.1507
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2937
+            "score": 0.293
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.006
+            "score": 0.0
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2576
+            "score": 0.2534
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1128
+            "score": 0.1125
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1507
+            "score": 0.1549
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.293
+            "score": 0.2937
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0
+            "score": 0.006
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2534
+            "score": 0.2576
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1125
+            "score": 0.1128
           }
         }
       ],
diff --git a/data/models/deepmount00_llama-3.1-8b-ita.json b/data/models/deepmount00_llama-3.1-8b-ita.json
index 1fef7ca0b3d471692e7379016093b45312ecc7df..be94466036e753700b8de72e15b468fc6edebdee 100644
--- a/data/models/deepmount00_llama-3.1-8b-ita.json
+++ b/data/models/deepmount00_llama-3.1-8b-ita.json
@@ -6,8 +6,8 @@
     "inference_platform": "unknown",
     "additional_details": {
       "precision": "bfloat16",
-      "architecture": "LlamaForCausalLM",
-      "params_billions": "8.03",
+      "architecture": "Unknown",
+      "params_billions": "0.0",
       "model_id_aliases": [
         "DeepMount00/Llama-3.1-8b-Ita"
       ]
@@ -15,7 +15,7 @@
   },
   "evaluations": [
     {
-      "evaluation_id": "hfopenllm_v2/DeepMount00_Llama-3.1-8b-ITA/1773936498.240187",
+      "evaluation_id": "hfopenllm_v2/DeepMount00_Llama-3.1-8b-Ita/1773936498.240187",
       "retrieved_timestamp": "1773936498.240187",
       "source_metadata": {
         "source_name": "HF Open LLM v2",
@@ -47,7 +47,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7917
+            "score": 0.5365
           }
         },
         {
@@ -65,7 +65,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5109
+            "score": 0.517
           }
         },
         {
@@ -83,7 +83,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1088
+            "score": 0.1707
           }
         },
         {
@@ -101,7 +101,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2878
+            "score": 0.3062
           }
         },
         {
@@ -119,7 +119,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4136
+            "score": 0.4487
           }
         },
         {
@@ -137,7 +137,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3876
+            "score": 0.396
           }
         }
       ],
@@ -145,7 +145,7 @@
       "generation_config": null
     },
     {
-      "evaluation_id": "hfopenllm_v2/DeepMount00_Llama-3.1-8b-Ita/1773936498.240187",
+      "evaluation_id": "hfopenllm_v2/DeepMount00_Llama-3.1-8b-ITA/1773936498.240187",
       "retrieved_timestamp": "1773936498.240187",
       "source_metadata": {
         "source_name": "HF Open LLM v2",
@@ -177,7 +177,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5365
+            "score": 0.7917
           }
         },
         {
@@ -195,7 +195,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.517
+            "score": 0.5109
           }
         },
         {
@@ -213,7 +213,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1707
+            "score": 0.1088
           }
         },
         {
@@ -231,7 +231,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3062
+            "score": 0.2878
           }
         },
         {
@@ -249,7 +249,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4487
+            "score": 0.4136
           }
         },
         {
@@ -267,7 +267,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.396
+            "score": 0.3876
           }
         }
       ],
diff --git a/data/models/epistemeai_fireball-meta-llama-3.1-8b-instruct-agent-0.003-128k-code-ds-auto.json b/data/models/epistemeai_fireball-meta-llama-3.1-8b-instruct-agent-0.003-128k-code-ds-auto.json
index 623bd9c2c8bfaa513dd516b6dc8551699ef2135b..34df651aabdc1d7685c9419a18517c0c9ee2b5a2 100644
--- a/data/models/epistemeai_fireball-meta-llama-3.1-8b-instruct-agent-0.003-128k-code-ds-auto.json
+++ b/data/models/epistemeai_fireball-meta-llama-3.1-8b-instruct-agent-0.003-128k-code-ds-auto.json
@@ -5,7 +5,7 @@
     "developer": "EpistemeAI",
     "inference_platform": "unknown",
     "additional_details": {
-      "precision": "bfloat16",
+      "precision": "float16",
       "architecture": "LlamaForCausalLM",
       "params_billions": "8.03"
     }
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7207
+            "score": 0.7305
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.461
+            "score": 0.4649
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1314
+            "score": 0.1397
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2701
+            "score": 0.2659
           }
         },
         {
@@ -116,7 +116,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3432
+            "score": 0.3209
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3354
+            "score": 0.348
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7305
+            "score": 0.7207
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4649
+            "score": 0.461
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1397
+            "score": 0.1314
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2659
+            "score": 0.2701
           }
         },
         {
@@ -246,7 +246,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3209
+            "score": 0.3432
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.348
+            "score": 0.3354
           }
         }
       ],
diff --git a/data/models/etherll_herplete-llm-llama-3.1-8b.json b/data/models/etherll_herplete-llm-llama-3.1-8b.json
index 1f50fb1261d1ec9c67c961ac513392f51c62e5ca..31e2291931d31d5d1deeb312e00cc5de025980fd 100644
--- a/data/models/etherll_herplete-llm-llama-3.1-8b.json
+++ b/data/models/etherll_herplete-llm-llama-3.1-8b.json
@@ -5,7 +5,7 @@
     "developer": "Etherll",
     "inference_platform": "unknown",
     "additional_details": {
-      "precision": "float16",
+      "precision": "bfloat16",
       "architecture": "LlamaForCausalLM",
       "params_billions": "8.03"
     }
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4672
+            "score": 0.6106
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5013
+            "score": 0.5347
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0279
+            "score": 0.1548
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2861
+            "score": 0.3146
           }
         },
         {
@@ -116,7 +116,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.386
+            "score": 0.3991
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3482
+            "score": 0.3752
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6106
+            "score": 0.4672
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5347
+            "score": 0.5013
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1548
+            "score": 0.0279
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3146
+            "score": 0.2861
           }
         },
         {
@@ -246,7 +246,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3991
+            "score": 0.386
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3752
+            "score": 0.3482
           }
         }
       ],
diff --git a/data/models/goekdeniz-guelmez_josie-7b-v6.0-step2000.json b/data/models/goekdeniz-guelmez_josie-7b-v6.0-step2000.json
index 4037d46b51c1d5f1b2d23453c409340e1c080518..37f82f81803012f4270da262872645abffc35b8f 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": "float16",
+      "precision": "bfloat16",
       "architecture": "Qwen2ForCausalLM",
       "params_billions": "7.616"
     }
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7598
+            "score": 0.7628
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5107
+            "score": 0.5098
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4237
+            "score": 0.0
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2768
+            "score": 0.2802
           }
         },
         {
@@ -116,7 +116,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4539
+            "score": 0.4579
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4012
+            "score": 0.4033
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7628
+            "score": 0.7598
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5098
+            "score": 0.5107
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0
+            "score": 0.4237
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2802
+            "score": 0.2768
           }
         },
         {
@@ -246,7 +246,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4579
+            "score": 0.4539
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4033
+            "score": 0.4012
           }
         }
       ],
diff --git a/data/models/goekdeniz-guelmez_josiefied-qwen2.5-0.5b-instruct-abliterated-v1.json b/data/models/goekdeniz-guelmez_josiefied-qwen2.5-0.5b-instruct-abliterated-v1.json
index 4e742d684d75a21064054d5a573ca557e7b1e590..57e8dc5e192d9afe5d8658b037afb0f25366b018 100644
--- a/data/models/goekdeniz-guelmez_josiefied-qwen2.5-0.5b-instruct-abliterated-v1.json
+++ b/data/models/goekdeniz-guelmez_josiefied-qwen2.5-0.5b-instruct-abliterated-v1.json
@@ -5,7 +5,7 @@
     "developer": "Goekdeniz-Guelmez",
     "inference_platform": "unknown",
     "additional_details": {
-      "precision": "bfloat16",
+      "precision": "float16",
       "architecture": "Qwen2ForCausalLM",
       "params_billions": "0.63"
     }
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3472
+            "score": 0.3417
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3268
+            "score": 0.3292
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0891
+            "score": 0.0023
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2517
+            "score": 0.2576
           }
         },
         {
@@ -116,7 +116,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3262
+            "score": 0.3249
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1641
+            "score": 0.1638
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3417
+            "score": 0.3472
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3292
+            "score": 0.3268
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0023
+            "score": 0.0891
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2576
+            "score": 0.2517
           }
         },
         {
@@ -246,7 +246,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3249
+            "score": 0.3262
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1638
+            "score": 0.1641
           }
         }
       ],
diff --git a/data/models/google_gemini-2.5-flash.json b/data/models/google_gemini-2.5-flash.json
index 820c8d9942dde2ebcfddb6efd01e86ba89a1eddf..95ba532548298d2f931d1f8d4f2b4d963221f666 100644
--- a/data/models/google_gemini-2.5-flash.json
+++ b/data/models/google_gemini-2.5-flash.json
@@ -1269,7 +1269,7 @@
       "generation_config": null
     },
     {
-      "evaluation_id": "terminal-bench-2.0/mini-swe-agent__gemini-2.5-flash/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/terminus-2__gemini-2.5-flash/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -1293,7 +1293,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-11-03",
+          "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": 17.1,
+            "score": 16.9,
             "uncertainty": {
               "standard_error": {
-                "value": 2.5
+                "value": 2.4
               },
               "num_samples": 435
             }
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Mini-SWE-Agent\" -m \"Gemini 2.5 Flash\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"Gemini 2.5 Flash\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -1329,7 +1329,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Mini-SWE-Agent\" -m \"Gemini 2.5 Flash\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"Gemini 2.5 Flash\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -1343,7 +1343,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/terminus-2__gemini-2.5-flash/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/openhands__gemini-2.5-flash/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -1367,7 +1367,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-10-31",
+          "evaluation_timestamp": "2025-11-02",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -1376,7 +1376,7 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 16.9,
+            "score": 16.4,
             "uncertainty": {
               "standard_error": {
                 "value": 2.4
@@ -1386,7 +1386,7 @@
           },
           "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 \"OpenHands\" -m \"Gemini 2.5 Flash\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -1403,7 +1403,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"Gemini 2.5 Flash\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"OpenHands\" -m \"Gemini 2.5 Flash\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -1417,7 +1417,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/openhands__gemini-2.5-flash/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/gemini-cli__gemini-2.5-flash/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -1441,7 +1441,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-11-02",
+          "evaluation_timestamp": "2025-11-04",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -1450,17 +1450,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 16.4,
+            "score": 15.4,
             "uncertainty": {
               "standard_error": {
-                "value": 2.4
+                "value": 2.3
               },
               "num_samples": 435
             }
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"OpenHands\" -m \"Gemini 2.5 Flash\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Gemini CLI\" -m \"Gemini 2.5 Flash\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -1477,7 +1477,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"OpenHands\" -m \"Gemini 2.5 Flash\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Gemini CLI\" -m \"Gemini 2.5 Flash\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -1491,7 +1491,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/gemini-cli__gemini-2.5-flash/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/mini-swe-agent__gemini-2.5-flash/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -1515,7 +1515,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-11-04",
+          "evaluation_timestamp": "2025-11-03",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -1524,17 +1524,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 15.4,
+            "score": 17.1,
             "uncertainty": {
               "standard_error": {
-                "value": 2.3
+                "value": 2.5
               },
               "num_samples": 435
             }
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Gemini CLI\" -m \"Gemini 2.5 Flash\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Mini-SWE-Agent\" -m \"Gemini 2.5 Flash\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -1551,7 +1551,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Gemini CLI\" -m \"Gemini 2.5 Flash\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Mini-SWE-Agent\" -m \"Gemini 2.5 Flash\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
diff --git a/data/models/google_gemini-2.5-pro.json b/data/models/google_gemini-2.5-pro.json
index ad69bc6f71351eff92acf181b72bb1ef3d2ca29a..64bf8e5b0bbd8066e28305bcfb70c0755706abd7 100644
--- a/data/models/google_gemini-2.5-pro.json
+++ b/data/models/google_gemini-2.5-pro.json
@@ -1269,7 +1269,7 @@
       "generation_config": null
     },
     {
-      "evaluation_id": "terminal-bench-2.0/terminus-2__gemini-2.5-pro/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/mini-swe-agent__gemini-2.5-pro/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -1293,7 +1293,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-10-31",
+          "evaluation_timestamp": "2025-11-03",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -1302,17 +1302,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 32.6,
+            "score": 26.1,
             "uncertainty": {
               "standard_error": {
-                "value": 3.0
+                "value": 2.5
               },
               "num_samples": 435
             }
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"Gemini 2.5 Pro\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Mini-SWE-Agent\" -m \"Gemini 2.5 Pro\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -1329,7 +1329,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"Gemini 2.5 Pro\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Mini-SWE-Agent\" -m \"Gemini 2.5 Pro\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -1343,7 +1343,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/mini-swe-agent__gemini-2.5-pro/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/gemini-cli__gemini-2.5-pro/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -1367,7 +1367,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-11-03",
+          "evaluation_timestamp": "2025-11-04",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -1376,17 +1376,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 26.1,
+            "score": 19.6,
             "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 \"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": [
                   {
@@ -1403,7 +1403,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Mini-SWE-Agent\" -m \"Gemini 2.5 Pro\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Gemini CLI\" -m \"Gemini 2.5 Pro\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -1417,7 +1417,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/gemini-cli__gemini-2.5-pro/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/terminus-2__gemini-2.5-pro/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -1441,7 +1441,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-11-04",
+          "evaluation_timestamp": "2025-10-31",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -1450,17 +1450,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 19.6,
+            "score": 32.6,
             "uncertainty": {
               "standard_error": {
-                "value": 2.9
+                "value": 3.0
               },
               "num_samples": 435
             }
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Gemini CLI\" -m \"Gemini 2.5 Pro\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"Gemini 2.5 Pro\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -1477,7 +1477,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Gemini CLI\" -m \"Gemini 2.5 Pro\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"Gemini 2.5 Pro\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
diff --git a/data/models/google_gemini-3-flash.json b/data/models/google_gemini-3-flash.json
index 47fa2df5c9baf77e090796d7a217aa9e4577803b..16cea45f1dff16269cebc97fb714914d5b11c007 100644
--- a/data/models/google_gemini-3-flash.json
+++ b/data/models/google_gemini-3-flash.json
@@ -4,13 +4,13 @@
     "id": "google/gemini-3-flash",
     "developer": "Google",
     "additional_details": {
-      "agent_name": "Terminus 2",
-      "agent_organization": "Terminal Bench"
+      "agent_name": "Gemini CLI",
+      "agent_organization": "Google"
     }
   },
   "evaluations": [
     {
-      "evaluation_id": "terminal-bench-2.0/terminus-2__gemini-3-flash/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/gemini-cli__gemini-3-flash/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -34,7 +34,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2026-01-07",
+          "evaluation_timestamp": "2025-12-23",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -43,17 +43,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 51.7,
+            "score": 51.0,
             "uncertainty": {
               "standard_error": {
-                "value": 3.1
+                "value": 3.0
               },
               "num_samples": 435
             }
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"Gemini 3 Flash\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Gemini CLI\" -m \"Gemini 3 Flash\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -70,7 +70,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"Gemini 3 Flash\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Gemini CLI\" -m \"Gemini 3 Flash\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -84,7 +84,7 @@
       }
     },
     {
-      "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",
@@ -108,7 +108,7 @@
               "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,
@@ -117,17 +117,17 @@
             "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": [
                   {
@@ -144,7 +144,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Junie CLI\" -m \"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": [
               {
@@ -232,7 +232,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/gemini-cli__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",
@@ -265,17 +265,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 51.0,
+            "score": 64.3,
             "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 \"Gemini CLI\" -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": [
                   {
@@ -292,7 +292,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Gemini CLI\" -m \"Gemini 3 Flash\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"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 003d3891c3ed687a312bcf65a5ce96e8186ce448..95e6d99eeb9c9c27b3f039c22763603c38516fd7 100644
--- a/data/models/google_gemini-3-pro-preview.json
+++ b/data/models/google_gemini-3-pro-preview.json
@@ -78,7 +78,7 @@
       }
     },
     {
-      "evaluation_id": "appworld/test_normal/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",
@@ -91,42 +91,42 @@
         "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": 0.582,
+            "score": 0.57,
             "uncertainty": {
               "num_samples": 100
             },
             "details": {
-              "average_agent_cost": "8.7",
-              "total_run_cost": "869.55",
-              "average_steps": "33.49",
-              "percent_finished": "0.98"
+              "average_agent_cost": "2.39",
+              "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"
                 }
               }
             }
@@ -138,15 +138,15 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "OpenAI Solo",
-              "agent_framework": "openai_solo"
+              "agent_name": "SmolAgents Code",
+              "agent_framework": "smolagents_code"
             }
           }
         }
       }
     },
     {
-      "evaluation_id": "browsecompplus/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",
@@ -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": 0.51,
+            "score": 0.55,
             "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": "1.3",
+              "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"
                 }
               }
             }
@@ -206,15 +206,15 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "Claude Code CLI",
-              "agent_framework": "claude_code"
+              "agent_name": "LiteLLM Tool Calling with Shortlisting",
+              "agent_framework": "tool_calling_with_shortlisting"
             }
           }
         }
       }
     },
     {
-      "evaluation_id": "appworld/test_normal/litellm-tool-calling-with-shortlisting__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",
@@ -227,42 +227,42 @@
         "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": 0.55,
+            "score": 0.51,
             "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": "2.85",
+              "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 with Shortlisting",
-                  "agent_framework": "tool_calling_with_shortlisting"
+                  "agent_name": "Claude Code CLI",
+                  "agent_framework": "claude_code"
                 }
               }
             }
@@ -274,15 +274,15 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "LiteLLM Tool Calling with Shortlisting",
-              "agent_framework": "tool_calling_with_shortlisting"
+              "agent_name": "Claude Code CLI",
+              "agent_framework": "claude_code"
             }
           }
         }
       }
     },
     {
-      "evaluation_id": "browsecompplus/smolagents-code__google_gemini-3-pro-preview/1774263615.0201504",
+      "evaluation_id": "appworld/test_normal/openai-solo__google_gemini-3-pro-preview/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -295,42 +295,42 @@
         "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": 0.57,
+            "score": 0.582,
             "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": "8.7",
+              "total_run_cost": "869.55",
+              "average_steps": "33.49",
+              "percent_finished": "0.98"
             }
           },
           "generation_config": {
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "SmolAgents Code",
-                  "agent_framework": "smolagents_code"
+                  "agent_name": "OpenAI Solo",
+                  "agent_framework": "openai_solo"
                 }
               }
             }
@@ -342,8 +342,8 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "SmolAgents Code",
-              "agent_framework": "smolagents_code"
+              "agent_name": "OpenAI Solo",
+              "agent_framework": "openai_solo"
             }
           }
         }
@@ -554,7 +554,7 @@
       }
     },
     {
-      "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",
@@ -601,8 +601,8 @@
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "LiteLLM Tool Calling with Shortlisting",
-                  "agent_framework": "tool_calling_with_shortlisting"
+                  "agent_name": "LiteLLM Tool Calling",
+                  "agent_framework": "tool_calling"
                 }
               }
             }
@@ -614,15 +614,15 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "LiteLLM Tool Calling with Shortlisting",
-              "agent_framework": "tool_calling_with_shortlisting"
+              "agent_name": "LiteLLM Tool Calling",
+              "agent_framework": "tool_calling"
             }
           }
         }
       }
     },
     {
-      "evaluation_id": "browsecompplus/litellm-tool-calling__google_gemini-3-pro-preview/1774263615.0201504",
+      "evaluation_id": "browsecompplus/litellm-tool-calling-with-shortlisting__google_gemini-3-pro-preview/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -669,8 +669,8 @@
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "LiteLLM Tool Calling",
-                  "agent_framework": "tool_calling"
+                  "agent_name": "LiteLLM Tool Calling with Shortlisting",
+                  "agent_framework": "tool_calling_with_shortlisting"
                 }
               }
             }
@@ -682,8 +682,8 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "LiteLLM Tool Calling",
-              "agent_framework": "tool_calling"
+              "agent_name": "LiteLLM Tool Calling with Shortlisting",
+              "agent_framework": "tool_calling_with_shortlisting"
             }
           }
         }
@@ -1720,7 +1720,7 @@
       "generation_config": null
     },
     {
-      "evaluation_id": "swe-bench/claude-code-cli__google_gemini-3-pro-preview/1774263615.0201504",
+      "evaluation_id": "swe-bench/smolagents-code__google_gemini-3-pro-preview/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -1752,14 +1752,14 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.67,
+            "score": 0.7576,
             "uncertainty": {
-              "num_samples": 100
+              "num_samples": 99
             },
             "details": {
-              "average_agent_cost": "3.68",
-              "total_run_cost": "367.97",
-              "average_steps": "43.72",
+              "average_agent_cost": "2.21",
+              "total_run_cost": "218.76",
+              "average_steps": "38.1",
               "percent_finished": "1.0"
             }
           },
@@ -1767,8 +1767,8 @@
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "Claude Code CLI",
-                  "agent_framework": "claude_code"
+                  "agent_name": "SmolAgents Code",
+                  "agent_framework": "smolagents_code"
                 }
               }
             }
@@ -1780,15 +1780,15 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "Claude Code CLI",
-              "agent_framework": "claude_code"
+              "agent_name": "SmolAgents Code",
+              "agent_framework": "smolagents_code"
             }
           }
         }
       }
     },
     {
-      "evaluation_id": "swe-bench/smolagents-code__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",
@@ -1820,14 +1820,14 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7576,
+            "score": 0.71,
             "uncertainty": {
-              "num_samples": 99
+              "num_samples": 100
             },
             "details": {
-              "average_agent_cost": "2.21",
-              "total_run_cost": "218.76",
-              "average_steps": "38.1",
+              "average_agent_cost": "0.7",
+              "total_run_cost": "69.56",
+              "average_steps": "32.55",
               "percent_finished": "1.0"
             }
           },
@@ -1835,8 +1835,8 @@
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "SmolAgents Code",
-                  "agent_framework": "smolagents_code"
+                  "agent_name": "LiteLLM Tool Calling",
+                  "agent_framework": "tool_calling"
                 }
               }
             }
@@ -1848,15 +1848,15 @@
         "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__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",
@@ -1903,8 +1903,8 @@
             "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"
                 }
               }
             }
@@ -1916,15 +1916,15 @@
         "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/claude-code-cli__google_gemini-3-pro-preview/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -1956,14 +1956,14 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.71,
+            "score": 0.67,
             "uncertainty": {
               "num_samples": 100
             },
             "details": {
-              "average_agent_cost": "0.7",
-              "total_run_cost": "69.56",
-              "average_steps": "32.55",
+              "average_agent_cost": "3.68",
+              "total_run_cost": "367.97",
+              "average_steps": "43.72",
               "percent_finished": "1.0"
             }
           },
@@ -1971,8 +1971,8 @@
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "LiteLLM Tool Calling with Shortlisting",
-                  "agent_framework": "tool_calling_with_shortlisting"
+                  "agent_name": "Claude Code CLI",
+                  "agent_framework": "claude_code"
                 }
               }
             }
@@ -1984,8 +1984,8 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "LiteLLM Tool Calling with Shortlisting",
-              "agent_framework": "tool_calling_with_shortlisting"
+              "agent_name": "Claude Code CLI",
+              "agent_framework": "claude_code"
             }
           }
         }
@@ -2060,7 +2060,7 @@
       }
     },
     {
-      "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",
@@ -2097,9 +2097,9 @@
               "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"
             }
           },
@@ -2107,8 +2107,8 @@
             "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"
                 }
               }
             }
@@ -2120,15 +2120,15 @@
         "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/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",
@@ -2160,14 +2160,14 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.62,
+            "score": 0.7,
             "uncertainty": {
               "num_samples": 50
             },
             "details": {
-              "average_agent_cost": "0.21",
-              "total_run_cost": "11.18",
-              "average_steps": "10.9",
+              "average_agent_cost": "0.16",
+              "total_run_cost": "8.48",
+              "average_steps": "10.14",
               "percent_finished": "1.0"
             }
           },
@@ -2175,8 +2175,8 @@
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "OpenAI Solo",
-                  "agent_framework": "openai_solo"
+                  "agent_name": "LiteLLM Tool Calling",
+                  "agent_framework": "tool_calling"
                 }
               }
             }
@@ -2188,15 +2188,15 @@
         "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/smolagents-code__google_gemini-3-pro-preview/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -2228,14 +2228,14 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7,
+            "score": 0.68,
             "uncertainty": {
               "num_samples": 50
             },
             "details": {
-              "average_agent_cost": "0.34",
-              "total_run_cost": "17.45",
-              "average_steps": "12.62",
+              "average_agent_cost": "0.2",
+              "total_run_cost": "10.29",
+              "average_steps": "12.28",
               "percent_finished": "1.0"
             }
           },
@@ -2243,8 +2243,8 @@
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "Claude Code CLI",
-                  "agent_framework": "claude_code"
+                  "agent_name": "SmolAgents Code",
+                  "agent_framework": "smolagents_code"
                 }
               }
             }
@@ -2256,8 +2256,8 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "Claude Code CLI",
-              "agent_framework": "claude_code"
+              "agent_name": "SmolAgents Code",
+              "agent_framework": "smolagents_code"
             }
           }
         }
@@ -2332,7 +2332,7 @@
       }
     },
     {
-      "evaluation_id": "tau-bench-2/airline/smolagents-code__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",
@@ -2364,14 +2364,14 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.68,
+            "score": 0.62,
             "uncertainty": {
               "num_samples": 50
             },
             "details": {
-              "average_agent_cost": "0.2",
-              "total_run_cost": "10.29",
-              "average_steps": "12.28",
+              "average_agent_cost": "0.21",
+              "total_run_cost": "11.18",
+              "average_steps": "10.9",
               "percent_finished": "1.0"
             }
           },
@@ -2379,8 +2379,8 @@
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "SmolAgents Code",
-                  "agent_framework": "smolagents_code"
+                  "agent_name": "OpenAI Solo",
+                  "agent_framework": "openai_solo"
                 }
               }
             }
@@ -2392,8 +2392,8 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "SmolAgents Code",
-              "agent_framework": "smolagents_code"
+              "agent_name": "OpenAI Solo",
+              "agent_framework": "openai_solo"
             }
           }
         }
@@ -2468,7 +2468,7 @@
       }
     },
     {
-      "evaluation_id": "tau-bench-2/retail/claude-code-cli__google_gemini-3-pro-preview/1774263615.0201504",
+      "evaluation_id": "tau-bench-2/retail/litellm-tool-calling-with-shortlisting__google_gemini-3-pro-preview/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -2500,14 +2500,14 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7805,
+            "score": 0.82,
             "uncertainty": {
               "num_samples": 100
             },
             "details": {
-              "average_agent_cost": "0.19",
-              "total_run_cost": "19.38",
-              "average_steps": "11.18",
+              "average_agent_cost": "0.16",
+              "total_run_cost": "16.64",
+              "average_steps": "11.25",
               "percent_finished": "1.0"
             }
           },
@@ -2515,8 +2515,8 @@
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "Claude Code CLI",
-                  "agent_framework": "claude_code"
+                  "agent_name": "LiteLLM Tool Calling with Shortlisting",
+                  "agent_framework": "tool_calling_with_shortlisting"
                 }
               }
             }
@@ -2528,15 +2528,15 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "Claude Code CLI",
-              "agent_framework": "claude_code"
+              "agent_name": "LiteLLM Tool Calling with Shortlisting",
+              "agent_framework": "tool_calling_with_shortlisting"
             }
           }
         }
       }
     },
     {
-      "evaluation_id": "tau-bench-2/retail/litellm-tool-calling-with-shortlisting__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",
@@ -2568,14 +2568,14 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.82,
+            "score": 0.7805,
             "uncertainty": {
               "num_samples": 100
             },
             "details": {
-              "average_agent_cost": "0.16",
-              "total_run_cost": "16.64",
-              "average_steps": "11.25",
+              "average_agent_cost": "0.19",
+              "total_run_cost": "19.38",
+              "average_steps": "11.18",
               "percent_finished": "1.0"
             }
           },
@@ -2583,8 +2583,8 @@
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "LiteLLM Tool Calling with Shortlisting",
-                  "agent_framework": "tool_calling_with_shortlisting"
+                  "agent_name": "Claude Code CLI",
+                  "agent_framework": "claude_code"
                 }
               }
             }
@@ -2596,15 +2596,15 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "LiteLLM Tool Calling with Shortlisting",
-              "agent_framework": "tool_calling_with_shortlisting"
+              "agent_name": "Claude Code CLI",
+              "agent_framework": "claude_code"
             }
           }
         }
       }
     },
     {
-      "evaluation_id": "tau-bench-2/retail/openai-solo__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",
@@ -2636,14 +2636,14 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.73,
+            "score": 0.82,
             "uncertainty": {
               "num_samples": 100
             },
             "details": {
-              "average_agent_cost": "0.27",
-              "total_run_cost": "27.48",
-              "average_steps": "10.62",
+              "average_agent_cost": "0.16",
+              "total_run_cost": "16.64",
+              "average_steps": "11.25",
               "percent_finished": "1.0"
             }
           },
@@ -2651,8 +2651,8 @@
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "OpenAI Solo",
-                  "agent_framework": "openai_solo"
+                  "agent_name": "LiteLLM Tool Calling",
+                  "agent_framework": "tool_calling"
                 }
               }
             }
@@ -2664,15 +2664,15 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "OpenAI Solo",
-              "agent_framework": "openai_solo"
+              "agent_name": "LiteLLM Tool Calling",
+              "agent_framework": "tool_calling"
             }
           }
         }
       }
     },
     {
-      "evaluation_id": "tau-bench-2/retail/litellm-tool-calling__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",
@@ -2704,14 +2704,14 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.82,
+            "score": 0.73,
             "uncertainty": {
               "num_samples": 100
             },
             "details": {
-              "average_agent_cost": "0.16",
-              "total_run_cost": "16.64",
-              "average_steps": "11.25",
+              "average_agent_cost": "0.27",
+              "total_run_cost": "27.48",
+              "average_steps": "10.62",
               "percent_finished": "1.0"
             }
           },
@@ -2719,8 +2719,8 @@
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "LiteLLM Tool Calling",
-                  "agent_framework": "tool_calling"
+                  "agent_name": "OpenAI Solo",
+                  "agent_framework": "openai_solo"
                 }
               }
             }
@@ -2732,15 +2732,15 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "LiteLLM Tool Calling",
-              "agent_framework": "tool_calling"
+              "agent_name": "OpenAI Solo",
+              "agent_framework": "openai_solo"
             }
           }
         }
       }
     },
     {
-      "evaluation_id": "tau-bench-2/telecom/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",
@@ -2772,14 +2772,14 @@
             "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"
             }
           },
@@ -2787,8 +2787,8 @@
             "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"
                 }
               }
             }
@@ -2800,15 +2800,15 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "LiteLLM Tool Calling with Shortlisting",
-              "agent_framework": "tool_calling_with_shortlisting"
+              "agent_name": "SmolAgents Code",
+              "agent_framework": "smolagents_code"
             }
           }
         }
       }
     },
     {
-      "evaluation_id": "tau-bench-2/telecom/openai-solo__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",
@@ -2840,23 +2840,23 @@
             "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"
                 }
               }
             }
@@ -2868,15 +2868,15 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "OpenAI Solo",
-              "agent_framework": "openai_solo"
+              "agent_name": "LiteLLM Tool Calling with Shortlisting",
+              "agent_framework": "tool_calling_with_shortlisting"
             }
           }
         }
       }
     },
     {
-      "evaluation_id": "tau-bench-2/telecom/claude-code-cli__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",
@@ -2908,23 +2908,23 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6852,
+            "score": 0.8876,
             "uncertainty": {
               "num_samples": 100
             },
             "details": {
-              "average_agent_cost": "0.21",
-              "total_run_cost": "25.48",
-              "average_steps": "9.9",
-              "percent_finished": "1.0"
+              "average_agent_cost": "0.54",
+              "total_run_cost": "58.29",
+              "average_steps": "10.82",
+              "percent_finished": "0.89"
             }
           },
           "generation_config": {
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "Claude Code CLI",
-                  "agent_framework": "claude_code"
+                  "agent_name": "OpenAI Solo",
+                  "agent_framework": "openai_solo"
                 }
               }
             }
@@ -2936,15 +2936,15 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "Claude Code CLI",
-              "agent_framework": "claude_code"
+              "agent_name": "OpenAI Solo",
+              "agent_framework": "openai_solo"
             }
           }
         }
       }
     },
     {
-      "evaluation_id": "tau-bench-2/telecom/smolagents-code__google_gemini-3-pro-preview/1774263615.0201504",
+      "evaluation_id": "tau-bench-2/telecom/litellm-tool-calling__google_gemini-3-pro-preview/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -2976,14 +2976,14 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.88,
+            "score": 0.73,
             "uncertainty": {
               "num_samples": 100
             },
             "details": {
-              "average_agent_cost": "0.35",
-              "total_run_cost": "40.25",
-              "average_steps": "12.71",
+              "average_agent_cost": "0.3",
+              "total_run_cost": "36.75",
+              "average_steps": "14.84",
               "percent_finished": "1.0"
             }
           },
@@ -2991,8 +2991,8 @@
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "SmolAgents Code",
-                  "agent_framework": "smolagents_code"
+                  "agent_name": "LiteLLM Tool Calling",
+                  "agent_framework": "tool_calling"
                 }
               }
             }
@@ -3004,15 +3004,15 @@
         "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/litellm-tool-calling__google_gemini-3-pro-preview/1774263615.0201504",
+      "evaluation_id": "tau-bench-2/telecom/claude-code-cli__google_gemini-3-pro-preview/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -3044,14 +3044,14 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.73,
+            "score": 0.6852,
             "uncertainty": {
               "num_samples": 100
             },
             "details": {
-              "average_agent_cost": "0.3",
-              "total_run_cost": "36.75",
-              "average_steps": "14.84",
+              "average_agent_cost": "0.21",
+              "total_run_cost": "25.48",
+              "average_steps": "9.9",
               "percent_finished": "1.0"
             }
           },
@@ -3059,8 +3059,8 @@
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "LiteLLM Tool Calling",
-                  "agent_framework": "tool_calling"
+                  "agent_name": "Claude Code CLI",
+                  "agent_framework": "claude_code"
                 }
               }
             }
@@ -3072,8 +3072,8 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "LiteLLM Tool Calling",
-              "agent_framework": "tool_calling"
+              "agent_name": "Claude Code CLI",
+              "agent_framework": "claude_code"
             }
           }
         }
diff --git a/data/models/google_gemini-3-pro.json b/data/models/google_gemini-3-pro.json
index 11bc2c604594dba4ea7261f6d2e8fc51b386c982..227708133a9fa942407fc14b35830ec5101b4955 100644
--- a/data/models/google_gemini-3-pro.json
+++ b/data/models/google_gemini-3-pro.json
@@ -84,7 +84,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/droid__gemini-3-pro/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/letta-code__gemini-3-pro/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -108,7 +108,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-12-24",
+          "evaluation_timestamp": "2025-12-17",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -117,17 +117,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 61.1,
+            "score": 56.0,
             "uncertainty": {
               "standard_error": {
-                "value": 2.8
+                "value": 3.0
               },
               "num_samples": 435
             }
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Droid\" -m \"Gemini 3 Pro\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Letta Code\" -m \"Gemini 3 Pro\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -144,7 +144,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Droid\" -m \"Gemini 3 Pro\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Letta Code\" -m \"Gemini 3 Pro\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -158,7 +158,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/letta-code__gemini-3-pro/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/terminus-2__gemini-3-pro/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -182,7 +182,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-12-17",
+          "evaluation_timestamp": "2025-11-21",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -191,17 +191,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 56.0,
+            "score": 56.9,
             "uncertainty": {
               "standard_error": {
-                "value": 3.0
+                "value": 2.5
               },
               "num_samples": 435
             }
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Letta Code\" -m \"Gemini 3 Pro\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"Gemini 3 Pro\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -218,7 +218,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Letta Code\" -m \"Gemini 3 Pro\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"Gemini 3 Pro\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -232,7 +232,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/ante__gemini-3-pro/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/codebrain-1__gemini-3-pro/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -256,7 +256,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2026-01-06",
+          "evaluation_timestamp": "2026-02-05",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -265,17 +265,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 69.4,
+            "score": 62.2,
             "uncertainty": {
               "standard_error": {
-                "value": 2.1
+                "value": 2.6
               },
               "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 \"CodeBrain-1\" -m \"Gemini 3 Pro\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -292,7 +292,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Ante\" -m \"Gemini 3 Pro\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"CodeBrain-1\" -m \"Gemini 3 Pro\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -306,7 +306,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/ii-agent__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",
@@ -330,7 +330,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-12-23",
+          "evaluation_timestamp": "2025-12-24",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -339,7 +339,7 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 61.8,
+            "score": 61.1,
             "uncertainty": {
               "standard_error": {
                 "value": 2.8
@@ -349,7 +349,7 @@
           },
           "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 \"Droid\" -m \"Gemini 3 Pro\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -366,7 +366,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"II-Agent\" -m \"Gemini 3 Pro\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Droid\" -m \"Gemini 3 Pro\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -380,7 +380,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/terminus-2__gemini-3-pro/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/ante__gemini-3-pro/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -404,7 +404,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-11-21",
+          "evaluation_timestamp": "2026-01-06",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -413,17 +413,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 56.9,
+            "score": 69.4,
             "uncertainty": {
               "standard_error": {
-                "value": 2.5
+                "value": 2.1
               },
               "num_samples": 435
             }
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"Gemini 3 Pro\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Ante\" -m \"Gemini 3 Pro\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -440,7 +440,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"Gemini 3 Pro\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Ante\" -m \"Gemini 3 Pro\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -454,7 +454,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/codebrain-1__gemini-3-pro/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/ii-agent__gemini-3-pro/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -478,7 +478,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2026-02-05",
+          "evaluation_timestamp": "2025-12-23",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -487,17 +487,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 62.2,
+            "score": 61.8,
             "uncertainty": {
               "standard_error": {
-                "value": 2.6
+                "value": 2.8
               },
               "num_samples": 435
             }
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"CodeBrain-1\" -m \"Gemini 3 Pro\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"II-Agent\" -m \"Gemini 3 Pro\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -514,7 +514,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"CodeBrain-1\" -m \"Gemini 3 Pro\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"II-Agent\" -m \"Gemini 3 Pro\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
diff --git a/data/models/google_gemini-3.1-pro.json b/data/models/google_gemini-3.1-pro.json
index ecc327e910f8e4125f6002db506fbf114eb7832a..d5a56163d0a60a102dbdbef6cd39c4565d8d4e26 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": "Forge Code",
-      "agent_organization": "Forge Code"
+      "agent_name": "Terminus-KIRA",
+      "agent_organization": "KRAFTON AI"
     }
   },
   "evaluations": [
     {
-      "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",
@@ -34,7 +34,7 @@
               "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,
@@ -43,17 +43,17 @@
             "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": [
                   {
@@ -70,7 +70,7 @@
       "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": [
               {
@@ -84,7 +84,7 @@
       }
     },
     {
-      "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",
@@ -108,7 +108,7 @@
               "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,
@@ -117,17 +117,17 @@
             "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": [
                   {
@@ -144,7 +144,7 @@
       "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": [
               {
diff --git a/data/models/google_gemini_3_pro.json b/data/models/google_gemini_3_pro.json
index 104ce8e17e340df7c6fe6dc4bc1f7866f9c1cc71..8f4f634348fdc10ff492053d2a6241085b80ddd7 100644
--- a/data/models/google_gemini_3_pro.json
+++ b/data/models/google_gemini_3_pro.json
@@ -6,6 +6,78 @@
     "inference_platform": "unknown"
   },
   "evaluations": [
+    {
+      "evaluation_id": "ace/google_gemini-3-pro/1773260200",
+      "retrieved_timestamp": "1773260200",
+      "source_metadata": {
+        "source_name": "Mercor ACE Leaderboard",
+        "source_type": "evaluation_run",
+        "source_organization_name": "Mercor",
+        "source_organization_url": "https://www.mercor.com",
+        "evaluator_relationship": "first_party"
+      },
+      "eval_library": {
+        "name": "archipelago",
+        "version": "1.0.0"
+      },
+      "benchmark": "ace",
+      "evaluation_results": [
+        {
+          "evaluation_name": "Overall Score",
+          "source_data": {
+            "dataset_name": "ace",
+            "source_type": "hf_dataset",
+            "hf_repo": "Mercor/ACE"
+          },
+          "metric_config": {
+            "evaluation_description": "Overall ACE score (paper snapshot, approximate).",
+            "lower_is_better": false,
+            "score_type": "continuous",
+            "min_score": 0,
+            "max_score": 1
+          },
+          "score_details": {
+            "score": 0.47
+          },
+          "generation_config": {
+            "additional_details": {
+              "run_setting": "High",
+              "value_quality": "approximate"
+            }
+          }
+        },
+        {
+          "evaluation_name": "Gaming Score",
+          "source_data": {
+            "dataset_name": "ace",
+            "source_type": "hf_dataset",
+            "hf_repo": "Mercor/ACE"
+          },
+          "metric_config": {
+            "evaluation_description": "Gaming domain score.",
+            "lower_is_better": false,
+            "score_type": "continuous",
+            "min_score": 0,
+            "max_score": 1
+          },
+          "score_details": {
+            "score": 0.509
+          },
+          "generation_config": {
+            "additional_details": {
+              "run_setting": "High"
+            }
+          }
+        }
+      ],
+      "detailed_evaluation_results": null,
+      "generation_config": {
+        "additional_details": {
+          "run_setting": "High",
+          "value_quality": "approximate"
+        }
+      }
+    },
     {
       "evaluation_id": "apex-agents/google_gemini-3-pro/1773260200",
       "retrieved_timestamp": "1773260200",
@@ -205,78 +277,6 @@
         }
       }
     },
-    {
-      "evaluation_id": "ace/google_gemini-3-pro/1773260200",
-      "retrieved_timestamp": "1773260200",
-      "source_metadata": {
-        "source_name": "Mercor ACE Leaderboard",
-        "source_type": "evaluation_run",
-        "source_organization_name": "Mercor",
-        "source_organization_url": "https://www.mercor.com",
-        "evaluator_relationship": "first_party"
-      },
-      "eval_library": {
-        "name": "archipelago",
-        "version": "1.0.0"
-      },
-      "benchmark": "ace",
-      "evaluation_results": [
-        {
-          "evaluation_name": "Overall Score",
-          "source_data": {
-            "dataset_name": "ace",
-            "source_type": "hf_dataset",
-            "hf_repo": "Mercor/ACE"
-          },
-          "metric_config": {
-            "evaluation_description": "Overall ACE score (paper snapshot, approximate).",
-            "lower_is_better": false,
-            "score_type": "continuous",
-            "min_score": 0,
-            "max_score": 1
-          },
-          "score_details": {
-            "score": 0.47
-          },
-          "generation_config": {
-            "additional_details": {
-              "run_setting": "High",
-              "value_quality": "approximate"
-            }
-          }
-        },
-        {
-          "evaluation_name": "Gaming Score",
-          "source_data": {
-            "dataset_name": "ace",
-            "source_type": "hf_dataset",
-            "hf_repo": "Mercor/ACE"
-          },
-          "metric_config": {
-            "evaluation_description": "Gaming domain score.",
-            "lower_is_better": false,
-            "score_type": "continuous",
-            "min_score": 0,
-            "max_score": 1
-          },
-          "score_details": {
-            "score": 0.509
-          },
-          "generation_config": {
-            "additional_details": {
-              "run_setting": "High"
-            }
-          }
-        }
-      ],
-      "detailed_evaluation_results": null,
-      "generation_config": {
-        "additional_details": {
-          "run_setting": "High",
-          "value_quality": "approximate"
-        }
-      }
-    },
     {
       "evaluation_id": "apex-v1/google_gemini-3-pro/1773260200",
       "retrieved_timestamp": "1773260200",
diff --git a/data/models/google_gemma-2-2b.json b/data/models/google_gemma-2-2b.json
index 3875c2305ff98601b733940bab48bde956384743..853dbf9408f0d97b5b090784ef420b0479e50847 100644
--- a/data/models/google_gemma-2-2b.json
+++ b/data/models/google_gemma-2-2b.json
@@ -5,7 +5,7 @@
     "developer": "Google",
     "inference_platform": "unknown",
     "additional_details": {
-      "precision": "float16",
+      "precision": "bfloat16",
       "architecture": "InternLM2ForCausalLM",
       "params_billions": "2.614"
     }
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2018
+            "score": 0.1993
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3709
+            "score": 0.3656
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0302
+            "score": 0.0287
           }
         },
         {
@@ -116,7 +116,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4219
+            "score": 0.4232
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2217
+            "score": 0.218
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1993
+            "score": 0.2018
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3656
+            "score": 0.3709
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0287
+            "score": 0.0302
           }
         },
         {
@@ -246,7 +246,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4232
+            "score": 0.4219
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.218
+            "score": 0.2217
           }
         }
       ],
diff --git a/data/models/gunulhona_gemma-ko-merge-peft.json b/data/models/gunulhona_gemma-ko-merge-peft.json
index 7aaca8e76ac4d54a166ddba85afcaa38d76748c4..632db743d31cc31d893a565c873ea7be7cc73fb2 100644
--- a/data/models/gunulhona_gemma-ko-merge-peft.json
+++ b/data/models/gunulhona_gemma-ko-merge-peft.json
@@ -5,7 +5,7 @@
     "developer": "Gunulhona",
     "inference_platform": "unknown",
     "additional_details": {
-      "precision": "float16",
+      "precision": "bfloat16",
       "architecture": "?",
       "params_billions": "20.318"
     }
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4441
+            "score": 0.288
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4863
+            "score": 0.5154
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.307
+            "score": 0.3247
           }
         },
         {
@@ -116,7 +116,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3986
+            "score": 0.408
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3098
+            "score": 0.3817
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.288
+            "score": 0.4441
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5154
+            "score": 0.4863
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3247
+            "score": 0.307
           }
         },
         {
@@ -246,7 +246,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.408
+            "score": 0.3986
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3817
+            "score": 0.3098
           }
         }
       ],
diff --git a/data/models/huggingfacetb_smollm2-360m-instruct.json b/data/models/huggingfacetb_smollm2-360m-instruct.json
index b9a479d91c3b9226f2e42a0a5392df69dc01d9df..a4edda6b87f3cb7e0eeabaee9333bba91d019d12 100644
--- a/data/models/huggingfacetb_smollm2-360m-instruct.json
+++ b/data/models/huggingfacetb_smollm2-360m-instruct.json
@@ -5,9 +5,9 @@
     "developer": "HuggingFaceTB",
     "inference_platform": "unknown",
     "additional_details": {
-      "precision": "bfloat16",
+      "precision": "float16",
       "architecture": "LlamaForCausalLM",
-      "params_billions": "0.36"
+      "params_billions": "0.362"
     }
   },
   "evaluations": [
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3842
+            "score": 0.083
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3144
+            "score": 0.3053
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0151
+            "score": 0.0083
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.255
+            "score": 0.2651
           }
         },
         {
@@ -116,7 +116,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3461
+            "score": 0.3423
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1117
+            "score": 0.1126
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.083
+            "score": 0.3842
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3053
+            "score": 0.3144
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0083
+            "score": 0.0151
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2651
+            "score": 0.255
           }
         },
         {
@@ -246,7 +246,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3423
+            "score": 0.3461
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1126
+            "score": 0.1117
           }
         }
       ],
diff --git a/data/models/internlm_internlm2-1_8b-reward.json b/data/models/internlm_internlm2-1_8b-reward.json
index fdd95af043dae0ccf6943006b6d82bc9a69847ba..db02a96edd7d4deec66c9db68ed23c5ecfdc96f9 100644
--- a/data/models/internlm_internlm2-1_8b-reward.json
+++ b/data/models/internlm_internlm2-1_8b-reward.json
@@ -9,10 +9,10 @@
   },
   "evaluations": [
     {
-      "evaluation_id": "reward-bench-2/internlm_internlm2-1_8b-reward/1766412838.146816",
+      "evaluation_id": "reward-bench/internlm_internlm2-1_8b-reward/1766412838.146816",
       "retrieved_timestamp": "1766412838.146816",
       "source_metadata": {
-        "source_name": "RewardBench 2",
+        "source_name": "RewardBench",
         "source_type": "documentation",
         "source_organization_name": "Allen Institute for AI",
         "source_organization_url": "https://allenai.org",
@@ -31,104 +31,128 @@
         {
           "evaluation_name": "Score",
           "metric_config": {
-            "evaluation_description": "Overall RewardBench 2 Score (mean of all metrics)",
+            "evaluation_description": "Overall RewardBench Score",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3902
+            "score": 0.8217
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Factuality",
+          "evaluation_name": "Chat",
           "metric_config": {
-            "evaluation_description": "Factuality score - measures factual accuracy",
+            "evaluation_description": "Chat accuracy - includes easy chat subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2758
+            "score": 0.9358
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Precise IF",
+          "evaluation_name": "Chat Hard",
           "metric_config": {
-            "evaluation_description": "Precise Instruction Following score",
+            "evaluation_description": "Chat Hard accuracy - includes hard chat subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3625
+            "score": 0.6623
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Math",
+          "evaluation_name": "Safety",
           "metric_config": {
-            "evaluation_description": "Math score - measures mathematical reasoning",
+            "evaluation_description": "Safety accuracy - includes safety subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4426
+            "score": 0.8162
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Safety",
+          "evaluation_name": "Reasoning",
           "metric_config": {
-            "evaluation_description": "Safety score - measures safety awareness",
+            "evaluation_description": "Reasoning accuracy - includes code and math subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4711
+            "score": 0.8724
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
-        },
+        }
+      ],
+      "detailed_evaluation_results": null,
+      "generation_config": null
+    },
+    {
+      "evaluation_id": "reward-bench-2/internlm_internlm2-1_8b-reward/1766412838.146816",
+      "retrieved_timestamp": "1766412838.146816",
+      "source_metadata": {
+        "source_name": "RewardBench 2",
+        "source_type": "documentation",
+        "source_organization_name": "Allen Institute for AI",
+        "source_organization_url": "https://allenai.org",
+        "evaluator_relationship": "third_party"
+      },
+      "eval_library": {
+        "name": "rewardbench",
+        "version": "0.1.3",
+        "additional_details": {
+          "subsets": "Chat, Chat Hard, Safety, Reasoning",
+          "hf_space": "allenai/reward-bench"
+        }
+      },
+      "benchmark": "reward-bench",
+      "evaluation_results": [
         {
-          "evaluation_name": "Focus",
+          "evaluation_name": "Score",
           "metric_config": {
-            "evaluation_description": "Focus score - measures response focus",
+            "evaluation_description": "Overall RewardBench 2 Score (mean of all metrics)",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.596
+            "score": 0.3902
           },
           "source_data": {
             "dataset_name": "RewardBench 2",
@@ -137,135 +161,111 @@
           }
         },
         {
-          "evaluation_name": "Ties",
+          "evaluation_name": "Factuality",
           "metric_config": {
-            "evaluation_description": "Ties score - ability to identify tie cases",
+            "evaluation_description": "Factuality score - measures factual accuracy",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1934
+            "score": 0.2758
           },
           "source_data": {
             "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
             "hf_repo": "allenai/reward-bench-2-results"
           }
-        }
-      ],
-      "detailed_evaluation_results": null,
-      "generation_config": null
-    },
-    {
-      "evaluation_id": "reward-bench/internlm_internlm2-1_8b-reward/1766412838.146816",
-      "retrieved_timestamp": "1766412838.146816",
-      "source_metadata": {
-        "source_name": "RewardBench",
-        "source_type": "documentation",
-        "source_organization_name": "Allen Institute for AI",
-        "source_organization_url": "https://allenai.org",
-        "evaluator_relationship": "third_party"
-      },
-      "eval_library": {
-        "name": "rewardbench",
-        "version": "0.1.3",
-        "additional_details": {
-          "subsets": "Chat, Chat Hard, Safety, Reasoning",
-          "hf_space": "allenai/reward-bench"
-        }
-      },
-      "benchmark": "reward-bench",
-      "evaluation_results": [
+        },
         {
-          "evaluation_name": "Score",
+          "evaluation_name": "Precise IF",
           "metric_config": {
-            "evaluation_description": "Overall RewardBench Score",
+            "evaluation_description": "Precise Instruction Following score",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.8217
+            "score": 0.3625
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Chat",
+          "evaluation_name": "Math",
           "metric_config": {
-            "evaluation_description": "Chat accuracy - includes easy chat subsets",
+            "evaluation_description": "Math score - measures mathematical reasoning",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9358
+            "score": 0.4426
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Chat Hard",
+          "evaluation_name": "Safety",
           "metric_config": {
-            "evaluation_description": "Chat Hard accuracy - includes hard chat subsets",
+            "evaluation_description": "Safety score - measures safety awareness",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6623
+            "score": 0.4711
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Safety",
+          "evaluation_name": "Focus",
           "metric_config": {
-            "evaluation_description": "Safety accuracy - includes safety subsets",
+            "evaluation_description": "Focus score - measures response focus",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.8162
+            "score": 0.596
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Reasoning",
+          "evaluation_name": "Ties",
           "metric_config": {
-            "evaluation_description": "Reasoning accuracy - includes code and math subsets",
+            "evaluation_description": "Ties score - ability to identify tie cases",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.8724
+            "score": 0.1934
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         }
       ],
diff --git a/data/models/jaspionjader_kosmos-evaa-fusion-8b.json b/data/models/jaspionjader_kosmos-evaa-fusion-8b.json
index 1160e36435338576bea29bef2eb39f295798e22d..88cf241ec28671fc887627a1e7bb1af09c15f9cf 100644
--- a/data/models/jaspionjader_kosmos-evaa-fusion-8b.json
+++ b/data/models/jaspionjader_kosmos-evaa-fusion-8b.json
@@ -5,7 +5,7 @@
     "developer": "jaspionjader",
     "inference_platform": "unknown",
     "additional_details": {
-      "precision": "bfloat16",
+      "precision": "float16",
       "architecture": "LlamaForCausalLM",
       "params_billions": "8.03"
     }
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4345
+            "score": 0.4418
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5419
+            "score": 0.5406
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1292
+            "score": 0.1352
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3087
+            "score": 0.3062
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3854
+            "score": 0.386
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4418
+            "score": 0.4345
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5406
+            "score": 0.5419
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1352
+            "score": 0.1292
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3062
+            "score": 0.3087
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.386
+            "score": 0.3854
           }
         }
       ],
diff --git a/data/models/leroydyer_spydazweb_ai_humanai_012_instruct_xa.json b/data/models/leroydyer_spydazweb_ai_humanai_012_instruct_xa.json
index 199a2574ee197c6be6eb6b38849e4c63ab43b085..90656456ac84eb015314278cafdaa288005eb1ba 100644
--- a/data/models/leroydyer_spydazweb_ai_humanai_012_instruct_xa.json
+++ b/data/models/leroydyer_spydazweb_ai_humanai_012_instruct_xa.json
@@ -5,7 +5,7 @@
     "developer": "LeroyDyer",
     "inference_platform": "unknown",
     "additional_details": {
-      "precision": "float16",
+      "precision": "bfloat16",
       "architecture": "MistralForCausalLM",
       "params_billions": "7.242"
     }
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3798
+            "score": 0.3579
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4483
+            "score": 0.4477
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.04
+            "score": 0.0423
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3129
+            "score": 0.3096
           }
         },
         {
@@ -116,7 +116,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4148
+            "score": 0.4134
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2389
+            "score": 0.2376
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3579
+            "score": 0.3798
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4477
+            "score": 0.4483
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0423
+            "score": 0.04
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3096
+            "score": 0.3129
           }
         },
         {
@@ -246,7 +246,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4134
+            "score": 0.4148
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2376
+            "score": 0.2389
           }
         }
       ],
diff --git a/data/models/llmat_mistral-v0.3-7b-orpo.json b/data/models/llmat_mistral-v0.3-7b-orpo.json
index c2c9120f6bd010e2ff566effb35617377de554ee..3a1b947d84c5d76bb2423237a20cbf150415592e 100644
--- a/data/models/llmat_mistral-v0.3-7b-orpo.json
+++ b/data/models/llmat_mistral-v0.3-7b-orpo.json
@@ -5,7 +5,7 @@
     "developer": "llmat",
     "inference_platform": "unknown",
     "additional_details": {
-      "precision": "bfloat16",
+      "precision": "float16",
       "architecture": "MistralForCausalLM",
       "params_billions": "7.248"
     }
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.377
+            "score": 0.364
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3978
+            "score": 0.4005
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0242
+            "score": 0.0015
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2668
+            "score": 0.2693
           }
         },
         {
@@ -116,7 +116,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3555
+            "score": 0.3529
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2278
+            "score": 0.2301
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.364
+            "score": 0.377
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4005
+            "score": 0.3978
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0015
+            "score": 0.0242
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2693
+            "score": 0.2668
           }
         },
         {
@@ -246,7 +246,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3529
+            "score": 0.3555
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2301
+            "score": 0.2278
           }
         }
       ],
diff --git a/data/models/magpie-align_llama-3-8b-magpie-align-v0.1.json b/data/models/magpie-align_llama-3-8b-magpie-align-v0.1.json
index 018a3210e6da83ca7e6d3501fd6a7fefdb10449c..2ac3bb48cceaf59e0da754702b99c90edec98998 100644
--- a/data/models/magpie-align_llama-3-8b-magpie-align-v0.1.json
+++ b/data/models/magpie-align_llama-3-8b-magpie-align-v0.1.json
@@ -5,7 +5,7 @@
     "developer": "Magpie-Align",
     "inference_platform": "unknown",
     "additional_details": {
-      "precision": "bfloat16",
+      "precision": "float16",
       "architecture": "LlamaForCausalLM",
       "params_billions": "8.03"
     }
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4118
+            "score": 0.4027
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4811
+            "score": 0.4789
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.034
+            "score": 0.0461
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2752
+            "score": 0.2768
           }
         },
         {
@@ -116,7 +116,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3047
+            "score": 0.3087
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3006
+            "score": 0.3001
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4027
+            "score": 0.4118
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4789
+            "score": 0.4811
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0461
+            "score": 0.034
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2768
+            "score": 0.2752
           }
         },
         {
@@ -246,7 +246,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3087
+            "score": 0.3047
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3001
+            "score": 0.3006
           }
         }
       ],
diff --git a/data/models/meta-llama_meta-llama-3-8b-instruct.json b/data/models/meta-llama_meta-llama-3-8b-instruct.json
index 6b360a3e795c08b36f8a5ae66db62ef8475fd282..7f250b5cb54b80c03e9c7605296b8768c6176139 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": "float16",
+      "precision": "bfloat16",
       "architecture": "LlamaForCausalLM",
       "params_billions": "8.03"
     }
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4782
+            "score": 0.7408
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.491
+            "score": 0.4989
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0914
+            "score": 0.0869
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2928
+            "score": 0.2592
           }
         },
         {
@@ -116,7 +116,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3805
+            "score": 0.3568
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3591
+            "score": 0.3664
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7408
+            "score": 0.4782
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4989
+            "score": 0.491
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0869
+            "score": 0.0914
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2592
+            "score": 0.2928
           }
         },
         {
@@ -246,7 +246,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3568
+            "score": 0.3805
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3664
+            "score": 0.3591
           }
         }
       ],
diff --git a/data/models/microsoft_phi-3-mini-4k-instruct.json b/data/models/microsoft_phi-3-mini-4k-instruct.json
index 9787f21694f92686e734f02c35c722665943d7d4..f0214854e07bd3ad87162726609ad6d31e31396a 100644
--- a/data/models/microsoft_phi-3-mini-4k-instruct.json
+++ b/data/models/microsoft_phi-3-mini-4k-instruct.json
@@ -5,7 +5,7 @@
     "developer": "microsoft",
     "inference_platform": "unknown",
     "additional_details": {
-      "precision": "bfloat16",
+      "precision": "float16",
       "architecture": "Phi3ForCausalLM",
       "params_billions": "3.821"
     }
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5613
+            "score": 0.5477
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5676
+            "score": 0.5491
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1163
+            "score": 0.1639
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3196
+            "score": 0.3322
           }
         },
         {
@@ -116,7 +116,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.395
+            "score": 0.4284
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3866
+            "score": 0.4022
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5477
+            "score": 0.5613
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5491
+            "score": 0.5676
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1639
+            "score": 0.1163
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3322
+            "score": 0.3196
           }
         },
         {
@@ -246,7 +246,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4284
+            "score": 0.395
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4022
+            "score": 0.3866
           }
         }
       ],
diff --git a/data/models/minimax_minimax-m2.1.json b/data/models/minimax_minimax-m2.1.json
index 33905b0ffaa72b65b1d021a73faac651c1ebfecd..a5b957c9841bcbc5016fb37de174c988ce273877 100644
--- a/data/models/minimax_minimax-m2.1.json
+++ b/data/models/minimax_minimax-m2.1.json
@@ -4,13 +4,13 @@
     "id": "minimax/minimax-m2.1",
     "developer": "MiniMax",
     "additional_details": {
-      "agent_name": "Crux",
-      "agent_organization": "Roam"
+      "agent_name": "Terminus 2",
+      "agent_organization": "Terminal Bench"
     }
   },
   "evaluations": [
     {
-      "evaluation_id": "terminal-bench-2.0/crux__minimax-m2.1/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/terminus-2__minimax-m2.1/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -34,7 +34,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-12-22",
+          "evaluation_timestamp": "2025-12-23",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -43,7 +43,7 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 36.6,
+            "score": 29.2,
             "uncertainty": {
               "standard_error": {
                 "value": 2.9
@@ -53,7 +53,7 @@
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Crux\" -m \"MiniMax M2.1\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"MiniMax M2.1\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -70,7 +70,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Crux\" -m \"MiniMax M2.1\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"MiniMax M2.1\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -84,7 +84,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/terminus-2__minimax-m2.1/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/crux__minimax-m2.1/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -108,7 +108,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-12-23",
+          "evaluation_timestamp": "2025-12-22",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -117,7 +117,7 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 29.2,
+            "score": 36.6,
             "uncertainty": {
               "standard_error": {
                 "value": 2.9
@@ -127,7 +127,7 @@
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"MiniMax M2.1\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Crux\" -m \"MiniMax M2.1\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -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 \"MiniMax M2.1\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Crux\" -m \"MiniMax M2.1\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
diff --git a/data/models/mistralai_mistral-medium-3.json b/data/models/mistralai_mistral-medium-3.json
index 8c2cd1ffe5583f8e08ea6a503148c17defbde8f4..3d0755e0237b9760231fee380b173b29d57eab4a 100644
--- a/data/models/mistralai_mistral-medium-3.json
+++ b/data/models/mistralai_mistral-medium-3.json
@@ -10,8 +10,8 @@
   },
   "evaluations": [
     {
-      "evaluation_id": "global-mmlu-lite/mistralai_mistral-medium-3/1773936583.743359",
-      "retrieved_timestamp": "1773936583.743359",
+      "evaluation_id": "global-mmlu-lite/mistralai_mistral-medium-3/1773936496.366405",
+      "retrieved_timestamp": "1773936496.366405",
       "source_metadata": {
         "source_name": "Global MMLU Lite Leaderboard",
         "source_type": "documentation",
@@ -525,8 +525,8 @@
       "generation_config": null
     },
     {
-      "evaluation_id": "global-mmlu-lite/mistralai_mistral-medium-3/1773936496.366405",
-      "retrieved_timestamp": "1773936496.366405",
+      "evaluation_id": "global-mmlu-lite/mistralai_mistral-medium-3/1773936583.743359",
+      "retrieved_timestamp": "1773936583.743359",
       "source_metadata": {
         "source_name": "Global MMLU Lite Leaderboard",
         "source_type": "documentation",
diff --git a/data/models/mistralai_mistral-small-2503.json b/data/models/mistralai_mistral-small-2503.json
index 6df0d972b005ae32b060fdc4673d6092e770670f..be5d73de7278abb3c747dbebd44b60d3fa624503 100644
--- a/data/models/mistralai_mistral-small-2503.json
+++ b/data/models/mistralai_mistral-small-2503.json
@@ -10,8 +10,8 @@
   },
   "evaluations": [
     {
-      "evaluation_id": "global-mmlu-lite/mistralai_mistral-small-2503/1773936583.743359",
-      "retrieved_timestamp": "1773936583.743359",
+      "evaluation_id": "global-mmlu-lite/mistralai_mistral-small-2503/1773936496.366405",
+      "retrieved_timestamp": "1773936496.366405",
       "source_metadata": {
         "source_name": "Global MMLU Lite Leaderboard",
         "source_type": "documentation",
@@ -525,8 +525,8 @@
       "generation_config": null
     },
     {
-      "evaluation_id": "global-mmlu-lite/mistralai_mistral-small-2503/1773936496.366405",
-      "retrieved_timestamp": "1773936496.366405",
+      "evaluation_id": "global-mmlu-lite/mistralai_mistral-small-2503/1773936583.743359",
+      "retrieved_timestamp": "1773936583.743359",
       "source_metadata": {
         "source_name": "Global MMLU Lite Leaderboard",
         "source_type": "documentation",
diff --git a/data/models/moonshot-ai_kimi-k2-instruct.json b/data/models/moonshot-ai_kimi-k2-instruct.json
index 758984500ae56b028445a56fb8562c74a90a3a8f..2cfded0145e5c6821159f45b392f6b86e15c7f49 100644
--- a/data/models/moonshot-ai_kimi-k2-instruct.json
+++ b/data/models/moonshot-ai_kimi-k2-instruct.json
@@ -4,13 +4,13 @@
     "id": "moonshot-ai/kimi-k2-instruct",
     "developer": "Moonshot AI",
     "additional_details": {
-      "agent_name": "OpenHands",
-      "agent_organization": "OpenHands"
+      "agent_name": "Terminus 2",
+      "agent_organization": "Terminal Bench"
     }
   },
   "evaluations": [
     {
-      "evaluation_id": "terminal-bench-2.0/openhands__kimi-k2-instruct/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/terminus-2__kimi-k2-instruct/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -34,7 +34,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-11-02",
+          "evaluation_timestamp": "2025-11-01",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -43,17 +43,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 26.7,
+            "score": 27.8,
             "uncertainty": {
               "standard_error": {
-                "value": 2.7
+                "value": 2.5
               },
               "num_samples": 435
             }
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"OpenHands\" -m \"Kimi K2 Instruct\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"Kimi K2 Instruct\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -70,7 +70,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"OpenHands\" -m \"Kimi K2 Instruct\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"Kimi K2 Instruct\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -84,7 +84,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/terminus-2__kimi-k2-instruct/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/openhands__kimi-k2-instruct/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -108,7 +108,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-11-01",
+          "evaluation_timestamp": "2025-11-02",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -117,17 +117,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 27.8,
+            "score": 26.7,
             "uncertainty": {
               "standard_error": {
-                "value": 2.5
+                "value": 2.7
               },
               "num_samples": 435
             }
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"Kimi K2 Instruct\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"OpenHands\" -m \"Kimi K2 Instruct\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -144,7 +144,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"Kimi K2 Instruct\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"OpenHands\" -m \"Kimi K2 Instruct\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
diff --git a/data/models/multiple_multiple.json b/data/models/multiple_multiple.json
index 45d5496f95937f9e2416eacde936df0b731a4892..fa0150e47673164e631d2fcaaf30ef2ab4f1a18b 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": "2025-11-20",
+          "evaluation_timestamp": "2025-11-11",
           "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": 59.1,
+            "score": 50.1,
             "uncertainty": {
               "standard_error": {
-                "value": 2.8
+                "value": 2.7
               },
               "num_samples": 435
             }
@@ -84,7 +84,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/junie-cli__multiple/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/abacus-ai-desktop__multiple/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -108,7 +108,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2026-03-07",
+          "evaluation_timestamp": "2025-12-11",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -117,17 +117,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 71.0,
+            "score": 58.4,
             "uncertainty": {
               "standard_error": {
-                "value": 2.9
+                "value": 2.8
               },
               "num_samples": 435
             }
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Junie CLI\" -m \"Multiple\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Abacus AI Desktop\" -m \"Multiple\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -144,7 +144,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Junie CLI\" -m \"Multiple\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Abacus AI Desktop\" -m \"Multiple\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -182,7 +182,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-11-11",
+          "evaluation_timestamp": "2025-11-20",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -191,10 +191,10 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 50.1,
+            "score": 59.1,
             "uncertainty": {
               "standard_error": {
-                "value": 2.7
+                "value": 2.8
               },
               "num_samples": 435
             }
@@ -232,7 +232,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/abacus-ai-desktop__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",
@@ -256,7 +256,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-12-11",
+          "evaluation_timestamp": "2026-03-07",
           "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": 58.4,
+            "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 \"Abacus AI Desktop\" -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": [
                   {
@@ -292,7 +292,7 @@
       "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 \"Junie CLI\" -m \"Multiple\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
diff --git a/data/models/nazimali_mistral-nemo-kurdish-instruct.json b/data/models/nazimali_mistral-nemo-kurdish-instruct.json
index bf12d1ac4ce4431e1cc4657892f1de48dd5df10b..7bcf436e7a29205a95d8b228b8e52bcfb9264e7a 100644
--- a/data/models/nazimali_mistral-nemo-kurdish-instruct.json
+++ b/data/models/nazimali_mistral-nemo-kurdish-instruct.json
@@ -5,7 +5,7 @@
     "developer": "nazimali",
     "inference_platform": "unknown",
     "additional_details": {
-      "precision": "float16",
+      "precision": "bfloat16",
       "architecture": "MistralForCausalLM",
       "params_billions": "12.248"
     }
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.486
+            "score": 0.4964
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4721
+            "score": 0.4699
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0846
+            "score": 0.0045
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2844
+            "score": 0.2827
           }
         },
         {
@@ -116,7 +116,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4006
+            "score": 0.3979
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3087
+            "score": 0.3063
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4964
+            "score": 0.486
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4699
+            "score": 0.4721
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0045
+            "score": 0.0846
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2827
+            "score": 0.2844
           }
         },
         {
@@ -246,7 +246,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3979
+            "score": 0.4006
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3063
+            "score": 0.3087
           }
         }
       ],
diff --git a/data/models/nicolinho_qrm-gemma-2-27b.json b/data/models/nicolinho_qrm-gemma-2-27b.json
index 98185886d3c230ddcd90456c69a5aeed49795fc5..1dea90f885df9d34139a9ef21e55b3dcce1a25fd 100644
--- a/data/models/nicolinho_qrm-gemma-2-27b.json
+++ b/data/models/nicolinho_qrm-gemma-2-27b.json
@@ -9,10 +9,10 @@
   },
   "evaluations": [
     {
-      "evaluation_id": "reward-bench-2/nicolinho_QRM-Gemma-2-27B/1766412838.146816",
+      "evaluation_id": "reward-bench/nicolinho_QRM-Gemma-2-27B/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": 0.7667
+            "score": 0.9444
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "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": 0.7853
+            "score": 0.9665
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Precise IF",
+          "evaluation_name": "Chat Hard",
           "metric_config": {
-            "evaluation_description": "Precise Instruction Following score",
+            "evaluation_description": "Chat Hard accuracy - includes hard chat subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3719
+            "score": 0.9013
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Math",
+          "evaluation_name": "Safety",
           "metric_config": {
-            "evaluation_description": "Math score - measures mathematical reasoning",
+            "evaluation_description": "Safety accuracy - includes safety subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6995
+            "score": 0.927
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "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": 0.9578
+            "score": 0.9826
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
-        },
+        }
+      ],
+      "detailed_evaluation_results": null,
+      "generation_config": null
+    },
+    {
+      "evaluation_id": "reward-bench-2/nicolinho_QRM-Gemma-2-27B/1766412838.146816",
+      "retrieved_timestamp": "1766412838.146816",
+      "source_metadata": {
+        "source_name": "RewardBench 2",
+        "source_type": "documentation",
+        "source_organization_name": "Allen Institute for AI",
+        "source_organization_url": "https://allenai.org",
+        "evaluator_relationship": "third_party"
+      },
+      "eval_library": {
+        "name": "rewardbench",
+        "version": "0.1.3",
+        "additional_details": {
+          "subsets": "Chat, Chat Hard, Safety, Reasoning",
+          "hf_space": "allenai/reward-bench"
+        }
+      },
+      "benchmark": "reward-bench",
+      "evaluation_results": [
         {
-          "evaluation_name": "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": 0.9535
+            "score": 0.7667
           },
           "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": 0.8321
+            "score": 0.7853
           },
           "source_data": {
             "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
             "hf_repo": "allenai/reward-bench-2-results"
           }
-        }
-      ],
-      "detailed_evaluation_results": null,
-      "generation_config": null
-    },
-    {
-      "evaluation_id": "reward-bench/nicolinho_QRM-Gemma-2-27B/1766412838.146816",
-      "retrieved_timestamp": "1766412838.146816",
-      "source_metadata": {
-        "source_name": "RewardBench",
-        "source_type": "documentation",
-        "source_organization_name": "Allen Institute for AI",
-        "source_organization_url": "https://allenai.org",
-        "evaluator_relationship": "third_party"
-      },
-      "eval_library": {
-        "name": "rewardbench",
-        "version": "0.1.3",
-        "additional_details": {
-          "subsets": "Chat, Chat Hard, Safety, Reasoning",
-          "hf_space": "allenai/reward-bench"
-        }
-      },
-      "benchmark": "reward-bench",
-      "evaluation_results": [
+        },
         {
-          "evaluation_name": "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": 0.9444
+            "score": 0.3719
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Chat",
+          "evaluation_name": "Math",
           "metric_config": {
-            "evaluation_description": "Chat accuracy - includes easy chat subsets",
+            "evaluation_description": "Math score - measures mathematical reasoning",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9665
+            "score": 0.6995
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Chat Hard",
+          "evaluation_name": "Safety",
           "metric_config": {
-            "evaluation_description": "Chat Hard accuracy - includes hard chat subsets",
+            "evaluation_description": "Safety score - measures safety awareness",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9013
+            "score": 0.9578
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "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": 0.927
+            "score": 0.9535
           },
           "source_data": {
-            "dataset_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": 0.9826
+            "score": 0.8321
           },
           "source_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/omkar1102_code-yi.json b/data/models/omkar1102_code-yi.json
index 420be452467271270dd617b6ac43e82dcaa608b1..c43a8e6f44d50964e1b475e97cca0076acc3fcc2 100644
--- a/data/models/omkar1102_code-yi.json
+++ b/data/models/omkar1102_code-yi.json
@@ -5,7 +5,7 @@
     "developer": "Omkar1102",
     "inference_platform": "unknown",
     "additional_details": {
-      "precision": "bfloat16",
+      "precision": "float16",
       "architecture": "LlamaForCausalLM",
       "params_billions": "2.084"
     }
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2254
+            "score": 0.2148
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.275
+            "score": 0.276
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2576
+            "score": 0.2508
           }
         },
         {
@@ -116,7 +116,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3762
+            "score": 0.3802
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1123
+            "score": 0.1126
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2148
+            "score": 0.2254
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.276
+            "score": 0.275
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2508
+            "score": 0.2576
           }
         },
         {
@@ -246,7 +246,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3802
+            "score": 0.3762
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1126
+            "score": 0.1123
           }
         }
       ],
diff --git a/data/models/ontocord_wide_3b_sft_stage1.1-ss1-with_generics_intr_math_stories.no_issue.json b/data/models/ontocord_wide_3b_sft_stage1.1-ss1-with_generics_intr_math_stories.no_issue.json
index f86ab61b521749eb0f8fa030a3c29f5a32d327a1..486ba5e61208261c68f73d7d2bf88d78b1b36131 100644
--- a/data/models/ontocord_wide_3b_sft_stage1.1-ss1-with_generics_intr_math_stories.no_issue.json
+++ b/data/models/ontocord_wide_3b_sft_stage1.1-ss1-with_generics_intr_math_stories.no_issue.json
@@ -5,7 +5,7 @@
     "developer": "ontocord",
     "inference_platform": "unknown",
     "additional_details": {
-      "precision": "float16",
+      "precision": "bfloat16",
       "architecture": "Qwen2ForCausalLM",
       "params_billions": "3.759"
     }
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1162
+            "score": 0.1128
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3184
+            "score": 0.3171
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0076
+            "score": 0.0113
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2634
+            "score": 0.2685
           }
         },
         {
@@ -116,7 +116,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3447
+            "score": 0.346
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1124
+            "score": 0.1129
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1128
+            "score": 0.1162
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3171
+            "score": 0.3184
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0113
+            "score": 0.0076
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2685
+            "score": 0.2634
           }
         },
         {
@@ -246,7 +246,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.346
+            "score": 0.3447
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1129
+            "score": 0.1124
           }
         }
       ],
diff --git a/data/models/openai_gpt-4o-mini-2024-07-18.json b/data/models/openai_gpt-4o-mini-2024-07-18.json
index f38f4e1ddedf08dfff3e3ceeb97aeebb3dcce913..1b3fb4c30102ee1f603e3640bb4c4b14c38b8cac 100644
--- a/data/models/openai_gpt-4o-mini-2024-07-18.json
+++ b/data/models/openai_gpt-4o-mini-2024-07-18.json
@@ -2124,10 +2124,10 @@
       }
     },
     {
-      "evaluation_id": "reward-bench/openai_gpt-4o-mini-2024-07-18/1766412838.146816",
+      "evaluation_id": "reward-bench-2/openai_gpt-4o-mini-2024-07-18/1766412838.146816",
       "retrieved_timestamp": "1766412838.146816",
       "source_metadata": {
-        "source_name": "RewardBench",
+        "source_name": "RewardBench 2",
         "source_type": "documentation",
         "source_organization_name": "Allen Institute for AI",
         "source_organization_url": "https://allenai.org",
@@ -2146,128 +2146,104 @@
         {
           "evaluation_name": "Score",
           "metric_config": {
-            "evaluation_description": "Overall RewardBench Score",
+            "evaluation_description": "Overall RewardBench 2 Score (mean of all metrics)",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.8007
+            "score": 0.5796
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Chat",
+          "evaluation_name": "Factuality",
           "metric_config": {
-            "evaluation_description": "Chat accuracy - includes easy chat subsets",
+            "evaluation_description": "Factuality score - measures factual accuracy",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9497
+            "score": 0.4105
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Chat Hard",
+          "evaluation_name": "Precise IF",
           "metric_config": {
-            "evaluation_description": "Chat Hard accuracy - includes hard chat subsets",
+            "evaluation_description": "Precise Instruction Following score",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6075
+            "score": 0.3438
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Safety",
+          "evaluation_name": "Math",
           "metric_config": {
-            "evaluation_description": "Safety accuracy - includes safety subsets",
+            "evaluation_description": "Math score - measures mathematical reasoning",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.8081
+            "score": 0.5191
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Reasoning",
+          "evaluation_name": "Safety",
           "metric_config": {
-            "evaluation_description": "Reasoning accuracy - includes code and math subsets",
+            "evaluation_description": "Safety score - measures safety awareness",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.8374
+            "score": 0.7667
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
-        }
-      ],
-      "detailed_evaluation_results": null,
-      "generation_config": null
-    },
-    {
-      "evaluation_id": "reward-bench-2/openai_gpt-4o-mini-2024-07-18/1766412838.146816",
-      "retrieved_timestamp": "1766412838.146816",
-      "source_metadata": {
-        "source_name": "RewardBench 2",
-        "source_type": "documentation",
-        "source_organization_name": "Allen Institute for AI",
-        "source_organization_url": "https://allenai.org",
-        "evaluator_relationship": "third_party"
-      },
-      "eval_library": {
-        "name": "rewardbench",
-        "version": "0.1.3",
-        "additional_details": {
-          "subsets": "Chat, Chat Hard, Safety, Reasoning",
-          "hf_space": "allenai/reward-bench"
-        }
-      },
-      "benchmark": "reward-bench",
-      "evaluation_results": [
+        },
         {
-          "evaluation_name": "Score",
+          "evaluation_name": "Focus",
           "metric_config": {
-            "evaluation_description": "Overall RewardBench 2 Score (mean of all metrics)",
+            "evaluation_description": "Focus score - measures response focus",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5796
+            "score": 0.7414
           },
           "source_data": {
             "dataset_name": "RewardBench 2",
@@ -2276,111 +2252,135 @@
           }
         },
         {
-          "evaluation_name": "Factuality",
+          "evaluation_name": "Ties",
           "metric_config": {
-            "evaluation_description": "Factuality score - measures factual accuracy",
+            "evaluation_description": "Ties score - ability to identify tie cases",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4105
+            "score": 0.6962
           },
           "source_data": {
             "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
             "hf_repo": "allenai/reward-bench-2-results"
           }
-        },
+        }
+      ],
+      "detailed_evaluation_results": null,
+      "generation_config": null
+    },
+    {
+      "evaluation_id": "reward-bench/openai_gpt-4o-mini-2024-07-18/1766412838.146816",
+      "retrieved_timestamp": "1766412838.146816",
+      "source_metadata": {
+        "source_name": "RewardBench",
+        "source_type": "documentation",
+        "source_organization_name": "Allen Institute for AI",
+        "source_organization_url": "https://allenai.org",
+        "evaluator_relationship": "third_party"
+      },
+      "eval_library": {
+        "name": "rewardbench",
+        "version": "0.1.3",
+        "additional_details": {
+          "subsets": "Chat, Chat Hard, Safety, Reasoning",
+          "hf_space": "allenai/reward-bench"
+        }
+      },
+      "benchmark": "reward-bench",
+      "evaluation_results": [
         {
-          "evaluation_name": "Precise IF",
+          "evaluation_name": "Score",
           "metric_config": {
-            "evaluation_description": "Precise Instruction Following score",
+            "evaluation_description": "Overall RewardBench Score",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3438
+            "score": 0.8007
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Math",
+          "evaluation_name": "Chat",
           "metric_config": {
-            "evaluation_description": "Math score - measures mathematical reasoning",
+            "evaluation_description": "Chat accuracy - includes easy chat subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5191
+            "score": 0.9497
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Safety",
+          "evaluation_name": "Chat Hard",
           "metric_config": {
-            "evaluation_description": "Safety score - measures safety awareness",
+            "evaluation_description": "Chat Hard accuracy - includes hard chat subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7667
+            "score": 0.6075
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Focus",
+          "evaluation_name": "Safety",
           "metric_config": {
-            "evaluation_description": "Focus score - measures response focus",
+            "evaluation_description": "Safety accuracy - includes safety subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7414
+            "score": 0.8081
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Ties",
+          "evaluation_name": "Reasoning",
           "metric_config": {
-            "evaluation_description": "Ties score - ability to identify tie cases",
+            "evaluation_description": "Reasoning accuracy - includes code and math subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6962
+            "score": 0.8374
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         }
       ],
diff --git a/data/models/openai_gpt-5-2025-08-07.json b/data/models/openai_gpt-5-2025-08-07.json
index 0853492fcc4bbd45f07185718454686350fe1be2..fdb97ce4111978e08938be252c1bd72645c11969 100644
--- a/data/models/openai_gpt-5-2025-08-07.json
+++ b/data/models/openai_gpt-5-2025-08-07.json
@@ -10,8 +10,8 @@
   },
   "evaluations": [
     {
-      "evaluation_id": "global-mmlu-lite/openai_gpt-5-2025-08-07/1773936496.366405",
-      "retrieved_timestamp": "1773936496.366405",
+      "evaluation_id": "global-mmlu-lite/openai_gpt-5-2025-08-07/1773936583.743359",
+      "retrieved_timestamp": "1773936583.743359",
       "source_metadata": {
         "source_name": "Global MMLU Lite Leaderboard",
         "source_type": "documentation",
@@ -525,8 +525,8 @@
       "generation_config": null
     },
     {
-      "evaluation_id": "global-mmlu-lite/openai_gpt-5-2025-08-07/1773936583.743359",
-      "retrieved_timestamp": "1773936583.743359",
+      "evaluation_id": "global-mmlu-lite/openai_gpt-5-2025-08-07/1773936496.366405",
+      "retrieved_timestamp": "1773936496.366405",
       "source_metadata": {
         "source_name": "Global MMLU Lite Leaderboard",
         "source_type": "documentation",
diff --git a/data/models/openai_gpt-5-codex.json b/data/models/openai_gpt-5-codex.json
index 21a2358b27ce78cb6bd659dfe0536dac012c1818..c82c5f95f908380f688e9ef7118281bf4bf2ade4 100644
--- a/data/models/openai_gpt-5-codex.json
+++ b/data/models/openai_gpt-5-codex.json
@@ -84,7 +84,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/codex-cli__gpt-5-codex/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/terminus-2__gpt-5-codex/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -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": 44.3,
+            "score": 43.4,
             "uncertainty": {
               "standard_error": {
-                "value": 2.7
+                "value": 2.9
               },
               "num_samples": 435
             }
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Codex CLI\" -m \"GPT-5-Codex\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"GPT-5-Codex\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -144,7 +144,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Codex CLI\" -m \"GPT-5-Codex\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"GPT-5-Codex\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -158,7 +158,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/terminus-2__gpt-5-codex/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/codex-cli__gpt-5-codex/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -182,7 +182,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-10-31",
+          "evaluation_timestamp": "2025-11-04",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -191,17 +191,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 43.4,
+            "score": 44.3,
             "uncertainty": {
               "standard_error": {
-                "value": 2.9
+                "value": 2.7
               },
               "num_samples": 435
             }
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"GPT-5-Codex\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Codex CLI\" -m \"GPT-5-Codex\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -218,7 +218,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"GPT-5-Codex\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Codex CLI\" -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 a9c814071acbfdd08e7ec7cb2178b705e66b8da6..1a99c04bbe99b006a4925655196388ed4bd20247 100644
--- a/data/models/openai_gpt-5-mini.json
+++ b/data/models/openai_gpt-5-mini.json
@@ -84,7 +84,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/codex-cli__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",
@@ -108,7 +108,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-11-04",
+          "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": 31.9,
+            "score": 34.8,
             "uncertainty": {
               "standard_error": {
-                "value": 3.0
+                "value": 2.7
               },
               "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 \"spoox-m\" -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 \"Codex CLI\" -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": [
               {
@@ -158,7 +158,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/terminus-2__gpt-5-mini/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/codex-cli__gpt-5-mini/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -182,7 +182,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-10-31",
+          "evaluation_timestamp": "2025-11-04",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -191,17 +191,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 24.0,
+            "score": 31.9,
             "uncertainty": {
               "standard_error": {
-                "value": 2.5
+                "value": 3.0
               },
               "num_samples": 435
             }
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"GPT-5-Mini\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Codex CLI\" -m \"GPT-5-Mini\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -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-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": [
               {
@@ -306,7 +306,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/spoox-m__gpt-5-mini/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/terminus-2__gpt-5-mini/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -330,7 +330,7 @@
               "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,
@@ -339,17 +339,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 34.8,
+            "score": 24.0,
             "uncertainty": {
               "standard_error": {
-                "value": 2.7
+                "value": 2.5
               },
               "num_samples": 435
             }
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"spoox-m\" -m \"GPT-5-Mini\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"GPT-5-Mini\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -366,7 +366,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"spoox-m\" -m \"GPT-5-Mini\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"GPT-5-Mini\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
diff --git a/data/models/openai_gpt-5-nano.json b/data/models/openai_gpt-5-nano.json
index 0d64dfdab152e442151bbf86365c72d39472c605..6e06e0851504fafe04f9fd1896b5ae58a6354f7a 100644
--- a/data/models/openai_gpt-5-nano.json
+++ b/data/models/openai_gpt-5-nano.json
@@ -158,7 +158,7 @@
       }
     },
     {
-      "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",
@@ -182,7 +182,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-10-31",
+          "evaluation_timestamp": "2025-11-03",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -191,7 +191,7 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 7.9,
+            "score": 7.0,
             "uncertainty": {
               "standard_error": {
                 "value": 1.9
@@ -201,7 +201,7 @@
           },
           "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": [
                   {
@@ -218,7 +218,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"GPT-5-Nano\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Mini-SWE-Agent\" -m \"GPT-5-Nano\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -232,7 +232,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/mini-swe-agent__gpt-5-nano/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/terminus-2__gpt-5-nano/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -256,7 +256,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-11-03",
+          "evaluation_timestamp": "2025-10-31",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -265,7 +265,7 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 7.0,
+            "score": 7.9,
             "uncertainty": {
               "standard_error": {
                 "value": 1.9
@@ -275,7 +275,7 @@
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Mini-SWE-Agent\" -m \"GPT-5-Nano\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"GPT-5-Nano\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -292,7 +292,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Mini-SWE-Agent\" -m \"GPT-5-Nano\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"GPT-5-Nano\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
diff --git a/data/models/openai_gpt-5.2-2025-12-11.json b/data/models/openai_gpt-5.2-2025-12-11.json
index b1415af8e1fa1580e027129e48746b8a6ec316b5..3ac8b435319869c3f1714af61314295abb8f963c 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": "LiteLLM Tool Calling with Shortlisting",
-      "agent_framework": "tool_calling_with_shortlisting"
+      "agent_name": "LiteLLM Tool Calling",
+      "agent_framework": "tool_calling"
     }
   },
   "evaluations": [
     {
-      "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",
@@ -42,23 +42,23 @@
             "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"
                 }
               }
             }
@@ -70,15 +70,15 @@
         "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/smolagents-code__openai_gpt-5.2-2025-12-11/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -110,23 +110,23 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0,
+            "score": 0.071,
             "uncertainty": {
               "num_samples": 100
             },
             "details": {
-              "average_agent_cost": "0.0",
-              "total_run_cost": "0.0",
-              "average_steps": "0.0",
-              "percent_finished": "0.0"
+              "average_agent_cost": "0.55",
+              "total_run_cost": "55.03",
+              "average_steps": "51.59",
+              "percent_finished": "0.61"
             }
           },
           "generation_config": {
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "Claude Code CLI",
-                  "agent_framework": "claude_code"
+                  "agent_name": "SmolAgents Code",
+                  "agent_framework": "smolagents_code"
                 }
               }
             }
@@ -138,15 +138,15 @@
         "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": "appworld/test_normal/litellm-tool-calling__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",
@@ -193,8 +193,8 @@
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "LiteLLM Tool Calling",
-                  "agent_framework": "tool_calling"
+                  "agent_name": "OpenAI Solo",
+                  "agent_framework": "openai_solo"
                 }
               }
             }
@@ -206,15 +206,15 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "LiteLLM Tool Calling",
-              "agent_framework": "tool_calling"
+              "agent_name": "OpenAI Solo",
+              "agent_framework": "openai_solo"
             }
           }
         }
       }
     },
     {
-      "evaluation_id": "appworld/test_normal/openai-solo__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",
@@ -246,23 +246,23 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0,
+            "score": 0.22,
             "uncertainty": {
               "num_samples": 100
             },
             "details": {
-              "average_agent_cost": "0.0",
-              "total_run_cost": "0.0",
-              "average_steps": "0.0",
-              "percent_finished": "0.0"
+              "average_agent_cost": "0.36",
+              "total_run_cost": "36.37",
+              "average_steps": "10.05",
+              "percent_finished": "1.0"
             }
           },
           "generation_config": {
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "OpenAI Solo",
-                  "agent_framework": "openai_solo"
+                  "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": "OpenAI Solo",
-              "agent_framework": "openai_solo"
+              "agent_name": "LiteLLM Tool Calling with Shortlisting",
+              "agent_framework": "tool_calling_with_shortlisting"
             }
           }
         }
       }
     },
     {
-      "evaluation_id": "appworld/test_normal/smolagents-code__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",
@@ -314,23 +314,23 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.071,
+            "score": 0.0,
             "uncertainty": {
               "num_samples": 100
             },
             "details": {
-              "average_agent_cost": "0.55",
-              "total_run_cost": "55.03",
-              "average_steps": "51.59",
-              "percent_finished": "0.61"
+              "average_agent_cost": "0.0",
+              "total_run_cost": "0.0",
+              "average_steps": "0.0",
+              "percent_finished": "0.0"
             }
           },
           "generation_config": {
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "SmolAgents Code",
-                  "agent_framework": "smolagents_code"
+                  "agent_name": "Claude Code CLI",
+                  "agent_framework": "claude_code"
                 }
               }
             }
@@ -342,8 +342,8 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "SmolAgents Code",
-              "agent_framework": "smolagents_code"
+              "agent_name": "Claude Code CLI",
+              "agent_framework": "claude_code"
             }
           }
         }
@@ -418,7 +418,7 @@
       }
     },
     {
-      "evaluation_id": "browsecompplus/claude-code-cli__openai_gpt-5.2-2025-12-11/1774263615.0201504",
+      "evaluation_id": "browsecompplus/openai-solo__openai_gpt-5.2-2025-12-11/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -450,14 +450,14 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.43,
+            "score": 0.48,
             "uncertainty": {
               "num_samples": 100
             },
             "details": {
-              "average_agent_cost": "0.43",
-              "total_run_cost": "43.11",
-              "average_steps": "8.97",
+              "average_agent_cost": "0.38",
+              "total_run_cost": "38.21",
+              "average_steps": "14.27",
               "percent_finished": "1.0"
             }
           },
@@ -465,8 +465,8 @@
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "Claude Code CLI",
-                  "agent_framework": "claude_code"
+                  "agent_name": "OpenAI Solo",
+                  "agent_framework": "openai_solo"
                 }
               }
             }
@@ -478,15 +478,15 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "Claude Code CLI",
-              "agent_framework": "claude_code"
+              "agent_name": "OpenAI Solo",
+              "agent_framework": "openai_solo"
             }
           }
         }
       }
     },
     {
-      "evaluation_id": "browsecompplus/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",
@@ -518,23 +518,23 @@
             "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"
                 }
               }
             }
@@ -546,8 +546,8 @@
         "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"
             }
           }
         }
@@ -622,7 +622,7 @@
       }
     },
     {
-      "evaluation_id": "browsecompplus/litellm-tool-calling-with-shortlisting__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",
@@ -654,23 +654,23 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.46,
+            "score": 0.43,
             "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": "0.43",
+              "total_run_cost": "43.11",
+              "average_steps": "8.97",
+              "percent_finished": "1.0"
             }
           },
           "generation_config": {
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "LiteLLM Tool Calling with Shortlisting",
-                  "agent_framework": "tool_calling_with_shortlisting"
+                  "agent_name": "Claude Code CLI",
+                  "agent_framework": "claude_code"
                 }
               }
             }
@@ -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": "Claude Code CLI",
+              "agent_framework": "claude_code"
             }
           }
         }
@@ -769,7 +769,7 @@
       "generation_config": null
     },
     {
-      "evaluation_id": "swe-bench/litellm-tool-calling__openai_gpt-5.2-2025-12-11/1774263615.0201504",
+      "evaluation_id": "swe-bench/claude-code-cli__openai_gpt-5.2-2025-12-11/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -801,14 +801,14 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.57,
+            "score": 0.58,
             "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"
             }
           },
@@ -816,8 +816,8 @@
             "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"
                 }
               }
             }
@@ -829,15 +829,15 @@
         "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/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",
@@ -869,14 +869,14 @@
             "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"
             }
           },
@@ -884,8 +884,8 @@
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "Claude Code CLI",
-                  "agent_framework": "claude_code"
+                  "agent_name": "SmolAgents Code",
+                  "agent_framework": "smolagents_code"
                 }
               }
             }
@@ -897,15 +897,15 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "Claude Code CLI",
-              "agent_framework": "claude_code"
+              "agent_name": "SmolAgents Code",
+              "agent_framework": "smolagents_code"
             }
           }
         }
       }
     },
     {
-      "evaluation_id": "swe-bench/openai-solo__openai_gpt-5.2-2025-12-11/1774263615.0201504",
+      "evaluation_id": "swe-bench/litellm-tool-calling-with-shortlisting__openai_gpt-5.2-2025-12-11/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -937,14 +937,14 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5455,
+            "score": 0.57,
             "uncertainty": {
-              "num_samples": 99
+              "num_samples": 100
             },
             "details": {
-              "average_agent_cost": "0.26",
-              "total_run_cost": "25.64",
-              "average_steps": "20.44",
+              "average_agent_cost": "0.25",
+              "total_run_cost": "24.76",
+              "average_steps": "20.47",
               "percent_finished": "1.0"
             }
           },
@@ -952,8 +952,8 @@
             "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"
                 }
               }
             }
@@ -965,15 +965,15 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "OpenAI Solo",
-              "agent_framework": "openai_solo"
+              "agent_name": "LiteLLM Tool Calling with Shortlisting",
+              "agent_framework": "tool_calling_with_shortlisting"
             }
           }
         }
       }
     },
     {
-      "evaluation_id": "swe-bench/smolagents-code__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",
@@ -1005,14 +1005,14 @@
             "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"
             }
           },
@@ -1020,8 +1020,8 @@
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "SmolAgents Code",
-                  "agent_framework": "smolagents_code"
+                  "agent_name": "LiteLLM Tool Calling",
+                  "agent_framework": "tool_calling"
                 }
               }
             }
@@ -1033,15 +1033,15 @@
         "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-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",
@@ -1073,14 +1073,14 @@
             "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"
             }
           },
@@ -1088,8 +1088,8 @@
             "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"
                 }
               }
             }
@@ -1101,15 +1101,15 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "LiteLLM Tool Calling with Shortlisting",
-              "agent_framework": "tool_calling_with_shortlisting"
+              "agent_name": "OpenAI Solo",
+              "agent_framework": "openai_solo"
             }
           }
         }
       }
     },
     {
-      "evaluation_id": "tau-bench-2/airline/openai-solo__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",
@@ -1141,14 +1141,14 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5,
+            "score": 0.48,
             "uncertainty": {
               "num_samples": 50
             },
             "details": {
-              "average_agent_cost": "0.11",
-              "total_run_cost": "5.77",
-              "average_steps": "11.4",
+              "average_agent_cost": "0.21",
+              "total_run_cost": "11.23",
+              "average_steps": "10.18",
               "percent_finished": "1.0"
             }
           },
@@ -1156,8 +1156,8 @@
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "OpenAI Solo",
-                  "agent_framework": "openai_solo"
+                  "agent_name": "Claude Code CLI",
+                  "agent_framework": "claude_code"
                 }
               }
             }
@@ -1169,15 +1169,15 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "OpenAI Solo",
-              "agent_framework": "openai_solo"
+              "agent_name": "Claude Code CLI",
+              "agent_framework": "claude_code"
             }
           }
         }
       }
     },
     {
-      "evaluation_id": "tau-bench-2/airline/litellm-tool-calling__openai_gpt-5.2-2025-12-11/1774263615.0201504",
+      "evaluation_id": "tau-bench-2/airline/openai-solo__openai_gpt-5.2-2025-12-11/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -1209,14 +1209,14 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.54,
+            "score": 0.5,
             "uncertainty": {
               "num_samples": 50
             },
             "details": {
-              "average_agent_cost": "0.13",
-              "total_run_cost": "6.96",
-              "average_steps": "11.22",
+              "average_agent_cost": "0.11",
+              "total_run_cost": "5.77",
+              "average_steps": "11.4",
               "percent_finished": "1.0"
             }
           },
@@ -1224,8 +1224,8 @@
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "LiteLLM Tool Calling",
-                  "agent_framework": "tool_calling"
+                  "agent_name": "OpenAI Solo",
+                  "agent_framework": "openai_solo"
                 }
               }
             }
@@ -1237,15 +1237,15 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "LiteLLM Tool Calling",
-              "agent_framework": "tool_calling"
+              "agent_name": "OpenAI Solo",
+              "agent_framework": "openai_solo"
             }
           }
         }
       }
     },
     {
-      "evaluation_id": "tau-bench-2/airline/claude-code-cli__openai_gpt-5.2-2025-12-11/1774263615.0201504",
+      "evaluation_id": "tau-bench-2/airline/litellm-tool-calling__openai_gpt-5.2-2025-12-11/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -1277,14 +1277,14 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.48,
+            "score": 0.54,
             "uncertainty": {
               "num_samples": 50
             },
             "details": {
-              "average_agent_cost": "0.21",
-              "total_run_cost": "11.23",
-              "average_steps": "10.18",
+              "average_agent_cost": "0.13",
+              "total_run_cost": "6.96",
+              "average_steps": "11.22",
               "percent_finished": "1.0"
             }
           },
@@ -1292,8 +1292,8 @@
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "Claude Code CLI",
-                  "agent_framework": "claude_code"
+                  "agent_name": "LiteLLM Tool Calling",
+                  "agent_framework": "tool_calling"
                 }
               }
             }
@@ -1305,8 +1305,8 @@
         "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"
             }
           }
         }
@@ -1517,7 +1517,7 @@
       }
     },
     {
-      "evaluation_id": "tau-bench-2/retail/litellm-tool-calling-with-shortlisting__openai_gpt-5.2-2025-12-11/1774263615.0201504",
+      "evaluation_id": "tau-bench-2/retail/smolagents-code__openai_gpt-5.2-2025-12-11/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -1549,14 +1549,14 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.73,
+            "score": 0.68,
             "uncertainty": {
               "num_samples": 100
             },
             "details": {
-              "average_agent_cost": "0.11",
-              "total_run_cost": "12.27",
-              "average_steps": "10.33",
+              "average_agent_cost": "0.25",
+              "total_run_cost": "26.27",
+              "average_steps": "11.08",
               "percent_finished": "1.0"
             }
           },
@@ -1564,8 +1564,8 @@
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "LiteLLM Tool Calling with Shortlisting",
-                  "agent_framework": "tool_calling_with_shortlisting"
+                  "agent_name": "SmolAgents Code",
+                  "agent_framework": "smolagents_code"
                 }
               }
             }
@@ -1577,8 +1577,8 @@
         "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"
             }
           }
         }
@@ -1653,7 +1653,7 @@
       }
     },
     {
-      "evaluation_id": "tau-bench-2/retail/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",
@@ -1685,14 +1685,14 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.68,
+            "score": 0.73,
             "uncertainty": {
               "num_samples": 100
             },
             "details": {
-              "average_agent_cost": "0.25",
-              "total_run_cost": "26.27",
-              "average_steps": "11.08",
+              "average_agent_cost": "0.11",
+              "total_run_cost": "12.27",
+              "average_steps": "10.33",
               "percent_finished": "1.0"
             }
           },
@@ -1700,8 +1700,8 @@
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "SmolAgents Code",
-                  "agent_framework": "smolagents_code"
+                  "agent_name": "LiteLLM Tool Calling",
+                  "agent_framework": "tool_calling"
                 }
               }
             }
@@ -1713,15 +1713,15 @@
         "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__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",
@@ -1768,8 +1768,8 @@
             "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"
                 }
               }
             }
@@ -1781,15 +1781,15 @@
         "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/telecom/litellm-tool-calling-with-shortlisting__openai_gpt-5.2-2025-12-11/1774263615.0201504",
+      "evaluation_id": "tau-bench-2/telecom/litellm-tool-calling__openai_gpt-5.2-2025-12-11/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -1836,8 +1836,8 @@
             "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"
                 }
               }
             }
@@ -1849,15 +1849,15 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "LiteLLM Tool Calling with Shortlisting",
-              "agent_framework": "tool_calling_with_shortlisting"
+              "agent_name": "LiteLLM Tool Calling",
+              "agent_framework": "tool_calling"
             }
           }
         }
       }
     },
     {
-      "evaluation_id": "tau-bench-2/telecom/openai-solo__openai_gpt-5.2-2025-12-11/1774263615.0201504",
+      "evaluation_id": "tau-bench-2/telecom/smolagents-code__openai_gpt-5.2-2025-12-11/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -1889,14 +1889,14 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.53,
+            "score": 0.71,
             "uncertainty": {
               "num_samples": 100
             },
             "details": {
-              "average_agent_cost": "0.15",
-              "total_run_cost": "18.88",
-              "average_steps": "9.92",
+              "average_agent_cost": "0.3",
+              "total_run_cost": "35.31",
+              "average_steps": "10.11",
               "percent_finished": "1.0"
             }
           },
@@ -1904,8 +1904,8 @@
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "OpenAI Solo",
-                  "agent_framework": "openai_solo"
+                  "agent_name": "SmolAgents Code",
+                  "agent_framework": "smolagents_code"
                 }
               }
             }
@@ -1917,15 +1917,15 @@
         "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/litellm-tool-calling__openai_gpt-5.2-2025-12-11/1774263615.0201504",
+      "evaluation_id": "tau-bench-2/telecom/claude-code-cli__openai_gpt-5.2-2025-12-11/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -1957,23 +1957,23 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5354,
+            "score": 0.55,
             "uncertainty": {
               "num_samples": 100
             },
             "details": {
-              "average_agent_cost": "0.14",
-              "total_run_cost": "19.92",
-              "average_steps": "10.18",
-              "percent_finished": "0.99"
+              "average_agent_cost": "0.1",
+              "total_run_cost": "15.15",
+              "average_steps": "9.36",
+              "percent_finished": "1.0"
             }
           },
           "generation_config": {
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "LiteLLM Tool Calling",
-                  "agent_framework": "tool_calling"
+                  "agent_name": "Claude Code CLI",
+                  "agent_framework": "claude_code"
                 }
               }
             }
@@ -1985,15 +1985,15 @@
         "generation_args": {
           "agentic_eval_config": {
             "additional_details": {
-              "agent_name": "LiteLLM Tool Calling",
-              "agent_framework": "tool_calling"
+              "agent_name": "Claude Code CLI",
+              "agent_framework": "claude_code"
             }
           }
         }
       }
     },
     {
-      "evaluation_id": "tau-bench-2/telecom/smolagents-code__openai_gpt-5.2-2025-12-11/1774263615.0201504",
+      "evaluation_id": "tau-bench-2/telecom/openai-solo__openai_gpt-5.2-2025-12-11/1774263615.0201504",
       "retrieved_timestamp": "1774263615.0201504",
       "source_metadata": {
         "source_name": "Exgentic Open Agent Leaderboard",
@@ -2025,14 +2025,14 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.71,
+            "score": 0.53,
             "uncertainty": {
               "num_samples": 100
             },
             "details": {
-              "average_agent_cost": "0.3",
-              "total_run_cost": "35.31",
-              "average_steps": "10.11",
+              "average_agent_cost": "0.15",
+              "total_run_cost": "18.88",
+              "average_steps": "9.92",
               "percent_finished": "1.0"
             }
           },
@@ -2040,8 +2040,8 @@
             "generation_args": {
               "agentic_eval_config": {
                 "additional_details": {
-                  "agent_name": "SmolAgents Code",
-                  "agent_framework": "smolagents_code"
+                  "agent_name": "OpenAI Solo",
+                  "agent_framework": "openai_solo"
                 }
               }
             }
@@ -2053,15 +2053,15 @@
         "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/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",
@@ -2093,23 +2093,23 @@
             "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"
                 }
               }
             }
@@ -2121,8 +2121,8 @@
         "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"
             }
           }
         }
diff --git a/data/models/openai_gpt-5.2.json b/data/models/openai_gpt-5.2.json
index 77930b98006acfd2c6efa9a1e831cbd44874ee48..b67565fdc4a3c74776c9cdbc79f6dbe213fd591f 100644
--- a/data/models/openai_gpt-5.2.json
+++ b/data/models/openai_gpt-5.2.json
@@ -4,13 +4,13 @@
     "id": "openai/gpt-5.2",
     "developer": "OpenAI",
     "additional_details": {
-      "agent_name": "Codex CLI",
-      "agent_organization": "OpenAI"
+      "agent_name": "Mux",
+      "agent_organization": "Coder"
     }
   },
   "evaluations": [
     {
-      "evaluation_id": "terminal-bench-2.0/codex-cli__gpt-5.2/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/mux__gpt-5.2/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -34,7 +34,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-12-18",
+          "evaluation_timestamp": "2026-01-17",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -43,17 +43,11 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 62.9,
-            "uncertainty": {
-              "standard_error": {
-                "value": 3.0
-              },
-              "num_samples": 435
-            }
+            "score": 60.7
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Codex CLI\" -m \"GPT-5.2\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Mux\" -m \"GPT-5.2\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -70,7 +64,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Codex CLI\" -m \"GPT-5.2\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Mux\" -m \"GPT-5.2\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -158,7 +152,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/terminus-2__gpt-5.2/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/codex-cli__gpt-5.2/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -182,7 +176,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-12-12",
+          "evaluation_timestamp": "2025-12-18",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -191,17 +185,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 54.0,
+            "score": 62.9,
             "uncertainty": {
               "standard_error": {
-                "value": 2.9
+                "value": 3.0
               },
               "num_samples": 435
             }
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"GPT-5.2\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Codex CLI\" -m \"GPT-5.2\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -218,7 +212,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"GPT-5.2\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Codex CLI\" -m \"GPT-5.2\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -232,7 +226,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/mux__gpt-5.2/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/terminus-2__gpt-5.2/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -256,7 +250,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2026-01-17",
+          "evaluation_timestamp": "2025-12-12",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -265,11 +259,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 60.7
+            "score": 54.0,
+            "uncertainty": {
+              "standard_error": {
+                "value": 2.9
+              },
+              "num_samples": 435
+            }
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Mux\" -m \"GPT-5.2\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"GPT-5.2\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -286,7 +286,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Mux\" -m \"GPT-5.2\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"GPT-5.2\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
diff --git a/data/models/openai_gpt-5.3-codex.json b/data/models/openai_gpt-5.3-codex.json
index 29bf24de6a839acf45f0dd14a04022b9052f2277..c4bd37007eca31e6c37beeb80d8affa5bcab3cb9 100644
--- a/data/models/openai_gpt-5.3-codex.json
+++ b/data/models/openai_gpt-5.3-codex.json
@@ -4,13 +4,13 @@
     "id": "openai/gpt-5.3-codex",
     "developer": "OpenAI",
     "additional_details": {
-      "agent_name": "Terminus 2",
-      "agent_organization": "Terminal Bench"
+      "agent_name": "Simple Codex",
+      "agent_organization": "OpenAI"
     }
   },
   "evaluations": [
     {
-      "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",
@@ -34,7 +34,7 @@
               "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,
@@ -43,17 +43,17 @@
             "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": [
                   {
@@ -70,7 +70,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"GPT-5.3-Codex\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Simple Codex\" -m \"GPT-5.3-Codex\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -158,7 +158,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/simple-codex__gpt-5.3-codex/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/droid__gpt-5.3-codex/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -182,7 +182,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2026-02-06",
+          "evaluation_timestamp": "2026-02-24",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -191,17 +191,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 75.1,
+            "score": 77.3,
             "uncertainty": {
               "standard_error": {
-                "value": 2.4
+                "value": 2.2
               },
               "num_samples": 435
             }
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Simple Codex\" -m \"GPT-5.3-Codex\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Droid\" -m \"GPT-5.3-Codex\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -218,7 +218,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Simple Codex\" -m \"GPT-5.3-Codex\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Droid\" -m \"GPT-5.3-Codex\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -232,7 +232,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/droid__gpt-5.3-codex/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/terminus-2__gpt-5.3-codex/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -256,7 +256,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2026-02-24",
+          "evaluation_timestamp": "2026-02-05",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -265,17 +265,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 77.3,
+            "score": 64.7,
             "uncertainty": {
               "standard_error": {
-                "value": 2.2
+                "value": 2.7
               },
               "num_samples": 435
             }
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Droid\" -m \"GPT-5.3-Codex\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"GPT-5.3-Codex\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -292,7 +292,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Droid\" -m \"GPT-5.3-Codex\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"GPT-5.3-Codex\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
diff --git a/data/models/openai_gpt-5.json b/data/models/openai_gpt-5.json
index 9005bf4e58d9a5ca4b1df67ba70d59695c801ffb..55a3f1373a6ae761230df9b4daabc2f189cbdd8d 100644
--- a/data/models/openai_gpt-5.json
+++ b/data/models/openai_gpt-5.json
@@ -158,7 +158,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/terminus-2__gpt-5/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/codex-cli__gpt-5/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -182,7 +182,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-10-31",
+          "evaluation_timestamp": "2025-11-04",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -191,17 +191,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 35.2,
+            "score": 49.6,
             "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 \"Terminus 2\" -m \"GPT-5\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Codex CLI\" -m \"GPT-5\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -218,7 +218,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"GPT-5\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Codex CLI\" -m \"GPT-5\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -232,7 +232,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/codex-cli__gpt-5/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/terminus-2__gpt-5/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -256,7 +256,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-11-04",
+          "evaluation_timestamp": "2025-10-31",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -265,17 +265,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 49.6,
+            "score": 35.2,
             "uncertainty": {
               "standard_error": {
-                "value": 2.9
+                "value": 3.1
               },
               "num_samples": 435
             }
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Codex CLI\" -m \"GPT-5\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"GPT-5\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -292,7 +292,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Codex CLI\" -m \"GPT-5\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"GPT-5\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
diff --git a/data/models/openai_o4-mini-2025-04-16.json b/data/models/openai_o4-mini-2025-04-16.json
index 2445a24c2417bbf08441a2388a2fba31fa9d6f49..751e567f80107ae7403958c0915864809e731407 100644
--- a/data/models/openai_o4-mini-2025-04-16.json
+++ b/data/models/openai_o4-mini-2025-04-16.json
@@ -749,13 +749,13 @@
       }
     },
     {
-      "evaluation_id": "livecodebenchpro/o4-mini-2025-04-16/1770683238.099205",
-      "retrieved_timestamp": "1770683238.099205",
+      "evaluation_id": "livecodebenchpro/o4-mini-2025-04-16/1760492095.8105888",
+      "retrieved_timestamp": "1760492095.8105888",
       "source_metadata": {
+        "source_organization_name": "New York University,  Princeton University, University of California San Diego, University of Washington and Canyon Crest Academy",
+        "evaluator_relationship": "third_party",
         "source_name": "Live Code Bench Pro",
-        "source_type": "documentation",
-        "source_organization_name": "New York University, Princeton University, University of California San Diego, University of Washington and Canyon Crest Academy",
-        "evaluator_relationship": "third_party"
+        "source_type": "documentation"
       },
       "eval_library": {
         "name": "unknown",
@@ -765,62 +765,62 @@
       "evaluation_results": [
         {
           "evaluation_name": "Hard Problems",
+          "metric_config": {
+            "evaluation_description": "Pass@1 on Hard Problems",
+            "lower_is_better": false,
+            "score_type": "continuous",
+            "min_score": 0,
+            "max_score": 1
+          },
+          "score_details": {
+            "score": 0.014084507042253521
+          },
           "source_data": {
             "dataset_name": "Hard Problems",
             "source_type": "url",
             "url": [
               "https://webhook.cp-bench.orzzh.com/leaderboard/llm/difficulty?difficulty=hard&benchmark_mode=live"
             ]
-          },
+          }
+        },
+        {
+          "evaluation_name": "Medium Problems",
           "metric_config": {
-            "evaluation_description": "Pass@1 on Hard Problems",
+            "evaluation_description": "Pass@1 on Medium Problems",
             "lower_is_better": false,
             "score_type": "continuous",
-            "min_score": 0.0,
-            "max_score": 1.0
+            "min_score": 0,
+            "max_score": 1
           },
           "score_details": {
-            "score": 0.0143
-          }
-        },
-        {
-          "evaluation_name": "Medium Problems",
+            "score": 0.30985915492957744
+          },
           "source_data": {
             "dataset_name": "Medium Problems",
             "source_type": "url",
             "url": [
               "https://webhook.cp-bench.orzzh.com/leaderboard/llm/difficulty?difficulty=medium&benchmark_mode=live"
             ]
-          },
+          }
+        },
+        {
+          "evaluation_name": "Easy Problems",
           "metric_config": {
-            "evaluation_description": "Pass@1 on Medium Problems",
+            "evaluation_description": "Pass@1 on Easy Problems",
             "lower_is_better": false,
             "score_type": "continuous",
-            "min_score": 0.0,
-            "max_score": 1.0
+            "min_score": 0,
+            "max_score": 1
           },
           "score_details": {
-            "score": 0.2923
-          }
-        },
-        {
-          "evaluation_name": "Easy Problems",
+            "score": 0.8873239436619719
+          },
           "source_data": {
             "dataset_name": "Easy Problems",
             "source_type": "url",
             "url": [
               "https://webhook.cp-bench.orzzh.com/leaderboard/llm/difficulty?difficulty=easy&benchmark_mode=live"
             ]
-          },
-          "metric_config": {
-            "evaluation_description": "Pass@1 on Easy Problems",
-            "lower_is_better": false,
-            "score_type": "continuous",
-            "min_score": 0.0,
-            "max_score": 1.0
-          },
-          "score_details": {
-            "score": 0.8571
           }
         }
       ],
@@ -828,13 +828,13 @@
       "generation_config": null
     },
     {
-      "evaluation_id": "livecodebenchpro/o4-mini-2025-04-16/1760492095.8105888",
-      "retrieved_timestamp": "1760492095.8105888",
+      "evaluation_id": "livecodebenchpro/o4-mini-2025-04-16/1770683238.099205",
+      "retrieved_timestamp": "1770683238.099205",
       "source_metadata": {
-        "source_organization_name": "New York University,  Princeton University, University of California San Diego, University of Washington and Canyon Crest Academy",
-        "evaluator_relationship": "third_party",
         "source_name": "Live Code Bench Pro",
-        "source_type": "documentation"
+        "source_type": "documentation",
+        "source_organization_name": "New York University, Princeton University, University of California San Diego, University of Washington and Canyon Crest Academy",
+        "evaluator_relationship": "third_party"
       },
       "eval_library": {
         "name": "unknown",
@@ -844,62 +844,62 @@
       "evaluation_results": [
         {
           "evaluation_name": "Hard Problems",
-          "metric_config": {
-            "evaluation_description": "Pass@1 on Hard Problems",
-            "lower_is_better": false,
-            "score_type": "continuous",
-            "min_score": 0,
-            "max_score": 1
-          },
-          "score_details": {
-            "score": 0.014084507042253521
-          },
           "source_data": {
             "dataset_name": "Hard Problems",
             "source_type": "url",
             "url": [
               "https://webhook.cp-bench.orzzh.com/leaderboard/llm/difficulty?difficulty=hard&benchmark_mode=live"
             ]
-          }
-        },
-        {
-          "evaluation_name": "Medium Problems",
+          },
           "metric_config": {
-            "evaluation_description": "Pass@1 on Medium Problems",
+            "evaluation_description": "Pass@1 on Hard Problems",
             "lower_is_better": false,
             "score_type": "continuous",
-            "min_score": 0,
-            "max_score": 1
+            "min_score": 0.0,
+            "max_score": 1.0
           },
           "score_details": {
-            "score": 0.30985915492957744
-          },
+            "score": 0.0143
+          }
+        },
+        {
+          "evaluation_name": "Medium Problems",
           "source_data": {
             "dataset_name": "Medium Problems",
             "source_type": "url",
             "url": [
               "https://webhook.cp-bench.orzzh.com/leaderboard/llm/difficulty?difficulty=medium&benchmark_mode=live"
             ]
-          }
-        },
-        {
-          "evaluation_name": "Easy Problems",
+          },
           "metric_config": {
-            "evaluation_description": "Pass@1 on Easy Problems",
+            "evaluation_description": "Pass@1 on Medium Problems",
             "lower_is_better": false,
             "score_type": "continuous",
-            "min_score": 0,
-            "max_score": 1
+            "min_score": 0.0,
+            "max_score": 1.0
           },
           "score_details": {
-            "score": 0.8873239436619719
-          },
+            "score": 0.2923
+          }
+        },
+        {
+          "evaluation_name": "Easy Problems",
           "source_data": {
             "dataset_name": "Easy Problems",
             "source_type": "url",
             "url": [
               "https://webhook.cp-bench.orzzh.com/leaderboard/llm/difficulty?difficulty=easy&benchmark_mode=live"
             ]
+          },
+          "metric_config": {
+            "evaluation_description": "Pass@1 on Easy Problems",
+            "lower_is_better": false,
+            "score_type": "continuous",
+            "min_score": 0.0,
+            "max_score": 1.0
+          },
+          "score_details": {
+            "score": 0.8571
           }
         }
       ],
diff --git a/data/models/openbmb_eurus-rm-7b.json b/data/models/openbmb_eurus-rm-7b.json
index e1154a660c89f219cec7ec844602d9d8fdfa08ad..44637ca17276f082725f61866dcfa3229cc54274 100644
--- a/data/models/openbmb_eurus-rm-7b.json
+++ b/data/models/openbmb_eurus-rm-7b.json
@@ -9,10 +9,10 @@
   },
   "evaluations": [
     {
-      "evaluation_id": "reward-bench-2/openbmb_Eurus-RM-7b/1766412838.146816",
+      "evaluation_id": "reward-bench/openbmb_Eurus-RM-7b/1766412838.146816",
       "retrieved_timestamp": "1766412838.146816",
       "source_metadata": {
-        "source_name": "RewardBench 2",
+        "source_name": "RewardBench",
         "source_type": "documentation",
         "source_organization_name": "Allen Institute for AI",
         "source_organization_url": "https://allenai.org",
@@ -31,127 +31,109 @@
         {
           "evaluation_name": "Score",
           "metric_config": {
-            "evaluation_description": "Overall RewardBench 2 Score (mean of all metrics)",
-            "lower_is_better": false,
-            "score_type": "continuous",
-            "min_score": 0.0,
-            "max_score": 1.0
-          },
-          "score_details": {
-            "score": 0.5806
-          },
-          "source_data": {
-            "dataset_name": "RewardBench 2",
-            "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
-          }
-        },
-        {
-          "evaluation_name": "Factuality",
-          "metric_config": {
-            "evaluation_description": "Factuality score - measures factual accuracy",
+            "evaluation_description": "Overall RewardBench Score",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6
+            "score": 0.8159
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Precise IF",
+          "evaluation_name": "Chat",
           "metric_config": {
-            "evaluation_description": "Precise Instruction Following score",
+            "evaluation_description": "Chat accuracy - includes easy chat subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3438
+            "score": 0.9804
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Math",
+          "evaluation_name": "Chat Hard",
           "metric_config": {
-            "evaluation_description": "Math score - measures mathematical reasoning",
+            "evaluation_description": "Chat Hard accuracy - includes hard chat subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5683
+            "score": 0.6557
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
           "evaluation_name": "Safety",
           "metric_config": {
-            "evaluation_description": "Safety score - measures safety awareness",
+            "evaluation_description": "Safety accuracy - includes safety subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6267
+            "score": 0.8135
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Focus",
+          "evaluation_name": "Reasoning",
           "metric_config": {
-            "evaluation_description": "Focus score - measures response focus",
+            "evaluation_description": "Reasoning accuracy - includes code and math subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7475
+            "score": 0.8633
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Ties",
+          "evaluation_name": "Prior Sets (0.5 weight)",
           "metric_config": {
-            "evaluation_description": "Ties score - ability to identify tie cases",
+            "evaluation_description": "Prior Sets score (weighted 0.5) - includes test sets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5972
+            "score": 0.7172
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         }
       ],
@@ -159,10 +141,10 @@
       "generation_config": null
     },
     {
-      "evaluation_id": "reward-bench/openbmb_Eurus-RM-7b/1766412838.146816",
+      "evaluation_id": "reward-bench-2/openbmb_Eurus-RM-7b/1766412838.146816",
       "retrieved_timestamp": "1766412838.146816",
       "source_metadata": {
-        "source_name": "RewardBench",
+        "source_name": "RewardBench 2",
         "source_type": "documentation",
         "source_organization_name": "Allen Institute for AI",
         "source_organization_url": "https://allenai.org",
@@ -181,109 +163,127 @@
         {
           "evaluation_name": "Score",
           "metric_config": {
-            "evaluation_description": "Overall RewardBench Score",
+            "evaluation_description": "Overall RewardBench 2 Score (mean of all metrics)",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.8159
+            "score": 0.5806
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Chat",
+          "evaluation_name": "Factuality",
           "metric_config": {
-            "evaluation_description": "Chat accuracy - includes easy chat subsets",
+            "evaluation_description": "Factuality score - measures factual accuracy",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9804
+            "score": 0.6
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Chat Hard",
+          "evaluation_name": "Precise IF",
           "metric_config": {
-            "evaluation_description": "Chat Hard accuracy - includes hard chat subsets",
+            "evaluation_description": "Precise Instruction Following score",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6557
+            "score": 0.3438
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
+          }
+        },
+        {
+          "evaluation_name": "Math",
+          "metric_config": {
+            "evaluation_description": "Math score - measures mathematical reasoning",
+            "lower_is_better": false,
+            "score_type": "continuous",
+            "min_score": 0.0,
+            "max_score": 1.0
+          },
+          "score_details": {
+            "score": 0.5683
+          },
+          "source_data": {
+            "dataset_name": "RewardBench 2",
+            "source_type": "hf_dataset",
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
           "evaluation_name": "Safety",
           "metric_config": {
-            "evaluation_description": "Safety accuracy - includes safety subsets",
+            "evaluation_description": "Safety score - measures safety awareness",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.8135
+            "score": 0.6267
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Reasoning",
+          "evaluation_name": "Focus",
           "metric_config": {
-            "evaluation_description": "Reasoning accuracy - includes code and math subsets",
+            "evaluation_description": "Focus score - measures response focus",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.8633
+            "score": 0.7475
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Prior Sets (0.5 weight)",
+          "evaluation_name": "Ties",
           "metric_config": {
-            "evaluation_description": "Prior Sets score (weighted 0.5) - includes test sets",
+            "evaluation_description": "Ties score - ability to identify tie cases",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7172
+            "score": 0.5972
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         }
       ],
diff --git a/data/models/openbmb_ultrarm-13b.json b/data/models/openbmb_ultrarm-13b.json
index 84bdd483e26f91976f0250093c6ea14b4f0ff97c..c52a509adb327ccd9798d5a844c78601940ebb17 100644
--- a/data/models/openbmb_ultrarm-13b.json
+++ b/data/models/openbmb_ultrarm-13b.json
@@ -9,10 +9,10 @@
   },
   "evaluations": [
     {
-      "evaluation_id": "reward-bench/openbmb_UltraRM-13b/1766412838.146816",
+      "evaluation_id": "reward-bench-2/openbmb_UltraRM-13b/1766412838.146816",
       "retrieved_timestamp": "1766412838.146816",
       "source_metadata": {
-        "source_name": "RewardBench",
+        "source_name": "RewardBench 2",
         "source_type": "documentation",
         "source_organization_name": "Allen Institute for AI",
         "source_organization_url": "https://allenai.org",
@@ -31,109 +31,127 @@
         {
           "evaluation_name": "Score",
           "metric_config": {
-            "evaluation_description": "Overall RewardBench Score",
+            "evaluation_description": "Overall RewardBench 2 Score (mean of all metrics)",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6903
+            "score": 0.4683
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Chat",
+          "evaluation_name": "Factuality",
           "metric_config": {
-            "evaluation_description": "Chat accuracy - includes easy chat subsets",
+            "evaluation_description": "Factuality score - measures factual accuracy",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9637
+            "score": 0.5063
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Chat Hard",
+          "evaluation_name": "Precise IF",
           "metric_config": {
-            "evaluation_description": "Chat Hard accuracy - includes hard chat subsets",
+            "evaluation_description": "Precise Instruction Following score",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5548
+            "score": 0.3312
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
+          }
+        },
+        {
+          "evaluation_name": "Math",
+          "metric_config": {
+            "evaluation_description": "Math score - measures mathematical reasoning",
+            "lower_is_better": false,
+            "score_type": "continuous",
+            "min_score": 0.0,
+            "max_score": 1.0
+          },
+          "score_details": {
+            "score": 0.5519
+          },
+          "source_data": {
+            "dataset_name": "RewardBench 2",
+            "source_type": "hf_dataset",
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
           "evaluation_name": "Safety",
           "metric_config": {
-            "evaluation_description": "Safety accuracy - includes safety subsets",
+            "evaluation_description": "Safety score - measures safety awareness",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5986
+            "score": 0.5089
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Reasoning",
+          "evaluation_name": "Focus",
           "metric_config": {
-            "evaluation_description": "Reasoning accuracy - includes code and math subsets",
+            "evaluation_description": "Focus score - measures response focus",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6244
+            "score": 0.6081
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Prior Sets (0.5 weight)",
+          "evaluation_name": "Ties",
           "metric_config": {
-            "evaluation_description": "Prior Sets score (weighted 0.5) - includes test sets",
+            "evaluation_description": "Ties score - ability to identify tie cases",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7294
+            "score": 0.3036
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         }
       ],
@@ -141,10 +159,10 @@
       "generation_config": null
     },
     {
-      "evaluation_id": "reward-bench-2/openbmb_UltraRM-13b/1766412838.146816",
+      "evaluation_id": "reward-bench/openbmb_UltraRM-13b/1766412838.146816",
       "retrieved_timestamp": "1766412838.146816",
       "source_metadata": {
-        "source_name": "RewardBench 2",
+        "source_name": "RewardBench",
         "source_type": "documentation",
         "source_organization_name": "Allen Institute for AI",
         "source_organization_url": "https://allenai.org",
@@ -163,127 +181,109 @@
         {
           "evaluation_name": "Score",
           "metric_config": {
-            "evaluation_description": "Overall RewardBench 2 Score (mean of all metrics)",
-            "lower_is_better": false,
-            "score_type": "continuous",
-            "min_score": 0.0,
-            "max_score": 1.0
-          },
-          "score_details": {
-            "score": 0.4683
-          },
-          "source_data": {
-            "dataset_name": "RewardBench 2",
-            "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
-          }
-        },
-        {
-          "evaluation_name": "Factuality",
-          "metric_config": {
-            "evaluation_description": "Factuality score - measures factual accuracy",
+            "evaluation_description": "Overall RewardBench Score",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5063
+            "score": 0.6903
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Precise IF",
+          "evaluation_name": "Chat",
           "metric_config": {
-            "evaluation_description": "Precise Instruction Following score",
+            "evaluation_description": "Chat accuracy - includes easy chat subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3312
+            "score": 0.9637
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Math",
+          "evaluation_name": "Chat Hard",
           "metric_config": {
-            "evaluation_description": "Math score - measures mathematical reasoning",
+            "evaluation_description": "Chat Hard accuracy - includes hard chat subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5519
+            "score": 0.5548
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
           "evaluation_name": "Safety",
           "metric_config": {
-            "evaluation_description": "Safety score - measures safety awareness",
+            "evaluation_description": "Safety accuracy - includes safety subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5089
+            "score": 0.5986
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Focus",
+          "evaluation_name": "Reasoning",
           "metric_config": {
-            "evaluation_description": "Focus score - measures response focus",
+            "evaluation_description": "Reasoning accuracy - includes code and math subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6081
+            "score": 0.6244
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Ties",
+          "evaluation_name": "Prior Sets (0.5 weight)",
           "metric_config": {
-            "evaluation_description": "Ties score - ability to identify tie cases",
+            "evaluation_description": "Prior Sets score (weighted 0.5) - includes test sets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3036
+            "score": 0.7294
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         }
       ],
diff --git a/data/models/pku-alignment_beaver-7b-v1.0-cost.json b/data/models/pku-alignment_beaver-7b-v1.0-cost.json
index 3777eba3edfdc470c669a503ac85994bf8139135..8e786484059e3101c1249c1cce8c4b2be81faa5a 100644
--- a/data/models/pku-alignment_beaver-7b-v1.0-cost.json
+++ b/data/models/pku-alignment_beaver-7b-v1.0-cost.json
@@ -9,10 +9,10 @@
   },
   "evaluations": [
     {
-      "evaluation_id": "reward-bench-2/PKU-Alignment_beaver-7b-v1.0-cost/1766412838.146816",
+      "evaluation_id": "reward-bench/PKU-Alignment_beaver-7b-v1.0-cost/1766412838.146816",
       "retrieved_timestamp": "1766412838.146816",
       "source_metadata": {
-        "source_name": "RewardBench 2",
+        "source_name": "RewardBench",
         "source_type": "documentation",
         "source_organization_name": "Allen Institute for AI",
         "source_organization_url": "https://allenai.org",
@@ -31,127 +31,109 @@
         {
           "evaluation_name": "Score",
           "metric_config": {
-            "evaluation_description": "Overall RewardBench 2 Score (mean of all metrics)",
-            "lower_is_better": false,
-            "score_type": "continuous",
-            "min_score": 0.0,
-            "max_score": 1.0
-          },
-          "score_details": {
-            "score": 0.3332
-          },
-          "source_data": {
-            "dataset_name": "RewardBench 2",
-            "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
-          }
-        },
-        {
-          "evaluation_name": "Factuality",
-          "metric_config": {
-            "evaluation_description": "Factuality score - measures factual accuracy",
+            "evaluation_description": "Overall RewardBench Score",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3263
+            "score": 0.5798
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Precise IF",
+          "evaluation_name": "Chat",
           "metric_config": {
-            "evaluation_description": "Precise Instruction Following score",
+            "evaluation_description": "Chat accuracy - includes easy chat subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2313
+            "score": 0.6173
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Math",
+          "evaluation_name": "Chat Hard",
           "metric_config": {
-            "evaluation_description": "Math score - measures mathematical reasoning",
+            "evaluation_description": "Chat Hard accuracy - includes hard chat subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3989
+            "score": 0.4232
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
           "evaluation_name": "Safety",
           "metric_config": {
-            "evaluation_description": "Safety score - measures safety awareness",
+            "evaluation_description": "Safety accuracy - includes safety subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7589
+            "score": 0.7351
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Focus",
+          "evaluation_name": "Reasoning",
           "metric_config": {
-            "evaluation_description": "Focus score - measures response focus",
+            "evaluation_description": "Reasoning accuracy - includes code and math subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2939
+            "score": 0.5482
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Ties",
+          "evaluation_name": "Prior Sets (0.5 weight)",
           "metric_config": {
-            "evaluation_description": "Ties score - ability to identify tie cases",
+            "evaluation_description": "Prior Sets score (weighted 0.5) - includes test sets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": -0.01
+            "score": 0.57
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         }
       ],
@@ -159,10 +141,10 @@
       "generation_config": null
     },
     {
-      "evaluation_id": "reward-bench/PKU-Alignment_beaver-7b-v1.0-cost/1766412838.146816",
+      "evaluation_id": "reward-bench-2/PKU-Alignment_beaver-7b-v1.0-cost/1766412838.146816",
       "retrieved_timestamp": "1766412838.146816",
       "source_metadata": {
-        "source_name": "RewardBench",
+        "source_name": "RewardBench 2",
         "source_type": "documentation",
         "source_organization_name": "Allen Institute for AI",
         "source_organization_url": "https://allenai.org",
@@ -181,109 +163,127 @@
         {
           "evaluation_name": "Score",
           "metric_config": {
-            "evaluation_description": "Overall RewardBench Score",
+            "evaluation_description": "Overall RewardBench 2 Score (mean of all metrics)",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5798
+            "score": 0.3332
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Chat",
+          "evaluation_name": "Factuality",
           "metric_config": {
-            "evaluation_description": "Chat accuracy - includes easy chat subsets",
+            "evaluation_description": "Factuality score - measures factual accuracy",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6173
+            "score": 0.3263
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Chat Hard",
+          "evaluation_name": "Precise IF",
           "metric_config": {
-            "evaluation_description": "Chat Hard accuracy - includes hard chat subsets",
+            "evaluation_description": "Precise Instruction Following score",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4232
+            "score": 0.2313
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
+          }
+        },
+        {
+          "evaluation_name": "Math",
+          "metric_config": {
+            "evaluation_description": "Math score - measures mathematical reasoning",
+            "lower_is_better": false,
+            "score_type": "continuous",
+            "min_score": 0.0,
+            "max_score": 1.0
+          },
+          "score_details": {
+            "score": 0.3989
+          },
+          "source_data": {
+            "dataset_name": "RewardBench 2",
+            "source_type": "hf_dataset",
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
           "evaluation_name": "Safety",
           "metric_config": {
-            "evaluation_description": "Safety accuracy - includes safety subsets",
+            "evaluation_description": "Safety score - measures safety awareness",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7351
+            "score": 0.7589
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Reasoning",
+          "evaluation_name": "Focus",
           "metric_config": {
-            "evaluation_description": "Reasoning accuracy - includes code and math subsets",
+            "evaluation_description": "Focus score - measures response focus",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5482
+            "score": 0.2939
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Prior Sets (0.5 weight)",
+          "evaluation_name": "Ties",
           "metric_config": {
-            "evaluation_description": "Prior Sets score (weighted 0.5) - includes test sets",
+            "evaluation_description": "Ties score - ability to identify tie cases",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.57
+            "score": -0.01
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         }
       ],
diff --git a/data/models/primeintellect_intellect-1.json b/data/models/primeintellect_intellect-1.json
index b8fa0710a43fde559062289de677b131f6527599..7d9ec915394b34f60309abc9ed073a5aa8bce5ab 100644
--- a/data/models/primeintellect_intellect-1.json
+++ b/data/models/primeintellect_intellect-1.json
@@ -5,7 +5,7 @@
     "developer": "PrimeIntellect",
     "inference_platform": "unknown",
     "additional_details": {
-      "precision": "bfloat16",
+      "precision": "float16",
       "architecture": "LlamaForCausalLM",
       "params_billions": "10.211"
     }
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.276
+            "score": 0.274
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2534
+            "score": 0.25
           }
         },
         {
@@ -116,7 +116,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3339
+            "score": 0.3753
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1123
+            "score": 0.112
           }
         }
       ],
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.274
+            "score": 0.276
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.25
+            "score": 0.2534
           }
         },
         {
@@ -246,7 +246,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3753
+            "score": 0.3339
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.112
+            "score": 0.1123
           }
         }
       ],
diff --git a/data/models/qingy2019_oracle-14b.json b/data/models/qingy2019_oracle-14b.json
index 8fc1dd082923a347043a18d5c18fb5d4904fae42..22bb2fc596a8b7a91dfafd1db7c00009286e84b4 100644
--- a/data/models/qingy2019_oracle-14b.json
+++ b/data/models/qingy2019_oracle-14b.json
@@ -5,7 +5,7 @@
     "developer": "qingy2019",
     "inference_platform": "unknown",
     "additional_details": {
-      "precision": "bfloat16",
+      "precision": "float16",
       "architecture": "MixtralForCausalLM",
       "params_billions": "13.668"
     }
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2401
+            "score": 0.2358
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4622
+            "score": 0.4612
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0725
+            "score": 0.0642
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2609
+            "score": 0.2576
           }
         },
         {
@@ -116,7 +116,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3703
+            "score": 0.3717
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2379
+            "score": 0.2382
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2358
+            "score": 0.2401
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4612
+            "score": 0.4622
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0642
+            "score": 0.0725
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2576
+            "score": 0.2609
           }
         },
         {
@@ -246,7 +246,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3717
+            "score": 0.3703
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2382
+            "score": 0.2379
           }
         }
       ],
diff --git a/data/models/qingy2019_qwen2.5-math-14b-instruct.json b/data/models/qingy2019_qwen2.5-math-14b-instruct.json
index 21a12461d0cce8974037575db54605a0da19b661..d07b0024c79975f453423bba6d277d902ff3056c 100644
--- a/data/models/qingy2019_qwen2.5-math-14b-instruct.json
+++ b/data/models/qingy2019_qwen2.5-math-14b-instruct.json
@@ -5,7 +5,7 @@
     "developer": "qingy2019",
     "inference_platform": "unknown",
     "additional_details": {
-      "precision": "bfloat16",
+      "precision": "float16",
       "architecture": "Qwen2ForCausalLM",
       "params_billions": "14.0"
     }
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6005
+            "score": 0.6066
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6356
+            "score": 0.635
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2764
+            "score": 0.3716
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3691
+            "score": 0.3725
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5339
+            "score": 0.5331
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6066
+            "score": 0.6005
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.635
+            "score": 0.6356
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3716
+            "score": 0.2764
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3725
+            "score": 0.3691
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5331
+            "score": 0.5339
           }
         }
       ],
diff --git a/data/models/ray2333_grm-llama3-8b-distill.json b/data/models/ray2333_grm-llama3-8b-distill.json
index a698e2dc0120e472c95dbd375c2ce72c243acf20..28bee941f1d39ce464ca73210ca8cbef67a5d082 100644
--- a/data/models/ray2333_grm-llama3-8b-distill.json
+++ b/data/models/ray2333_grm-llama3-8b-distill.json
@@ -9,10 +9,10 @@
   },
   "evaluations": [
     {
-      "evaluation_id": "reward-bench/Ray2333_GRM-llama3-8B-distill/1766412838.146816",
+      "evaluation_id": "reward-bench-2/Ray2333_GRM-llama3-8B-distill/1766412838.146816",
       "retrieved_timestamp": "1766412838.146816",
       "source_metadata": {
-        "source_name": "RewardBench",
+        "source_name": "RewardBench 2",
         "source_type": "documentation",
         "source_organization_name": "Allen Institute for AI",
         "source_organization_url": "https://allenai.org",
@@ -31,109 +31,127 @@
         {
           "evaluation_name": "Score",
           "metric_config": {
-            "evaluation_description": "Overall RewardBench Score",
+            "evaluation_description": "Overall RewardBench 2 Score (mean of all metrics)",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.8464
+            "score": 0.589
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Chat",
+          "evaluation_name": "Factuality",
           "metric_config": {
-            "evaluation_description": "Chat accuracy - includes easy chat subsets",
+            "evaluation_description": "Factuality score - measures factual accuracy",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9832
+            "score": 0.5874
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Chat Hard",
+          "evaluation_name": "Precise IF",
           "metric_config": {
-            "evaluation_description": "Chat Hard accuracy - includes hard chat subsets",
+            "evaluation_description": "Precise Instruction Following score",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6842
+            "score": 0.3875
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
+          }
+        },
+        {
+          "evaluation_name": "Math",
+          "metric_config": {
+            "evaluation_description": "Math score - measures mathematical reasoning",
+            "lower_is_better": false,
+            "score_type": "continuous",
+            "min_score": 0.0,
+            "max_score": 1.0
+          },
+          "score_details": {
+            "score": 0.5902
+          },
+          "source_data": {
+            "dataset_name": "RewardBench 2",
+            "source_type": "hf_dataset",
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
           "evaluation_name": "Safety",
           "metric_config": {
-            "evaluation_description": "Safety accuracy - includes safety subsets",
+            "evaluation_description": "Safety score - measures safety awareness",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.8676
+            "score": 0.7222
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Reasoning",
+          "evaluation_name": "Focus",
           "metric_config": {
-            "evaluation_description": "Reasoning accuracy - includes code and math subsets",
+            "evaluation_description": "Focus score - measures response focus",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9133
+            "score": 0.6727
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Prior Sets (0.5 weight)",
+          "evaluation_name": "Ties",
           "metric_config": {
-            "evaluation_description": "Prior Sets score (weighted 0.5) - includes test sets",
+            "evaluation_description": "Ties score - ability to identify tie cases",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7209
+            "score": 0.5743
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         }
       ],
@@ -141,10 +159,10 @@
       "generation_config": null
     },
     {
-      "evaluation_id": "reward-bench-2/Ray2333_GRM-llama3-8B-distill/1766412838.146816",
+      "evaluation_id": "reward-bench/Ray2333_GRM-llama3-8B-distill/1766412838.146816",
       "retrieved_timestamp": "1766412838.146816",
       "source_metadata": {
-        "source_name": "RewardBench 2",
+        "source_name": "RewardBench",
         "source_type": "documentation",
         "source_organization_name": "Allen Institute for AI",
         "source_organization_url": "https://allenai.org",
@@ -163,127 +181,109 @@
         {
           "evaluation_name": "Score",
           "metric_config": {
-            "evaluation_description": "Overall RewardBench 2 Score (mean of all metrics)",
-            "lower_is_better": false,
-            "score_type": "continuous",
-            "min_score": 0.0,
-            "max_score": 1.0
-          },
-          "score_details": {
-            "score": 0.589
-          },
-          "source_data": {
-            "dataset_name": "RewardBench 2",
-            "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
-          }
-        },
-        {
-          "evaluation_name": "Factuality",
-          "metric_config": {
-            "evaluation_description": "Factuality score - measures factual accuracy",
+            "evaluation_description": "Overall RewardBench Score",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5874
+            "score": 0.8464
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Precise IF",
+          "evaluation_name": "Chat",
           "metric_config": {
-            "evaluation_description": "Precise Instruction Following score",
+            "evaluation_description": "Chat accuracy - includes easy chat subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3875
+            "score": 0.9832
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Math",
+          "evaluation_name": "Chat Hard",
           "metric_config": {
-            "evaluation_description": "Math score - measures mathematical reasoning",
+            "evaluation_description": "Chat Hard accuracy - includes hard chat subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5902
+            "score": 0.6842
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
           "evaluation_name": "Safety",
           "metric_config": {
-            "evaluation_description": "Safety score - measures safety awareness",
+            "evaluation_description": "Safety accuracy - includes safety subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7222
+            "score": 0.8676
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Focus",
+          "evaluation_name": "Reasoning",
           "metric_config": {
-            "evaluation_description": "Focus score - measures response focus",
+            "evaluation_description": "Reasoning accuracy - includes code and math subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6727
+            "score": 0.9133
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Ties",
+          "evaluation_name": "Prior Sets (0.5 weight)",
           "metric_config": {
-            "evaluation_description": "Ties score - ability to identify tie cases",
+            "evaluation_description": "Prior Sets score (weighted 0.5) - includes test sets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5743
+            "score": 0.7209
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         }
       ],
diff --git a/data/models/replete-ai_replete-llm-qwen2-7b.json b/data/models/replete-ai_replete-llm-qwen2-7b.json
index e51b10d1bb4ff7d76603042a5cdf25b16b9bc87f..627d67572ee0cd0135e173767115d5ee7360b5e6 100644
--- a/data/models/replete-ai_replete-llm-qwen2-7b.json
+++ b/data/models/replete-ai_replete-llm-qwen2-7b.json
@@ -5,7 +5,7 @@
     "developer": "Replete-AI",
     "inference_platform": "unknown",
     "additional_details": {
-      "precision": "bfloat16",
+      "precision": "float16",
       "architecture": "Qwen2ForCausalLM",
       "params_billions": "7.616"
     }
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0932
+            "score": 0.0905
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2977
+            "score": 0.2985
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2475
+            "score": 0.2534
           }
         },
         {
@@ -116,7 +116,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3941
+            "score": 0.3848
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1157
+            "score": 0.1158
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0905
+            "score": 0.0932
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2985
+            "score": 0.2977
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2534
+            "score": 0.2475
           }
         },
         {
@@ -246,7 +246,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3848
+            "score": 0.3941
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1158
+            "score": 0.1157
           }
         }
       ],
diff --git a/data/models/riaz_finellama-3.1-8b.json b/data/models/riaz_finellama-3.1-8b.json
index 554fa555a5c7288aadab0b51655132daffa7eed6..926e4908b22e1e63c1ff9b2a4076f85fbbd8288e 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": "bfloat16",
+      "precision": "float16",
       "architecture": "LlamaForCausalLM",
       "params_billions": "8.03"
     }
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4373
+            "score": 0.4137
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4586
+            "score": 0.4565
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0514
+            "score": 0.0453
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2752
+            "score": 0.276
           }
         },
         {
@@ -116,7 +116,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3763
+            "score": 0.3776
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2964
+            "score": 0.2978
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4137
+            "score": 0.4373
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4565
+            "score": 0.4586
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0453
+            "score": 0.0514
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.276
+            "score": 0.2752
           }
         },
         {
@@ -246,7 +246,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3776
+            "score": 0.3763
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2978
+            "score": 0.2964
           }
         }
       ],
diff --git a/data/models/sao10k_l3-70b-euryale-v2.1.json b/data/models/sao10k_l3-70b-euryale-v2.1.json
index 66fd342cda2fcd43939fb102adcaae988f1eb857..c24d09a959df8d13e2602095ebcf1b7a3f8d330c 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": "float16",
+      "precision": "bfloat16",
       "architecture": "LlamaForCausalLM",
       "params_billions": "70.554"
     }
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7281
+            "score": 0.7384
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6503
+            "score": 0.6471
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2243
+            "score": 0.2137
           }
         },
         {
@@ -116,7 +116,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4196
+            "score": 0.4209
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5096
+            "score": 0.5104
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7384
+            "score": 0.7281
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6471
+            "score": 0.6503
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2137
+            "score": 0.2243
           }
         },
         {
@@ -246,7 +246,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4209
+            "score": 0.4196
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5104
+            "score": 0.5096
           }
         }
       ],
diff --git a/data/models/sfairxc_fsfairx-llama3-rm-v0.1.json b/data/models/sfairxc_fsfairx-llama3-rm-v0.1.json
index ecef2ed14b1e2210796bfe9e4943404f7ebd3b7c..83ff30916d3f35c6333d5f652927c45d63836756 100644
--- a/data/models/sfairxc_fsfairx-llama3-rm-v0.1.json
+++ b/data/models/sfairxc_fsfairx-llama3-rm-v0.1.json
@@ -9,10 +9,10 @@
   },
   "evaluations": [
     {
-      "evaluation_id": "reward-bench-2/sfairXC_FsfairX-LLaMA3-RM-v0.1/1766412838.146816",
+      "evaluation_id": "reward-bench/sfairXC_FsfairX-LLaMA3-RM-v0.1/1766412838.146816",
       "retrieved_timestamp": "1766412838.146816",
       "source_metadata": {
-        "source_name": "RewardBench 2",
+        "source_name": "RewardBench",
         "source_type": "documentation",
         "source_organization_name": "Allen Institute for AI",
         "source_organization_url": "https://allenai.org",
@@ -31,127 +31,109 @@
         {
           "evaluation_name": "Score",
           "metric_config": {
-            "evaluation_description": "Overall RewardBench 2 Score (mean of all metrics)",
-            "lower_is_better": false,
-            "score_type": "continuous",
-            "min_score": 0.0,
-            "max_score": 1.0
-          },
-          "score_details": {
-            "score": 0.6292
-          },
-          "source_data": {
-            "dataset_name": "RewardBench 2",
-            "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
-          }
-        },
-        {
-          "evaluation_name": "Factuality",
-          "metric_config": {
-            "evaluation_description": "Factuality score - measures factual accuracy",
+            "evaluation_description": "Overall RewardBench Score",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5916
+            "score": 0.8338
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Precise IF",
+          "evaluation_name": "Chat",
           "metric_config": {
-            "evaluation_description": "Precise Instruction Following score",
+            "evaluation_description": "Chat accuracy - includes easy chat subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4188
+            "score": 0.9944
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Math",
+          "evaluation_name": "Chat Hard",
           "metric_config": {
-            "evaluation_description": "Math score - measures mathematical reasoning",
+            "evaluation_description": "Chat Hard accuracy - includes hard chat subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6284
+            "score": 0.6513
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
           "evaluation_name": "Safety",
           "metric_config": {
-            "evaluation_description": "Safety score - measures safety awareness",
+            "evaluation_description": "Safety accuracy - includes safety subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7667
+            "score": 0.8676
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Focus",
+          "evaluation_name": "Reasoning",
           "metric_config": {
-            "evaluation_description": "Focus score - measures response focus",
+            "evaluation_description": "Reasoning accuracy - includes code and math subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7051
+            "score": 0.8644
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Ties",
+          "evaluation_name": "Prior Sets (0.5 weight)",
           "metric_config": {
-            "evaluation_description": "Ties score - ability to identify tie cases",
+            "evaluation_description": "Prior Sets score (weighted 0.5) - includes test sets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6647
+            "score": 0.7492
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         }
       ],
@@ -159,10 +141,10 @@
       "generation_config": null
     },
     {
-      "evaluation_id": "reward-bench/sfairXC_FsfairX-LLaMA3-RM-v0.1/1766412838.146816",
+      "evaluation_id": "reward-bench-2/sfairXC_FsfairX-LLaMA3-RM-v0.1/1766412838.146816",
       "retrieved_timestamp": "1766412838.146816",
       "source_metadata": {
-        "source_name": "RewardBench",
+        "source_name": "RewardBench 2",
         "source_type": "documentation",
         "source_organization_name": "Allen Institute for AI",
         "source_organization_url": "https://allenai.org",
@@ -181,109 +163,127 @@
         {
           "evaluation_name": "Score",
           "metric_config": {
-            "evaluation_description": "Overall RewardBench Score",
+            "evaluation_description": "Overall RewardBench 2 Score (mean of all metrics)",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.8338
+            "score": 0.6292
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Chat",
+          "evaluation_name": "Factuality",
           "metric_config": {
-            "evaluation_description": "Chat accuracy - includes easy chat subsets",
+            "evaluation_description": "Factuality score - measures factual accuracy",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9944
+            "score": 0.5916
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Chat Hard",
+          "evaluation_name": "Precise IF",
           "metric_config": {
-            "evaluation_description": "Chat Hard accuracy - includes hard chat subsets",
+            "evaluation_description": "Precise Instruction Following score",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6513
+            "score": 0.4188
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
+          }
+        },
+        {
+          "evaluation_name": "Math",
+          "metric_config": {
+            "evaluation_description": "Math score - measures mathematical reasoning",
+            "lower_is_better": false,
+            "score_type": "continuous",
+            "min_score": 0.0,
+            "max_score": 1.0
+          },
+          "score_details": {
+            "score": 0.6284
+          },
+          "source_data": {
+            "dataset_name": "RewardBench 2",
+            "source_type": "hf_dataset",
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
           "evaluation_name": "Safety",
           "metric_config": {
-            "evaluation_description": "Safety accuracy - includes safety subsets",
+            "evaluation_description": "Safety score - measures safety awareness",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.8676
+            "score": 0.7667
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Reasoning",
+          "evaluation_name": "Focus",
           "metric_config": {
-            "evaluation_description": "Reasoning accuracy - includes code and math subsets",
+            "evaluation_description": "Focus score - measures response focus",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.8644
+            "score": 0.7051
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Prior Sets (0.5 weight)",
+          "evaluation_name": "Ties",
           "metric_config": {
-            "evaluation_description": "Prior Sets score (weighted 0.5) - includes test sets",
+            "evaluation_description": "Ties score - ability to identify tie cases",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7492
+            "score": 0.6647
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         }
       ],
diff --git a/data/models/skywork_skywork-reward-gemma-2-27b.json b/data/models/skywork_skywork-reward-gemma-2-27b.json
index c2b742dbc17aa9720f66d090e08eb784ec7accdc..0b4cc11a7f17a4535cc37f935fdae034a6214bce 100644
--- a/data/models/skywork_skywork-reward-gemma-2-27b.json
+++ b/data/models/skywork_skywork-reward-gemma-2-27b.json
@@ -9,10 +9,10 @@
   },
   "evaluations": [
     {
-      "evaluation_id": "reward-bench-2/Skywork_Skywork-Reward-Gemma-2-27B/1766412838.146816",
+      "evaluation_id": "reward-bench/Skywork_Skywork-Reward-Gemma-2-27B/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": 0.7576
+            "score": 0.938
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "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": 0.7368
+            "score": 0.9581
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Precise IF",
+          "evaluation_name": "Chat Hard",
           "metric_config": {
-            "evaluation_description": "Precise Instruction Following score",
+            "evaluation_description": "Chat Hard accuracy - includes hard chat subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4031
+            "score": 0.9145
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "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": 0.7049
+            "score": 0.9189
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "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": 0.9422
+            "score": 0.9606
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
-        },
+        }
+      ],
+      "detailed_evaluation_results": null,
+      "generation_config": null
+    },
+    {
+      "evaluation_id": "reward-bench-2/Skywork_Skywork-Reward-Gemma-2-27B/1766412838.146816",
+      "retrieved_timestamp": "1766412838.146816",
+      "source_metadata": {
+        "source_name": "RewardBench 2",
+        "source_type": "documentation",
+        "source_organization_name": "Allen Institute for AI",
+        "source_organization_url": "https://allenai.org",
+        "evaluator_relationship": "third_party"
+      },
+      "eval_library": {
+        "name": "rewardbench",
+        "version": "0.1.3",
+        "additional_details": {
+          "subsets": "Chat, Chat Hard, Safety, Reasoning",
+          "hf_space": "allenai/reward-bench"
+        }
+      },
+      "benchmark": "reward-bench",
+      "evaluation_results": [
         {
-          "evaluation_name": "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": 0.9323
+            "score": 0.7576
           },
           "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": 0.8261
+            "score": 0.7368
           },
           "source_data": {
             "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
             "hf_repo": "allenai/reward-bench-2-results"
           }
-        }
-      ],
-      "detailed_evaluation_results": null,
-      "generation_config": null
-    },
-    {
-      "evaluation_id": "reward-bench/Skywork_Skywork-Reward-Gemma-2-27B/1766412838.146816",
-      "retrieved_timestamp": "1766412838.146816",
-      "source_metadata": {
-        "source_name": "RewardBench",
-        "source_type": "documentation",
-        "source_organization_name": "Allen Institute for AI",
-        "source_organization_url": "https://allenai.org",
-        "evaluator_relationship": "third_party"
-      },
-      "eval_library": {
-        "name": "rewardbench",
-        "version": "0.1.3",
-        "additional_details": {
-          "subsets": "Chat, Chat Hard, Safety, Reasoning",
-          "hf_space": "allenai/reward-bench"
-        }
-      },
-      "benchmark": "reward-bench",
-      "evaluation_results": [
+        },
         {
-          "evaluation_name": "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": 0.938
+            "score": 0.4031
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Chat",
+          "evaluation_name": "Math",
           "metric_config": {
-            "evaluation_description": "Chat accuracy - includes easy chat subsets",
+            "evaluation_description": "Math score - measures mathematical reasoning",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9581
+            "score": 0.7049
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "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": 0.9145
+            "score": 0.9422
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "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": 0.9189
+            "score": 0.9323
           },
           "source_data": {
-            "dataset_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": 0.9606
+            "score": 0.8261
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         }
       ],
diff --git a/data/models/skywork_skywork-reward-llama-3.1-8b.json b/data/models/skywork_skywork-reward-llama-3.1-8b.json
index dedd0015bc30c7a59cc8db5e1fbdb3b6b6cbc978..d700e3f49377a01e2f9d11b4773879e002a65e98 100644
--- a/data/models/skywork_skywork-reward-llama-3.1-8b.json
+++ b/data/models/skywork_skywork-reward-llama-3.1-8b.json
@@ -9,10 +9,10 @@
   },
   "evaluations": [
     {
-      "evaluation_id": "reward-bench/Skywork_Skywork-Reward-Llama-3.1-8B/1766412838.146816",
+      "evaluation_id": "reward-bench-2/Skywork_Skywork-Reward-Llama-3.1-8B/1766412838.146816",
       "retrieved_timestamp": "1766412838.146816",
       "source_metadata": {
-        "source_name": "RewardBench",
+        "source_name": "RewardBench 2",
         "source_type": "documentation",
         "source_organization_name": "Allen Institute for AI",
         "source_organization_url": "https://allenai.org",
@@ -31,128 +31,104 @@
         {
           "evaluation_name": "Score",
           "metric_config": {
-            "evaluation_description": "Overall RewardBench Score",
+            "evaluation_description": "Overall RewardBench 2 Score (mean of all metrics)",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9252
+            "score": 0.7314
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Chat",
+          "evaluation_name": "Factuality",
           "metric_config": {
-            "evaluation_description": "Chat accuracy - includes easy chat subsets",
+            "evaluation_description": "Factuality score - measures factual accuracy",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9581
+            "score": 0.6989
           },
           "source_data": {
-            "dataset_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": 0.8728
+            "score": 0.425
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Safety",
+          "evaluation_name": "Math",
           "metric_config": {
-            "evaluation_description": "Safety accuracy - includes safety subsets",
+            "evaluation_description": "Math score - measures mathematical reasoning",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9081
+            "score": 0.6284
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "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": 0.962
+            "score": 0.9333
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
-        }
-      ],
-      "detailed_evaluation_results": null,
-      "generation_config": null
-    },
-    {
-      "evaluation_id": "reward-bench-2/Skywork_Skywork-Reward-Llama-3.1-8B/1766412838.146816",
-      "retrieved_timestamp": "1766412838.146816",
-      "source_metadata": {
-        "source_name": "RewardBench 2",
-        "source_type": "documentation",
-        "source_organization_name": "Allen Institute for AI",
-        "source_organization_url": "https://allenai.org",
-        "evaluator_relationship": "third_party"
-      },
-      "eval_library": {
-        "name": "rewardbench",
-        "version": "0.1.3",
-        "additional_details": {
-          "subsets": "Chat, Chat Hard, Safety, Reasoning",
-          "hf_space": "allenai/reward-bench"
-        }
-      },
-      "benchmark": "reward-bench",
-      "evaluation_results": [
+        },
         {
-          "evaluation_name": "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": 0.7314
+            "score": 0.9616
           },
           "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": 0.6989
+            "score": 0.741
           },
           "source_data": {
             "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
             "hf_repo": "allenai/reward-bench-2-results"
           }
-        },
+        }
+      ],
+      "detailed_evaluation_results": null,
+      "generation_config": null
+    },
+    {
+      "evaluation_id": "reward-bench/Skywork_Skywork-Reward-Llama-3.1-8B/1766412838.146816",
+      "retrieved_timestamp": "1766412838.146816",
+      "source_metadata": {
+        "source_name": "RewardBench",
+        "source_type": "documentation",
+        "source_organization_name": "Allen Institute for AI",
+        "source_organization_url": "https://allenai.org",
+        "evaluator_relationship": "third_party"
+      },
+      "eval_library": {
+        "name": "rewardbench",
+        "version": "0.1.3",
+        "additional_details": {
+          "subsets": "Chat, Chat Hard, Safety, Reasoning",
+          "hf_space": "allenai/reward-bench"
+        }
+      },
+      "benchmark": "reward-bench",
+      "evaluation_results": [
         {
-          "evaluation_name": "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": 0.425
+            "score": 0.9252
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "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": 0.6284
+            "score": 0.9581
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Safety",
+          "evaluation_name": "Chat Hard",
           "metric_config": {
-            "evaluation_description": "Safety score - measures safety awareness",
+            "evaluation_description": "Chat Hard accuracy - includes hard chat subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9333
+            "score": 0.8728
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "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": 0.9616
+            "score": 0.9081
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Ties",
+          "evaluation_name": "Reasoning",
           "metric_config": {
-            "evaluation_description": "Ties score - ability to identify tie cases",
+            "evaluation_description": "Reasoning accuracy - includes code and math subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.741
+            "score": 0.962
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         }
       ],
diff --git a/data/models/skywork_skywork-vl-reward-7b.json b/data/models/skywork_skywork-vl-reward-7b.json
index 651d1416fd84d9618565234fc2f23befa272cb51..d1caca7afd32adac0ce3eaccc5894c6b1d1db99d 100644
--- a/data/models/skywork_skywork-vl-reward-7b.json
+++ b/data/models/skywork_skywork-vl-reward-7b.json
@@ -9,10 +9,10 @@
   },
   "evaluations": [
     {
-      "evaluation_id": "reward-bench-2/Skywork_Skywork-VL-Reward-7B/1766412838.146816",
+      "evaluation_id": "reward-bench/Skywork_Skywork-VL-Reward-7B/1766412838.146816",
       "retrieved_timestamp": "1766412838.146816",
       "source_metadata": {
-        "source_name": "RewardBench 2",
+        "source_name": "RewardBench",
         "source_type": "documentation",
         "source_organization_name": "Allen Institute for AI",
         "source_organization_url": "https://allenai.org",
@@ -31,104 +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": 0.6885
+            "score": 0.9007
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "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": 0.6063
+            "score": 0.8994
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "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": 0.875
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "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": 0.6339
+            "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": 0.8911
+            "score": 0.9176
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
-        },
+        }
+      ],
+      "detailed_evaluation_results": null,
+      "generation_config": null
+    },
+    {
+      "evaluation_id": "reward-bench-2/Skywork_Skywork-VL-Reward-7B/1766412838.146816",
+      "retrieved_timestamp": "1766412838.146816",
+      "source_metadata": {
+        "source_name": "RewardBench 2",
+        "source_type": "documentation",
+        "source_organization_name": "Allen Institute for AI",
+        "source_organization_url": "https://allenai.org",
+        "evaluator_relationship": "third_party"
+      },
+      "eval_library": {
+        "name": "rewardbench",
+        "version": "0.1.3",
+        "additional_details": {
+          "subsets": "Chat, Chat Hard, Safety, Reasoning",
+          "hf_space": "allenai/reward-bench"
+        }
+      },
+      "benchmark": "reward-bench",
+      "evaluation_results": [
         {
-          "evaluation_name": "Focus",
+          "evaluation_name": "Score",
           "metric_config": {
-            "evaluation_description": "Focus score - measures response focus",
+            "evaluation_description": "Overall RewardBench 2 Score (mean of all metrics)",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.8909
+            "score": 0.6885
           },
           "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": 0.7586
+            "score": 0.6063
           },
           "source_data": {
             "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
             "hf_repo": "allenai/reward-bench-2-results"
           }
-        }
-      ],
-      "detailed_evaluation_results": null,
-      "generation_config": null
-    },
-    {
-      "evaluation_id": "reward-bench/Skywork_Skywork-VL-Reward-7B/1766412838.146816",
-      "retrieved_timestamp": "1766412838.146816",
-      "source_metadata": {
-        "source_name": "RewardBench",
-        "source_type": "documentation",
-        "source_organization_name": "Allen Institute for AI",
-        "source_organization_url": "https://allenai.org",
-        "evaluator_relationship": "third_party"
-      },
-      "eval_library": {
-        "name": "rewardbench",
-        "version": "0.1.3",
-        "additional_details": {
-          "subsets": "Chat, Chat Hard, Safety, Reasoning",
-          "hf_space": "allenai/reward-bench"
-        }
-      },
-      "benchmark": "reward-bench",
-      "evaluation_results": [
+        },
         {
-          "evaluation_name": "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": 0.9007
+            "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": 0.8994
+            "score": 0.6339
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "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": 0.875
+            "score": 0.8911
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "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": 0.8909
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Reasoning",
+          "evaluation_name": "Ties",
           "metric_config": {
-            "evaluation_description": "Reasoning accuracy - includes code and math subsets",
+            "evaluation_description": "Ties score - ability to identify tie cases",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9176
+            "score": 0.7586
           },
           "source_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/sometimesanotion_qwenvergence-14b-v3-reason.json b/data/models/sometimesanotion_qwenvergence-14b-v3-reason.json
index a439bc62eb51d7fa9519bb2716501909fa712711..1f18d691fd936d47f7bbe51ac3217aef426c667e 100644
--- a/data/models/sometimesanotion_qwenvergence-14b-v3-reason.json
+++ b/data/models/sometimesanotion_qwenvergence-14b-v3-reason.json
@@ -5,7 +5,7 @@
     "developer": "sometimesanotion",
     "inference_platform": "unknown",
     "additional_details": {
-      "precision": "float16",
+      "precision": "bfloat16",
       "architecture": "Qwen2ForCausalLM",
       "params_billions": "14.0"
     }
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5367
+            "score": 0.5278
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6561
+            "score": 0.6557
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.358
+            "score": 0.3119
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3867
+            "score": 0.3842
           }
         },
         {
@@ -116,7 +116,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.474
+            "score": 0.4754
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5395
+            "score": 0.5396
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5278
+            "score": 0.5367
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6557
+            "score": 0.6561
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3119
+            "score": 0.358
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3842
+            "score": 0.3867
           }
         },
         {
@@ -246,7 +246,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4754
+            "score": 0.474
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5396
+            "score": 0.5395
           }
         }
       ],
diff --git a/data/models/spow12_chatwaifu_v2.0_22b.json b/data/models/spow12_chatwaifu_v2.0_22b.json
index ca25894b34b4dcd9cda648ad0e73ccd6dac87171..b7b1556be3e6af250728822417ad3ec7fa2fe00c 100644
--- a/data/models/spow12_chatwaifu_v2.0_22b.json
+++ b/data/models/spow12_chatwaifu_v2.0_22b.json
@@ -5,7 +5,7 @@
     "developer": "spow12",
     "inference_platform": "unknown",
     "additional_details": {
-      "precision": "bfloat16",
+      "precision": "float16",
       "architecture": "MistralForCausalLM",
       "params_billions": "22.247"
     }
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6517
+            "score": 0.6511
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5908
+            "score": 0.5926
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2032
+            "score": 0.1858
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3238
+            "score": 0.3247
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3812
+            "score": 0.3836
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6511
+            "score": 0.6517
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5926
+            "score": 0.5908
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1858
+            "score": 0.2032
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3247
+            "score": 0.3238
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3836
+            "score": 0.3812
           }
         }
       ],
diff --git a/data/models/tanliboy_lambda-gemma-2-9b-dpo.json b/data/models/tanliboy_lambda-gemma-2-9b-dpo.json
index 5d50cd0f56f0ac33470efc8c81f51c02a702598e..7fb384620bce09b34b0d31ff763d2b1e971d0558 100644
--- a/data/models/tanliboy_lambda-gemma-2-9b-dpo.json
+++ b/data/models/tanliboy_lambda-gemma-2-9b-dpo.json
@@ -5,7 +5,7 @@
     "developer": "tanliboy",
     "inference_platform": "unknown",
     "additional_details": {
-      "precision": "float16",
+      "precision": "bfloat16",
       "architecture": "Gemma2ForCausalLM",
       "params_billions": "9.242"
     }
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4501
+            "score": 0.1829
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5472
+            "score": 0.5488
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0944
+            "score": 0.0
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3138
+            "score": 0.3104
           }
         },
         {
@@ -116,7 +116,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4017
+            "score": 0.4056
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3792
+            "score": 0.3805
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1829
+            "score": 0.4501
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5488
+            "score": 0.5472
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0
+            "score": 0.0944
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3104
+            "score": 0.3138
           }
         },
         {
@@ -246,7 +246,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4056
+            "score": 0.4017
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3805
+            "score": 0.3792
           }
         }
       ],
diff --git a/data/models/valiantlabs_llama3.1-8b-cobalt.json b/data/models/valiantlabs_llama3.1-8b-cobalt.json
index c47cbaf67f9d28f7ee6c973b80a6e624aec4a0cc..e1d1a85c95f8deab607165ea40b9f93f0dba9c6d 100644
--- a/data/models/valiantlabs_llama3.1-8b-cobalt.json
+++ b/data/models/valiantlabs_llama3.1-8b-cobalt.json
@@ -5,7 +5,7 @@
     "developer": "ValiantLabs",
     "inference_platform": "unknown",
     "additional_details": {
-      "precision": "float16",
+      "precision": "bfloat16",
       "architecture": "LlamaForCausalLM",
       "params_billions": "8.03"
     }
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3496
+            "score": 0.7168
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4947
+            "score": 0.4911
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1269
+            "score": 0.1533
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3037
+            "score": 0.2861
           }
         },
         {
@@ -116,7 +116,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3959
+            "score": 0.3512
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3644
+            "score": 0.3663
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7168
+            "score": 0.3496
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4911
+            "score": 0.4947
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1533
+            "score": 0.1269
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2861
+            "score": 0.3037
           }
         },
         {
@@ -246,7 +246,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3512
+            "score": 0.3959
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3663
+            "score": 0.3644
           }
         }
       ],
diff --git a/data/models/valiantlabs_llama3.1-8b-shiningvaliant2.json b/data/models/valiantlabs_llama3.1-8b-shiningvaliant2.json
index f3e37b204fa779a9e21a0521a813b464c3fe641b..0736460b872bea97a209be68cef1f113fa7d9f3d 100644
--- a/data/models/valiantlabs_llama3.1-8b-shiningvaliant2.json
+++ b/data/models/valiantlabs_llama3.1-8b-shiningvaliant2.json
@@ -5,7 +5,7 @@
     "developer": "ValiantLabs",
     "inference_platform": "unknown",
     "additional_details": {
-      "precision": "bfloat16",
+      "precision": "float16",
       "architecture": "LlamaForCausalLM",
       "params_billions": "8.03"
     }
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6496
+            "score": 0.2678
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4774
+            "score": 0.4429
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0566
+            "score": 0.0521
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3104
+            "score": 0.302
           }
         },
         {
@@ -116,7 +116,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3909
+            "score": 0.3959
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3382
+            "score": 0.2927
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2678
+            "score": 0.6496
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4429
+            "score": 0.4774
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0521
+            "score": 0.0566
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.302
+            "score": 0.3104
           }
         },
         {
@@ -246,7 +246,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3959
+            "score": 0.3909
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2927
+            "score": 0.3382
           }
         }
       ],
diff --git a/data/models/weqweasdas_hh_rlhf_rm_open_llama_3b.json b/data/models/weqweasdas_hh_rlhf_rm_open_llama_3b.json
index 564c2ceeb0768d947ec7e8507c351558f76e3907..f9d2b14f0a0f79f11e39957c0f38b89aa1e78ac9 100644
--- a/data/models/weqweasdas_hh_rlhf_rm_open_llama_3b.json
+++ b/data/models/weqweasdas_hh_rlhf_rm_open_llama_3b.json
@@ -9,10 +9,10 @@
   },
   "evaluations": [
     {
-      "evaluation_id": "reward-bench-2/weqweasdas_hh_rlhf_rm_open_llama_3b/1766412838.146816",
+      "evaluation_id": "reward-bench/weqweasdas_hh_rlhf_rm_open_llama_3b/1766412838.146816",
       "retrieved_timestamp": "1766412838.146816",
       "source_metadata": {
-        "source_name": "RewardBench 2",
+        "source_name": "RewardBench",
         "source_type": "documentation",
         "source_organization_name": "Allen Institute for AI",
         "source_organization_url": "https://allenai.org",
@@ -31,127 +31,109 @@
         {
           "evaluation_name": "Score",
           "metric_config": {
-            "evaluation_description": "Overall RewardBench 2 Score (mean of all metrics)",
-            "lower_is_better": false,
-            "score_type": "continuous",
-            "min_score": 0.0,
-            "max_score": 1.0
-          },
-          "score_details": {
-            "score": 0.2498
-          },
-          "source_data": {
-            "dataset_name": "RewardBench 2",
-            "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
-          }
-        },
-        {
-          "evaluation_name": "Factuality",
-          "metric_config": {
-            "evaluation_description": "Factuality score - measures factual accuracy",
+            "evaluation_description": "Overall RewardBench Score",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3642
+            "score": 0.5027
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Precise IF",
+          "evaluation_name": "Chat",
           "metric_config": {
-            "evaluation_description": "Precise Instruction Following score",
+            "evaluation_description": "Chat accuracy - includes easy chat subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.275
+            "score": 0.8184
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Math",
+          "evaluation_name": "Chat Hard",
           "metric_config": {
-            "evaluation_description": "Math score - measures mathematical reasoning",
+            "evaluation_description": "Chat Hard accuracy - includes hard chat subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3497
+            "score": 0.3728
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
           "evaluation_name": "Safety",
           "metric_config": {
-            "evaluation_description": "Safety score - measures safety awareness",
+            "evaluation_description": "Safety accuracy - includes safety subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.24
+            "score": 0.4149
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Focus",
+          "evaluation_name": "Reasoning",
           "metric_config": {
-            "evaluation_description": "Focus score - measures response focus",
+            "evaluation_description": "Reasoning accuracy - includes code and math subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2384
+            "score": 0.3281
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Ties",
+          "evaluation_name": "Prior Sets (0.5 weight)",
           "metric_config": {
-            "evaluation_description": "Ties score - ability to identify tie cases",
+            "evaluation_description": "Prior Sets score (weighted 0.5) - includes test sets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0315
+            "score": 0.6564
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         }
       ],
@@ -159,10 +141,10 @@
       "generation_config": null
     },
     {
-      "evaluation_id": "reward-bench/weqweasdas_hh_rlhf_rm_open_llama_3b/1766412838.146816",
+      "evaluation_id": "reward-bench-2/weqweasdas_hh_rlhf_rm_open_llama_3b/1766412838.146816",
       "retrieved_timestamp": "1766412838.146816",
       "source_metadata": {
-        "source_name": "RewardBench",
+        "source_name": "RewardBench 2",
         "source_type": "documentation",
         "source_organization_name": "Allen Institute for AI",
         "source_organization_url": "https://allenai.org",
@@ -181,109 +163,127 @@
         {
           "evaluation_name": "Score",
           "metric_config": {
-            "evaluation_description": "Overall RewardBench Score",
+            "evaluation_description": "Overall RewardBench 2 Score (mean of all metrics)",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5027
+            "score": 0.2498
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Chat",
+          "evaluation_name": "Factuality",
           "metric_config": {
-            "evaluation_description": "Chat accuracy - includes easy chat subsets",
+            "evaluation_description": "Factuality score - measures factual accuracy",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.8184
+            "score": 0.3642
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Chat Hard",
+          "evaluation_name": "Precise IF",
           "metric_config": {
-            "evaluation_description": "Chat Hard accuracy - includes hard chat subsets",
+            "evaluation_description": "Precise Instruction Following score",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3728
+            "score": 0.275
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
+          }
+        },
+        {
+          "evaluation_name": "Math",
+          "metric_config": {
+            "evaluation_description": "Math score - measures mathematical reasoning",
+            "lower_is_better": false,
+            "score_type": "continuous",
+            "min_score": 0.0,
+            "max_score": 1.0
+          },
+          "score_details": {
+            "score": 0.3497
+          },
+          "source_data": {
+            "dataset_name": "RewardBench 2",
+            "source_type": "hf_dataset",
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
           "evaluation_name": "Safety",
           "metric_config": {
-            "evaluation_description": "Safety accuracy - includes safety subsets",
+            "evaluation_description": "Safety score - measures safety awareness",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4149
+            "score": 0.24
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Reasoning",
+          "evaluation_name": "Focus",
           "metric_config": {
-            "evaluation_description": "Reasoning accuracy - includes code and math subsets",
+            "evaluation_description": "Focus score - measures response focus",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3281
+            "score": 0.2384
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Prior Sets (0.5 weight)",
+          "evaluation_name": "Ties",
           "metric_config": {
-            "evaluation_description": "Prior Sets score (weighted 0.5) - includes test sets",
+            "evaluation_description": "Ties score - ability to identify tie cases",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6564
+            "score": 0.0315
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         }
       ],
diff --git a/data/models/weqweasdas_rm-gemma-2b.json b/data/models/weqweasdas_rm-gemma-2b.json
index 23bdb9776ed416ae7ab56cbae8b9e5655ba27e0c..b1151d30882a530616e4e5f2252a198e5a25a8a2 100644
--- a/data/models/weqweasdas_rm-gemma-2b.json
+++ b/data/models/weqweasdas_rm-gemma-2b.json
@@ -9,10 +9,10 @@
   },
   "evaluations": [
     {
-      "evaluation_id": "reward-bench/weqweasdas_RM-Gemma-2B/1766412838.146816",
+      "evaluation_id": "reward-bench-2/weqweasdas_RM-Gemma-2B/1766412838.146816",
       "retrieved_timestamp": "1766412838.146816",
       "source_metadata": {
-        "source_name": "RewardBench",
+        "source_name": "RewardBench 2",
         "source_type": "documentation",
         "source_organization_name": "Allen Institute for AI",
         "source_organization_url": "https://allenai.org",
@@ -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": 0.6549
+            "score": 0.3057
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Chat",
+          "evaluation_name": "Factuality",
           "metric_config": {
-            "evaluation_description": "Chat accuracy - includes easy chat subsets",
+            "evaluation_description": "Factuality score - measures factual accuracy",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9441
+            "score": 0.3705
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Chat Hard",
+          "evaluation_name": "Precise IF",
           "metric_config": {
-            "evaluation_description": "Chat Hard accuracy - includes hard chat subsets",
+            "evaluation_description": "Precise Instruction Following score",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4079
+            "score": 0.2812
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
+          }
+        },
+        {
+          "evaluation_name": "Math",
+          "metric_config": {
+            "evaluation_description": "Math score - measures mathematical reasoning",
+            "lower_is_better": false,
+            "score_type": "continuous",
+            "min_score": 0.0,
+            "max_score": 1.0
+          },
+          "score_details": {
+            "score": 0.4317
+          },
+          "source_data": {
+            "dataset_name": "RewardBench 2",
+            "source_type": "hf_dataset",
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
           "evaluation_name": "Safety",
           "metric_config": {
-            "evaluation_description": "Safety accuracy - includes safety subsets",
+            "evaluation_description": "Safety score - measures safety awareness",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4986
+            "score": 0.3311
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Reasoning",
+          "evaluation_name": "Focus",
           "metric_config": {
-            "evaluation_description": "Reasoning accuracy - includes code and math subsets",
+            "evaluation_description": "Focus score - measures response focus",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7637
+            "score": 0.2343
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Prior Sets (0.5 weight)",
+          "evaluation_name": "Ties",
           "metric_config": {
-            "evaluation_description": "Prior Sets score (weighted 0.5) - includes test sets",
+            "evaluation_description": "Ties score - ability to identify tie cases",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6652
+            "score": 0.1851
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         }
       ],
@@ -141,10 +159,10 @@
       "generation_config": null
     },
     {
-      "evaluation_id": "reward-bench-2/weqweasdas_RM-Gemma-2B/1766412838.146816",
+      "evaluation_id": "reward-bench/weqweasdas_RM-Gemma-2B/1766412838.146816",
       "retrieved_timestamp": "1766412838.146816",
       "source_metadata": {
-        "source_name": "RewardBench 2",
+        "source_name": "RewardBench",
         "source_type": "documentation",
         "source_organization_name": "Allen Institute for AI",
         "source_organization_url": "https://allenai.org",
@@ -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": 0.3057
-          },
-          "source_data": {
-            "dataset_name": "RewardBench 2",
-            "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
-          }
-        },
-        {
-          "evaluation_name": "Factuality",
-          "metric_config": {
-            "evaluation_description": "Factuality score - measures factual accuracy",
+            "evaluation_description": "Overall RewardBench Score",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3705
+            "score": 0.6549
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Precise IF",
+          "evaluation_name": "Chat",
           "metric_config": {
-            "evaluation_description": "Precise Instruction Following score",
+            "evaluation_description": "Chat accuracy - includes easy chat subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2812
+            "score": 0.9441
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Math",
+          "evaluation_name": "Chat Hard",
           "metric_config": {
-            "evaluation_description": "Math score - measures mathematical reasoning",
+            "evaluation_description": "Chat Hard accuracy - includes hard chat subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4317
+            "score": 0.4079
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
           "evaluation_name": "Safety",
           "metric_config": {
-            "evaluation_description": "Safety score - measures safety awareness",
+            "evaluation_description": "Safety accuracy - includes safety subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3311
+            "score": 0.4986
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Focus",
+          "evaluation_name": "Reasoning",
           "metric_config": {
-            "evaluation_description": "Focus score - measures response focus",
+            "evaluation_description": "Reasoning accuracy - includes code and math subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.2343
+            "score": 0.7637
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Ties",
+          "evaluation_name": "Prior Sets (0.5 weight)",
           "metric_config": {
-            "evaluation_description": "Ties score - ability to identify tie cases",
+            "evaluation_description": "Prior Sets score (weighted 0.5) - includes test sets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.1851
+            "score": 0.6652
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         }
       ],
diff --git a/data/models/weqweasdas_rm-mistral-7b.json b/data/models/weqweasdas_rm-mistral-7b.json
index 014b8589e308fa2571a3ca85971364da616341ae..2c0c95b4657b4530753b94c6c05b68b220f49072 100644
--- a/data/models/weqweasdas_rm-mistral-7b.json
+++ b/data/models/weqweasdas_rm-mistral-7b.json
@@ -9,10 +9,10 @@
   },
   "evaluations": [
     {
-      "evaluation_id": "reward-bench/weqweasdas_RM-Mistral-7B/1766412838.146816",
+      "evaluation_id": "reward-bench-2/weqweasdas_RM-Mistral-7B/1766412838.146816",
       "retrieved_timestamp": "1766412838.146816",
       "source_metadata": {
-        "source_name": "RewardBench",
+        "source_name": "RewardBench 2",
         "source_type": "documentation",
         "source_organization_name": "Allen Institute for AI",
         "source_organization_url": "https://allenai.org",
@@ -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": 0.7982
+            "score": 0.596
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Chat",
+          "evaluation_name": "Factuality",
           "metric_config": {
-            "evaluation_description": "Chat accuracy - includes easy chat subsets",
+            "evaluation_description": "Factuality score - measures factual accuracy",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.9665
+            "score": 0.5937
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Chat Hard",
+          "evaluation_name": "Precise IF",
           "metric_config": {
-            "evaluation_description": "Chat Hard accuracy - includes hard chat subsets",
+            "evaluation_description": "Precise Instruction Following score",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6053
+            "score": 0.3438
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
+          }
+        },
+        {
+          "evaluation_name": "Math",
+          "metric_config": {
+            "evaluation_description": "Math score - measures mathematical reasoning",
+            "lower_is_better": false,
+            "score_type": "continuous",
+            "min_score": 0.0,
+            "max_score": 1.0
+          },
+          "score_details": {
+            "score": 0.5956
+          },
+          "source_data": {
+            "dataset_name": "RewardBench 2",
+            "source_type": "hf_dataset",
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
           "evaluation_name": "Safety",
           "metric_config": {
-            "evaluation_description": "Safety accuracy - includes safety subsets",
+            "evaluation_description": "Safety score - measures safety awareness",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.8703
+            "score": 0.6911
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Reasoning",
+          "evaluation_name": "Focus",
           "metric_config": {
-            "evaluation_description": "Reasoning accuracy - includes code and math subsets",
+            "evaluation_description": "Focus score - measures response focus",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7736
+            "score": 0.7293
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         },
         {
-          "evaluation_name": "Prior Sets (0.5 weight)",
+          "evaluation_name": "Ties",
           "metric_config": {
-            "evaluation_description": "Prior Sets score (weighted 0.5) - includes test sets",
+            "evaluation_description": "Ties score - ability to identify tie cases",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.753
+            "score": 0.6226
           },
           "source_data": {
-            "dataset_name": "RewardBench",
+            "dataset_name": "RewardBench 2",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench"
+            "hf_repo": "allenai/reward-bench-2-results"
           }
         }
       ],
@@ -141,10 +159,10 @@
       "generation_config": null
     },
     {
-      "evaluation_id": "reward-bench-2/weqweasdas_RM-Mistral-7B/1766412838.146816",
+      "evaluation_id": "reward-bench/weqweasdas_RM-Mistral-7B/1766412838.146816",
       "retrieved_timestamp": "1766412838.146816",
       "source_metadata": {
-        "source_name": "RewardBench 2",
+        "source_name": "RewardBench",
         "source_type": "documentation",
         "source_organization_name": "Allen Institute for AI",
         "source_organization_url": "https://allenai.org",
@@ -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": 0.596
-          },
-          "source_data": {
-            "dataset_name": "RewardBench 2",
-            "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
-          }
-        },
-        {
-          "evaluation_name": "Factuality",
-          "metric_config": {
-            "evaluation_description": "Factuality score - measures factual accuracy",
+            "evaluation_description": "Overall RewardBench Score",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5937
+            "score": 0.7982
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Precise IF",
+          "evaluation_name": "Chat",
           "metric_config": {
-            "evaluation_description": "Precise Instruction Following score",
+            "evaluation_description": "Chat accuracy - includes easy chat subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3438
+            "score": 0.9665
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Math",
+          "evaluation_name": "Chat Hard",
           "metric_config": {
-            "evaluation_description": "Math score - measures mathematical reasoning",
+            "evaluation_description": "Chat Hard accuracy - includes hard chat subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5956
+            "score": 0.6053
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
           "evaluation_name": "Safety",
           "metric_config": {
-            "evaluation_description": "Safety score - measures safety awareness",
+            "evaluation_description": "Safety accuracy - includes safety subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6911
+            "score": 0.8703
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Focus",
+          "evaluation_name": "Reasoning",
           "metric_config": {
-            "evaluation_description": "Focus score - measures response focus",
+            "evaluation_description": "Reasoning accuracy - includes code and math subsets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7293
+            "score": 0.7736
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         },
         {
-          "evaluation_name": "Ties",
+          "evaluation_name": "Prior Sets (0.5 weight)",
           "metric_config": {
-            "evaluation_description": "Ties score - ability to identify tie cases",
+            "evaluation_description": "Prior Sets score (weighted 0.5) - includes test sets",
             "lower_is_better": false,
             "score_type": "continuous",
             "min_score": 0.0,
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6226
+            "score": 0.753
           },
           "source_data": {
-            "dataset_name": "RewardBench 2",
+            "dataset_name": "RewardBench",
             "source_type": "hf_dataset",
-            "hf_repo": "allenai/reward-bench-2-results"
+            "hf_repo": "allenai/reward-bench"
           }
         }
       ],
diff --git a/data/models/xai_grok-3-mini.json b/data/models/xai_grok-3-mini.json
index 6f7e913322e4d12afd1b4e9815b3c829b5eb051d..7fda2d0643a4e1f5eb9d98f1dc44e9ec85970d5d 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/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",
@@ -525,8 +525,8 @@
       "generation_config": null
     },
     {
-      "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",
diff --git a/data/models/xai_grok-4.json b/data/models/xai_grok-4.json
index 2396de921bef3d760583d06f283159a7a4b7cc87..1a7ae0a5e37faeab9841b8816b2f9d9332f7d639 100644
--- a/data/models/xai_grok-4.json
+++ b/data/models/xai_grok-4.json
@@ -4,13 +4,13 @@
     "id": "xai/grok-4",
     "developer": "xAI",
     "additional_details": {
-      "agent_name": "OpenHands",
-      "agent_organization": "OpenHands"
+      "agent_name": "Terminus 2",
+      "agent_organization": "Terminal Bench"
     }
   },
   "evaluations": [
     {
-      "evaluation_id": "terminal-bench-2.0/openhands__grok-4/1773776901.772108",
+      "evaluation_id": "terminal-bench-2.0/terminus-2__grok-4/1773776901.772108",
       "retrieved_timestamp": "1773776901.772108",
       "source_metadata": {
         "source_name": "Terminal-Bench 2.0",
@@ -34,7 +34,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-11-02",
+          "evaluation_timestamp": "2025-10-31",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -43,17 +43,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 27.2,
+            "score": 23.1,
             "uncertainty": {
               "standard_error": {
-                "value": 3.1
+                "value": 2.9
               },
               "num_samples": 435
             }
           },
           "generation_config": {
             "generation_args": {
-              "execution_command": "harbor run -d terminal-bench@2.0 -a \"OpenHands\" -m \"Grok 4\" -k 5",
+              "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"Grok 4\" -k 5",
               "agentic_eval_config": {
                 "available_tools": [
                   {
@@ -70,7 +70,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"OpenHands\" -m \"Grok 4\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Terminus 2\" -m \"Grok 4\" -k 5",
           "agentic_eval_config": {
             "available_tools": [
               {
@@ -84,7 +84,7 @@
       }
     },
     {
-      "evaluation_id": "terminal-bench-2.0/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",
@@ -108,7 +108,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-10-31",
+          "evaluation_timestamp": "2025-11-02",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -117,17 +117,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 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": [
                   {
@@ -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 4\" -k 5",
+          "execution_command": "harbor run -d terminal-bench@2.0 -a \"OpenHands\" -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 3dead5de67b9b087729b3bc778973bf9f0bdd596..80a497dcbe0e067252e23ff5d2567dcecf97e827 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": "Terminus 2",
-      "agent_organization": "Terminal Bench"
+      "agent_name": "Mini-SWE-Agent",
+      "agent_organization": "Princeton"
     }
   },
   "evaluations": [
     {
-      "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",
@@ -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": 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": [
                   {
@@ -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 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": [
               {
@@ -84,7 +84,7 @@
       }
     },
     {
-      "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",
@@ -108,7 +108,7 @@
               "https://www.tbench.ai/leaderboard/terminal-bench/2.0"
             ]
           },
-          "evaluation_timestamp": "2025-11-03",
+          "evaluation_timestamp": "2025-10-31",
           "metric_config": {
             "evaluation_description": "Task resolution accuracy across 87 terminal tasks with 5 trials each",
             "lower_is_better": false,
@@ -117,17 +117,17 @@
             "max_score": 100.0
           },
           "score_details": {
-            "score": 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": [
                   {
@@ -144,7 +144,7 @@
       "detailed_evaluation_results": null,
       "generation_config": {
         "generation_args": {
-          "execution_command": "harbor run -d terminal-bench@2.0 -a \"Mini-SWE-Agent\" -m \"Grok 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": [
               {
diff --git a/data/models/ycros_bagelmisterytour-v2-8x7b.json b/data/models/ycros_bagelmisterytour-v2-8x7b.json
index c7b7f840ab350df665db2f8b289c03a4556651c3..ba69aabd10b1f09ccc48e0969d876027b03e3a4b 100644
--- a/data/models/ycros_bagelmisterytour-v2-8x7b.json
+++ b/data/models/ycros_bagelmisterytour-v2-8x7b.json
@@ -5,7 +5,7 @@
     "developer": "ycros",
     "inference_platform": "unknown",
     "additional_details": {
-      "precision": "float16",
+      "precision": "bfloat16",
       "architecture": "MixtralForCausalLM",
       "params_billions": "46.703"
     }
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5994
+            "score": 0.6262
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5159
+            "score": 0.5142
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0785
+            "score": 0.0937
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3045
+            "score": 0.3079
           }
         },
         {
@@ -116,7 +116,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4203
+            "score": 0.4138
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3473
+            "score": 0.3481
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6262
+            "score": 0.5994
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5142
+            "score": 0.5159
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0937
+            "score": 0.0785
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3079
+            "score": 0.3045
           }
         },
         {
@@ -246,7 +246,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4138
+            "score": 0.4203
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3481
+            "score": 0.3473
           }
         }
       ],
diff --git a/data/models/yoyo-ai_qwen2.5-14b-yoyo-1010.json b/data/models/yoyo-ai_qwen2.5-14b-yoyo-1010.json
index 2a296ce898176000fe4f075772b9bc2bcb8d3b71..e42112fd11a9b36734c8e8c4176443d8815fdc44 100644
--- a/data/models/yoyo-ai_qwen2.5-14b-yoyo-1010.json
+++ b/data/models/yoyo-ai_qwen2.5-14b-yoyo-1010.json
@@ -5,7 +5,7 @@
     "developer": "YOYO-AI",
     "inference_platform": "unknown",
     "additional_details": {
-      "precision": "float16",
+      "precision": "bfloat16",
       "architecture": "Qwen2ForCausalLM",
       "params_billions": "14.77"
     }
@@ -44,7 +44,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5899
+            "score": 0.7905
           }
         },
         {
@@ -62,7 +62,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.654
+            "score": 0.6406
           }
         },
         {
@@ -80,7 +80,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4509
+            "score": 0.0
           }
         },
         {
@@ -98,7 +98,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3834
+            "score": 0.3163
           }
         },
         {
@@ -116,7 +116,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4744
+            "score": 0.4181
           }
         },
         {
@@ -134,7 +134,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.5376
+            "score": 0.4944
           }
         }
       ],
@@ -174,7 +174,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.7905
+            "score": 0.5899
           }
         },
         {
@@ -192,7 +192,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.6406
+            "score": 0.654
           }
         },
         {
@@ -210,7 +210,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.0
+            "score": 0.4509
           }
         },
         {
@@ -228,7 +228,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.3163
+            "score": 0.3834
           }
         },
         {
@@ -246,7 +246,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4181
+            "score": 0.4744
           }
         },
         {
@@ -264,7 +264,7 @@
             "max_score": 1.0
           },
           "score_details": {
-            "score": 0.4944
+            "score": 0.5376
           }
         }
       ],