{"claude-fable-5":{"bs":{"gpqa":[0.8586,87.8,55,205],"arc_agi_2":[0.8917,97.6,5,82],"arc_agi":[0.985,100,1,84],"simpleqa":[0.707,97,4,72],"simplebench":[0.819,100,1,82],"enigma":[0.3928,100,1,42],"critpt":[0.2857,92.3,8,121],"chess":[0.41,65.1,17,138],"aime":[1,100,1,186],"proofbench":[0.95,96,4,64],"scicode":[0.6019,100,2,112],"cursorbench":[0.705,94.7,3,22],"frontiercode":[0.5348,100,1,31],"alebench":[2041.3,94.7,4,102],"deepswe":[0.6991,92.4,5,26],"apex_agents":[0.609,98,3,53],"vending2":[5680.258,52.5,17,55],"weirdml":[0.9194,100,3,128],"blueprint2":[0.3861,95.6,2,24],"gbaeval":[0.7447,96.3,2,23],"posttrain":[0.4179,100,1,11],"rli":[0.161,100,1,11],"surface_evolver":[0.95,100,1,23],"btf3":[0.13,32,5,6],"webdev_arena":[1626.26,86,7,94]},"ar":{"text_style_control":[1506,30057,1,100],"webdev":[1628,10081,10,88.9],"agent":[0.0909,36950,5,86.1],"vision_style_control":[1310,11304,1,100],"search_style_control":[1229,41795,2,94.4],"document_style_control":[1499,8497,1,100]}},"claude-opus-5":{"bs":{"gpqa":[0.9388,98.9,10,205],"arc_agi_2":[0.9042,99,3,82],"arc_agi":[0.975,99.3,4,84],"simpleqa":[0.599,79.5,13,72],"simplebench":[0.806,100,2,82],"critpt":[0.2914,94.1,7,121],"chess":[0.42,66.7,16,138],"aime":[0.9889,98.9,12,186],"proofbench":[0.99,100,2,64],"scicode":[0.5567,92.2,13,112],"cursorbench":[0.7,93.2,4,22],"frontiercode":[0.5338,99.9,2,31],"alebench":[2164.57,100,2,102],"deepswe":[0.7365,99.4,3,26],"apex_agents":[0.606,97.4,4,53],"osworld2":[0.3143,100,1,9],"vending2":[11181.8733,100,1,55],"weirdml":[0.9178,99.8,4,128],"blueprint2":[0.3037,75.2,9,24],"gbaeval":[0.796,100,1,23],"posttrain":[0.3504,73.3,3,11],"btf3":[0.118,0,6,6],"webdev_arena":[1690.64,98,3,94]},"ar":{"text_style_control":[1493,42617,10,100],"webdev":[1687,12087,3,100],"agent":[0.1106,23679,3,93.7],"vision_style_control":[1289,11599,10,96.9],"document_style_control":[1490,8794,7,92.4]}},"gpt-5-6-sol":{"bs":{"gpqa":[0.935,98.4,11,205],"arc_agi_2":[0.925,100,2,82],"arc_agi":[0.975,99.3,5,84],"simpleqa":[0.697,95.3,5,72],"simplebench":[0.717,84.8,10,82],"enigma":[0.3712,98.3,2,42],"critpt":[0.323,100,1,121],"chess":[0.64,100,2,138],"aime":[1,100,2,186],"proofbench":[0.83,83.8,6,64],"scicode":[0.5694,95.3,7,112],"cursorbench":[0.672,84.9,6,22],"frontiercode":[0.4749,86.7,6,31],"alebench":[2176.88,100,1,102],"deepswe":[0.7267,97.5,4,26],"apex_agents":[0.567,90.3,8,53],"osworld2":[0.2734,87.6,2,9],"vending2":[9619.368,88.8,3,55],"weirdml":[0.8943,96.2,5,128],"blueprint2":[0.3362,83.3,4,24],"gbaeval":[0.5259,68,7,23],"posttrain":[0.3623,78.9,2,11],"surface_evolver":[0.9313,97.6,3,23],"btf3":[0.137,52.8,4,6],"webdev_arena":[1618.71,84.6,8,94]},"ar":{"text_style_control":[1483,27069,18,97.9],"agent":[0.0751,30881,7,80],"vision_style_control":[1286,7729,14,96],"search_style_control":[1256,29663,1,100],"document_style_control":[1489,4818,8,91.1]}},"claude-fable-5-1":{"bs":{"hle":[0.465,100,1,43],"arc_agi_2":[0.9,98.5,4,82],"arc_agi":[0.975,99.3,6,84],"simpleqa":[0.708,97.1,3,72],"critpt":[0.3114,100,3,121],"chess":[0.47,74.6,11,138],"aime":[1,100,3,186],"proofbench":[1,100,1,64],"scicode":[0.6204,100,1,112],"cursorbench":[0.734,100,1,22],"frontiercode":[0.5091,94.4,4,31],"alebench":[2143.2,100,3,102],"apex_agents":[0.62,100,2,53],"vending2":[5421.5567,50.2,20,55],"weirdml":[0.929,100,1,128],"blueprint2":[0.4187,100,1,24],"webdev_arena":[1765.37,100,2,94]},"ar":{"text_style_control":[1498,5783,5,100],"webdev":[1758,3036,2,100],"agent":[0.1385,12416,1,100],"vision_style_control":[1289,2701,11,96.9],"document_style_control":[1493,1403,6,96]}},"gpt-6-astra":{"bs":{"gpqa":[0.9577,100,1,205],"arc_agi_2":[0.95,100,1,82],"arc_agi":[0.985,100,2,84],"simpleqa":[0.756,100,1,72],"critpt":[0.3171,100,2,121],"chess":[0.72,100,1,138],"aime":[1,100,4,186],"proofbench":[0.99,100,3,64],"scicode":[0.5648,94.1,9,112],"frontiercode":[0.5326,99.6,3,31],"deepswe":[0.7412,100,1,26],"apex_agents":[0.624,100,1,53],"weirdml":[0.9287,100,2,128],"webdev_arena":[1797.04,100,1,94]},"ar":{"text_style_control":[1480,2693,24,97.1],"webdev":[1800,2281,1,100],"agent":[0.1239,9692,2,98.8],"vision_style_control":[1284,1367,16,95.4],"document_style_control":[1473,1621,17,72]}},"gpt-5-5":{"bs":{"gpqa":[0.94,99.1,7,205],"arc_agi_2":[0.85,93,6,82],"arc_agi":[0.95,96.7,12,84],"simpleqa":[0.63,84.5,11,72],"simplebench":[0.69,80,13,82],"critpt":[0.2714,87.6,9,121],"forecastbench":[61.1,86.6,14,75],"chess":[0.54,85.7,7,138],"frontiermath":[0.517,100,2,71],"frontiermath_t4":[0.354,89.8,4,56],"aime":[1,100,5,186],"proofbench":[0.5,50.5,17,64],"swebench":[0.8058,95.8,2,32],"terminalbench":[0.847,100,1,45],"scicode":[0.5613,93.3,12,112],"cursorbench":[0.584,58.9,14,22],"frontiercode":[0.4296,76.5,10,31],"gso":[0.402,87.8,4,28],"alebench":[1942.97,89.6,6,102],"deepswe":[0.6704,86.9,11,26],"apex_agents":[0.555,88.1,9,53],"osworld2":[0.13,35.8,5,9],"deepresearch":[0.54,94.5,4,25],"vending2":[7523.844,69.5,8,55],"exploitbench":[0.474,60.5,2,9],"weirdml":[0.8491,89.4,6,128],"blueprint2":[0.3623,89.7,3,24],"gbaeval":[0.5322,68.8,6,23],"posttrain":[0.2723,36.2,8,11],"rli":[0.0625,39.1,3,11],"surface_evolver":[0.8813,91.3,4,23],"btf3":[0.143,70.6,2,6],"webdev_arena":[1508.35,64,32,94]},"ar":{"text_style_control":[1482,64924,20,97.5],"agent":[0.0522,52336,11,71.2],"vision_style_control":[1287,23423,13,96.4],"document_style_control":[1483,21279,10,84.2]}},"claude-opus-4-8":{"bs":{"gpqa":[0.9104,95,24,205],"arc_agi_2":[0.7208,78.9,15,82],"arc_agi":[0.925,94.1,18,84],"simpleqa":[0.53,68.3,16,72],"simplebench":[0.648,72.5,15,82],"enigma":[0.2351,61.6,6,42],"critpt":[0.2086,67.3,13,121],"forecastbench":[59.3,59.7,39,75],"chess":[0.34,54,28,138],"frontiermath":[0.4724,92,5,71],"frontiermath_t4":[0.3125,79.3,6,56],"aime":[0.9833,98.3,15,186],"proofbench":[0.69,69.7,9,64],"scicode":[0.5347,86.8,20,112],"cursorbench":[0.623,70.4,9,22],"frontiercode":[0.465,84.5,7,31],"gso":[0.4706,100,1,28],"alebench":[1563.83,70,10,102],"deepswe":[0.5897,71.8,14,26],"apex_agents":[0.594,95.2,5,53],"osworld2":[0.206,63.2,3,9],"deepresearch":[0.502,75.5,6,25],"vending2":[5787.428,53.5,16,55],"weirdml":[0.8289,86.3,7,128],"blueprint2":[0.1453,36,17,24],"gbaeval":[0.709,91.7,3,23],"posttrain":[0.3384,67.6,4,11],"rli":[0.0833,54.4,2,11],"surface_evolver":[0.875,90.6,5,23],"btf3":[0.14,61.7,3,6],"webdev_arena":[1563.49,74.3,18,94]},"ar":{"text_style_control":[1481,52535,21,97.4],"webdev":[1559,13787,24,75.6],"agent":[0.0757,39316,6,80.3],"vision_style_control":[1283,15274,18,95.3],"search_style_control":[1195,70998,13,73.7],"document_style_control":[1486,11551,9,87.8]}},"kimi-k3":{"bs":{"gpqa":[0.9312,97.9,15,205],"arc_agi_2":[0.6042,66.1,23,82],"arc_agi":[0.945,96.1,13,84],"simpleqa":[0.506,64.4,20,72],"simplebench":[0.607,65.3,23,82],"critpt":[0.234,75.6,12,121],"chess":[0.39,61.9,22,138],"aime":[0.9722,97.2,20,186],"proofbench":[0.87,87.9,5,64],"scicode":[0.5868,99.5,4,112],"cursorbench":[0.608,66,13,22],"frontiercode":[0.4417,79.3,8,31],"alebench":[1524.47,68,11,102],"deepswe":[0.6851,89.7,8,26],"apex_agents":[0.554,87.9,10,53],"vending2":[5165.035,47.8,22,55],"weirdml":[0.8257,85.8,8,128],"blueprint2":[0.295,73.1,10,24],"gbaeval":[0.4835,62.5,9,23],"posttrain":[0.3196,58.6,5,11],"surface_evolver":[0.95,100,2,23],"webdev_arena":[1673.7,94.9,4,94]},"ar":{"text_style_control":[1485,20987,17,98.2],"webdev":[1674,4547,5,97.8],"agent":[0.0646,101022,8,76]}},"claude-opus-4-7":{"bs":{"gpqa":[0.9015,93.8,33,205],"hle":[0.362,75.2,7,43],"arc_agi_2":[0.7583,83,13,82],"arc_agi":[0.935,95.1,17,84],"simpleqa":[0.517,66.2,19,72],"simplebench":[0.617,67.1,19,82],"critpt":[0.12,38.7,33,121],"forecastbench":[59.6,64.2,35,75],"chess":[0.3,47.6,32,138],"frontiermath":[0.4379,85.2,6,71],"frontiermath_t4":[0.2292,58.1,8,56],"aime":[0.978,97.7,17,186],"proofbench":[0.54,54.5,15,64],"swebench":[0.8347,100,1,32],"terminalbench":[0.802,97.4,3,45],"scicode":[0.5451,89.3,15,112],"cursorbench":[0.648,77.8,8,22],"frontiercode":[0.3854,66.6,16,31],"gso":[0.4412,96.7,2,28],"alebench":[1323.05,57.6,17,102],"apex_agents":[0.506,79.2,14,53],"osworld2":[0.182,54.6,4,9],"vending2":[10936.7633,100,2,55],"exploitbench":[0.265,23.4,3,9],"weirdml":[0.7644,76.5,13,128],"blueprint2":[0.2451,60.7,15,24],"gbaeval":[0.4381,56.6,12,23],"posttrain":[0.2856,42.5,7,11],"webdev_arena":[1566.85,74.9,17,94]},"ar":{"text_style_control":[1502,60002,3,100],"webdev":[1557,15914,25,75.4],"vision_style_control":[1301,21092,3,100],"search_style_control":[1212,91394,5,84.1],"document_style_control":[1494,22192,3,97.6]}},"grok-4-6":{"bs":{"gpqa":[0.94,99.1,8,205],"arc_agi_2":[0.6708,73.4,18,82],"arc_agi":[0.875,88.8,26,84],"simpleqa":[0.493,62.3,23,72],"simplebench":[0.759,92.2,7,82],"critpt":[0.1971,63.7,17,121],"chess":[0.4,63.5,18,138],"aime":[0.9917,99.1,10,186],"proofbench":[0.51,51.5,16,64],"scicode":[0.5463,89.6,14,112],"cursorbench":[0.708,95.5,2,22],"frontiercode":[0.4801,87.9,5,31],"alebench":[1508.08,67.1,12,102],"deepswe":[0.6748,87.8,9,26],"apex_agents":[0.575,91.8,7,53],"vending2":[9047.0325,83.6,4,55],"weirdml":[0.6729,62.6,20,128],"blueprint2":[0.3319,82.2,6,24],"webdev_arena":[1628.84,86.5,6,94]},"ar":{"text_style_control":[1456,15521,63,91.7],"webdev":[1618,4282,13,87],"agent":[0.0312,20911,18,63.2],"vision_style_control":[1265,3632,35,89.7],"document_style_control":[1461,2258,24,58.4]}},"claude-opus-4-6":{"bs":{"gpqa":[0.9053,94.3,31,205],"hle":[0.3444,70.9,8,43],"arc_agi_2":[0.6917,75.7,17,82],"arc_agi":[0.94,95.6,15,84],"simpleqa":[0.47,58.6,28,72],"simplebench":[0.676,77.5,14,82],"enigma":[0.076,18.8,17,42],"forecastbench":[60,70.1,30,75],"chess":[0.17,27,65,138],"frontiermath":[0.407,79.1,7,71],"frontiermath_t4":[0.229,58.1,9,56],"aime":[0.9444,94.3,31,186],"proofbench":[0.5,50.5,18,64],"swebench":[0.7872,89.1,4,32],"terminalbench":[0.798,96.8,5,45],"frontiercode":[0.2664,39.9,20,31],"gso":[0.412,90.1,3,28],"alebench":[996.5,40.7,37,102],"algotune":[1.47,21.2,12,18],"apex_agents":[0.487,75.7,15,53],"metr":[0.7886,93.1,2,35],"deepresearch":[0.553,100,1,25],"vending2":[8017.594,74.1,7,55],"cybench":[0.93,100,1,21],"weirdml":[0.7795,78.8,11,128],"gbaeval":[0.4412,57,11,23],"rli":[0.0417,23.9,5,11],"webdev_arena":[1556.29,72.9,20,94]},"ar":{"text_style_control":[1505,71993,2,100],"webdev":[1547,18332,28,73.3],"vision_style_control":[1299,20835,5,99.8],"document_style_control":[1495,27929,2,98.9]}},"gpt-5-6-terra":{"bs":{"gpqa":[0.9331,98.1,13,205],"arc_agi_2":[0.839,91.8,10,82],"arc_agi":[0.965,98.2,7,84],"simpleqa":[0.432,52.4,35,72],"simplebench":[0.489,44.4,43,82],"critpt":[0.3,96.9,5,121],"chess":[0.54,85.7,8,138],"aime":[0.9972,99.7,8,186],"proofbench":[0.74,74.7,8,64],"scicode":[0.5394,87.9,18,112],"cursorbench":[0.649,78.1,7,22],"frontiercode":[0.4131,72.8,14,31],"alebench":[1951.42,90.1,5,102],"deepswe":[0.6962,91.8,6,26],"vending2":[7343.206,67.9,9,55],"weirdml":[0.7827,79.3,10,128],"blueprint2":[0.308,76.3,8,24],"surface_evolver":[0.8375,85.8,6,23],"webdev_arena":[1519.87,66.1,26,94]},"ar":{"text_style_control":[1466,28119,45,94],"agent":[0.0146,19096,24,56.8],"vision_style_control":[1267,7726,32,90.3],"document_style_control":[1477,5787,14,76.9]}},"gpt-5-5-pro":{"bs":{"gpqa":[0.9392,99,9,205],"arc_agi_2":[0.8458,92.6,8,82],"arc_agi":[0.965,98.2,8,84],"simplebench":[0.769,94,4,82],"critpt":[0.3057,98.7,4,121],"chess":[0.64,100,3,138],"frontiermath":[0.524,100,1,71],"frontiermath_t4":[0.396,100,2,56],"aime":[1,100,6,186]}},"gemini-3-8-flash":{"bs":{"gpqa":[0.9539,100,2,205],"simpleqa":[0.697,95.3,6,72],"critpt":[0.1829,59,19,121],"chess":[0.61,96.9,4,138],"aime":[0.9889,98.9,13,186],"proofbench":[0.48,48.5,21,64],"scicode":[0.544,89.1,16,112],"cursorbench":[0.692,90.8,5,22],"deepswe":[0.7383,99.7,2,26],"webdev_arena":[1567.33,75,16,94]},"ar":{"text_style_control":[1493,5076,9,100],"webdev":[1568,2732,23,77.4],"agent":[0.0384,10105,16,65.9]}},"gpt-5-4":{"bs":{"gpqa":[0.933,98.1,14,205],"hle":[0.3624,75.3,6,43],"arc_agi_2":[0.7395,80.9,14,82],"arc_agi":[0.9367,95.3,16,84],"simpleqa":[0.451,55.5,33,72],"enigma":[0.1596,41.3,9,42],"critpt":[0.2343,75.6,11,121],"forecastbench":[59.5,62.7,37,75],"chess":[0.44,69.9,14,138],"frontiermath":[0.476,92.7,4,71],"frontiermath_t4":[0.271,68.7,7,56],"aime":[0.9778,97.7,18,186],"proofbench":[0.56,56.6,13,64],"swebench":[0.7686,82.5,8,32],"terminalbench":[0.818,99.5,2,45],"scicode":[0.566,94.4,8,112],"gso":[0.3137,67.9,6,28],"alebench":[1607,72.3,9,102],"algotune":[1.85,73.7,3,18],"deepswe":[0.5177,58.2,20,26],"apex_agents":[0.527,83,11,53],"metr":[0.7434,84,7,35],"deepresearch":[0.351,0,24,25],"vending2":[6144.176,56.8,14,55],"weirdml":[0.777,78.4,12,128],"blueprint2":[0.2711,67.2,12,24],"gbaeval":[0.4515,58.4,10,23],"posttrain":[0.19,0,11,11],"webdev_arena":[1462.9,55.5,41,94]},"ar":{"text_style_control":[1476,60537,26,96.3],"webdev":[1387,2493,83,42.6],"agent":[0.0154,79621,23,57.1],"vision_style_control":[1285,25357,15,95.7],"document_style_control":[1470,33331,18,69.1]}},"claude-sonnet-5":{"bs":{"gpqa":[0.9053,94.3,32,205],"simpleqa":[0.337,37,48,72],"simplebench":[0.606,65.1,24,82],"critpt":[0.1686,54.4,23,121],"forecastbench":[59.9,68.7,32,75],"chess":[0.35,55.6,27,138],"aime":[0.9472,94.6,30,186],"proofbench":[0.77,77.8,7,64],"scicode":[0.5359,87.1,19,112],"cursorbench":[0.615,68,11,22],"frontiercode":[0.4273,76,11,31],"gso":[0.3725,81.2,5,28],"alebench":[1463.12,64.8,13,102],"deepswe":[0.5385,62.1,17,26],"apex_agents":[0.485,75.3,17,53],"vending2":[6377.7017,59,12,55],"weirdml":[0.6878,64.9,19,128],"blueprint2":[0.2495,61.8,14,24],"gbaeval":[0.6526,84.4,5,23],"surface_evolver":[0.6,55.9,9,23],"btf3":[0.154,100,1,6],"webdev_arena":[1538.58,69.6,23,94]},"ar":{"text_style_control":[1461,35301,51,93],"webdev":[1537,9296,33,71.4],"agent":[0.0588,29782,9,73.8],"vision_style_control":[1266,10289,33,90.2],"document_style_control":[1476,7411,15,75.7]}},"qwen3-8":{"bs":{"gpqa":[0.9268,97.3,17,205],"simpleqa":[0.458,56.6,31,72],"critpt":[0.2,64.6,16,121],"chess":[0.29,46,35,138],"aime":[0.9944,99.4,9,186],"proofbench":[0.58,58.6,11,64],"scicode":[0.5289,85.4,23,112],"deepswe":[0.5746,68.9,15,26],"webdev_arena":[1668.94,94,5,94]},"ar":{"text_style_control":[1481,16670,22,97.3],"webdev":[1671,3221,6,97.1],"agent":[0.0397,23261,15,66.4],"vision_style_control":[1302,8665,2,100]}},"gemini-3-1-pro-preview":{"bs":{"gpqa":[0.9444,99.7,5,205],"hle":[0.4644,100,2,43],"arc_agi_2":[0.771,84.4,12,82],"arc_agi":[0.98,99.8,3,84],"simpleqa":[0.735,100,2,72],"simplebench":[0.796,98.8,3,82],"enigma":[0.3678,97.3,3,42],"critpt":[0.1771,57.2,21,121],"forecastbench":[59,55.2,44,75],"chess":[0.55,87.3,6,138],"frontiermath":[0.369,71.7,13,71],"frontiermath_t4":[0.167,42.4,12,56],"aime":[0.956,95.5,25,186],"proofbench":[0.26,26.3,30,64],"terminalbench":[0.802,97.4,4,45],"scicode":[0.5891,100,3,112],"gso":[0.2255,48,9,28],"alebench":[1160.6,49.2,30,102],"algotune":[2.02,97.3,2,18],"deepswe":[0.1173,0,26,26],"apex_agents":[0.487,75.7,16,53],"metr":[0.7704,89.4,3,35],"deepresearch":[0.478,63.5,10,25],"vending2":[911.214,8.6,42,55],"balrog":[0.57,97.7,2,32],"exploitbench":[0.261,22.7,4,9],"weirdml":[0.7207,69.9,16,128],"blueprint2":[0.2646,65.6,13,24],"gbaeval":[0.0085,1.1,19,23],"posttrain":[0.2199,11.3,10,11],"webdev_arena":[1446.46,52.4,44,94]},"ar":{"text_style_control":[1487,106951,15,98.7],"webdev":[1447,22891,57,54.1],"agent":[-0.056,85599,38,29.7],"vision_style_control":[1279,40691,26,93.9],"document_style_control":[1459,49457,27,55.8]}},"gemini-3-pro":{"bs":{"gpqa":[0.9261,97.2,18,205],"hle":[0.3752,78.4,5,43],"arc_agi_2":[0.3111,34,33,82],"arc_agi":[0.75,75.8,36,84],"simplebench":[0.764,93.1,6,82],"enigma":[0.1824,47.4,8,42],"critpt":[0.069,22.3,45,121],"forecastbench":[61.2,88.1,12,75],"chess":[0.31,49.2,31,138],"frontiermath":[0.376,73,12,71],"frontiermath_t4":[0.1875,47.6,11,56],"aime":[0.9139,91.2,41,186],"proofbench":[0.2,20.2,36,64],"swebench":[0.7293,68.3,21,32],"terminalbench":[0.694,82.7,7,45],"gso":[0.1863,39.1,10,28],"alebench":[1176.75,50,28,102],"algotune":[1.83,71,4,18],"apex_agents":[0.467,72,20,53],"metr":[0.7098,77.2,8,35],"gdpval":[0.403,68.5,5,11],"deepresearch":[0.463,56,14,25],"vending2":[5478.158,50.7,19,55],"balrog":[0.581,100,1,32],"weirdml":[0.6993,66.6,18,128],"rli":[0.0125,2.5,10,11],"vpct":[0.91,100,1,27],"geobench":[4145,93,2,28],"webdev_arena":[1437.8,50.8,45,94]},"ar":{"text_style_control":[1485,40654,16,98.4],"webdev":[1439,13573,61,52.6],"vision_style_control":[1289,12995,12,96.8],"document_style_control":[1451,10769,31,46.6]}},"grok-4-5":{"bs":{"gpqa":[0.9343,98.3,12,205],"arc_agi_2":[0.5264,57.6,28,82],"arc_agi":[0.8717,88.5,27,84],"simpleqa":[0.483,60.7,25,72],"simplebench":[0.7,81.8,12,82],"critpt":[0.1543,49.8,25,121],"chess":[0.36,57.2,26,138],"aime":[0.9778,97.7,19,186],"proofbench":[0.31,31.3,28,64],"scicode":[0.5405,88.2,17,112],"frontiercode":[0.4244,75.4,12,31],"alebench":[1309.28,56.9,19,102],"deepswe":[0.5376,62,18,26],"apex_agents":[0.509,79.7,13,53],"vending2":[3887.426,36,30,55],"weirdml":[0.4643,31,55,128],"blueprint2":[0.2733,67.7,11,24],"gbaeval":[0.6541,84.6,4,23],"posttrain":[0.2345,18.3,9,11],"surface_evolver":[0.7438,74,7,23],"webdev_arena":[1556.36,73,19,94]},"ar":{"text_style_control":[1468,30103,42,94.5],"webdev":[1555,8133,27,74.9],"agent":[0.0383,36452,17,65.9],"vision_style_control":[1279,8355,24,94.1],"search_style_control":[1202,31505,8,78.2],"document_style_control":[1464,4965,22,62.3]}},"glm-5-3":{"bs":{"gpqa":[0.9091,94.8,26,205],"simpleqa":[0.41,48.8,37,72],"critpt":[0.1914,61.8,18,121],"chess":[0.21,33.3,50,138],"aime":[0.9111,90.9,43,186],"proofbench":[0.49,49.5,20,64],"scicode":[0.5648,94.1,10,112],"alebench":[1317.4,57.3,18,102],"deepswe":[0.6896,90.6,7,26],"vending2":[8163.61,75.4,6,55],"weirdml":[0.754,74.9,14,128],"webdev_arena":[1598.6,80.8,10,94]},"ar":{"text_style_control":[1483,10960,19,97.8],"webdev":[1614,3725,15,86.3],"agent":[0.0262,65488,20,61.3]}},"gemini-3-7-flash":{"bs":{"gpqa":[0.9482,100,3,205],"arc_agi_2":[0.8458,92.6,7,82],"arc_agi":[0.955,97.2,11,84],"simpleqa":[0.692,94.5,7,72],"critpt":[0.1429,46.1,28,121],"chess":[0.47,74.6,12,138],"aime":[0.9722,97.2,21,186],"proofbench":[0.58,58.6,12,64],"scicode":[0.5787,97.5,6,112],"cursorbench":[0.616,68.3,10,22],"frontiercode":[0.4359,77.9,9,31],"alebench":[904.3,35.9,44,102],"deepswe":[0.6549,84,12,26],"rli":[0.05,30,4,11],"webdev_arena":[1587.04,78.7,13,94]},"ar":{"text_style_control":[1490,5640,12,99.3],"webdev":[1587,3007,20,81.1]}},"gpt-5-6-luna":{"bs":{"gpqa":[0.916,95.8,22,205],"arc_agi_2":[0.5954,65.2,25,82],"arc_agi":[0.88,89.4,25,84],"simpleqa":[0.41,48.8,38,72],"simplebench":[0.468,40.7,45,82],"critpt":[0.206,66.5,15,121],"chess":[0.4,63.5,19,138],"aime":[0.9833,98.3,16,186],"proofbench":[0.6,60.6,10,64],"scicode":[0.5255,84.5,25,112],"cursorbench":[0.611,66.9,12,22],"frontiercode":[0.3981,69.5,15,31],"alebench":[1667.4,75.4,7,102],"deepswe":[0.6719,87.2,10,26],"vending2":[4094.712,37.9,29,55],"weirdml":[0.6086,52.9,27,128],"blueprint2":[0.2256,55.9,16,24],"surface_evolver":[0.6188,58.3,8,23],"webdev_arena":[1517.6,65.7,27,94]},"ar":{"text_style_control":[1452,28547,67,91],"agent":[0.0073,22203,25,54],"vision_style_control":[1258,7793,40,87.8],"document_style_control":[1462,5766,23,59.5]}},"gemini-3-5-flash":{"bs":{"gpqa":[0.928,97.4,16,205],"arc_agi_2":[0.7208,78.9,16,82],"arc_agi":[0.925,94.1,19,84],"simpleqa":[0.662,89.7,9,72],"simplebench":[0.767,93.6,5,82],"enigma":[0.2541,66.7,4,42],"critpt":[0.1314,42.4,30,121],"forecastbench":[59.2,58.2,40,75],"chess":[0.5,79.4,9,138],"frontiermath":[0.3897,75.7,10,71],"frontiermath_t4":[0.1458,37,15,56],"aime":[0.9556,95.4,26,186],"proofbench":[0.31,31.3,29,64],"swebench":[0.7934,91.4,3,32],"scicode":[0.5313,86,22,112],"cursorbench":[0.498,33.4,18,22],"alebench":[911.02,36.3,43,102],"deepswe":[0.3739,31.2,23,26],"vending2":[5396.4183,49.9,21,55],"weirdml":[0.6264,55.6,25,128],"blueprint2":[0.3362,83.3,5,24],"gbaeval":[0.067,8.7,14,23],"surface_evolver":[0.5813,53.5,10,23],"webdev_arena":[1506.38,63.6,33,94]},"ar":{"text_style_control":[1478,38257,25,96.6],"webdev":[1500,8931,44,64.3],"vision_style_control":[1284,9579,17,95.3],"document_style_control":[1461,6500,25,57.8]}},"muse-spark":{"bs":{"gpqa":[0.898,93.3,36,205],"hle":[0.4056,85.7,4,43],"critpt":[0.1133,36.6,34,121],"frontiermath":[0.39,75.8,9,71],"frontiermath_t4":[0.146,37,13,56],"aime":[0.889,88.6,47,186],"proofbench":[0.17,17.2,40,64],"scicode":[0.515,82,26,112],"webdev_arena":[1512.53,64.8,29,94]},"ar":{"text_style_control":[1488,13565,13,98.9],"vision_style_control":[1294,5572,7,98.3],"document_style_control":[1467,1084,20,65.8]}},"qwen3-8-max-0902":{"bs":{"gpqa":[0.923,96.7,19,205],"simpleqa":[0.473,59.1,27,72],"chess":[0.4,63.5,20,138],"aime":[1,100,7,186]},"ar":{"webdev":[1681,2262,4,99.1]}},"gpt-5-2":{"bs":{"gpqa":[0.914,95.5,23,205],"hle":[0.278,54.8,10,43],"arc_agi_2":[0.5291,57.9,27,82],"arc_agi":[0.862,87.5,29,84],"simpleqa":[0.371,42.5,41,72],"simplebench":[0.458,38.9,49,82],"enigma":[0.1039,26.3,14,42],"forecastbench":[60.1,71.6,29,75],"chess":[0.49,77.8,10,138],"frontiermath":[0.407,79.1,8,71],"frontiermath_t4":[0.188,47.7,10,56],"aime":[0.9611,96,23,186],"proofbench":[0.15,15.2,45,64],"swebench":[0.7376,71.3,17,32],"terminalbench":[0.649,76.6,9,45],"gso":[0.2745,59,7,28],"alebench":[1293.55,56,22,102],"algotune":[2.05,100,1,18],"apex_agents":[0.484,75.1,18,53],"metr":[0.7529,85.9,4,35],"gdpval":[0.497,100,1,11],"deepresearch":[0.411,30,21,25],"vending2":[3591.326,33.3,34,55],"weirdml":[0.7219,70.1,15,128],"rli":[0.025,11.6,7,11],"vpct":[0.84,93,2,27],"webdev_arena":[1480,58.7,36,94]},"ar":{"text_style_control":[1438,47538,89,87.7],"webdev":[1417,1055,70,48.3],"vision_style_control":[1244,17926,50,83.6],"document_style_control":[1425,28212,40,16.1]}},"gpt-5":{"bs":{"gpqa":[0.8617,88.2,53,205],"hle":[0.2532,48.8,11,43],"arc_agi_2":[0.0986,10.8,42,82],"arc_agi":[0.6567,66.1,40,84],"simpleqa":[0.501,63.6,21,72],"simplebench":[0.567,58.2,31,82],"enigma":[0.1047,26.5,13,42],"critpt":[0.126,40.7,32,121],"forecastbench":[61.4,91,8,75],"chess":[0.37,58.7,25,138],"frontiermath":[0.3241,62.8,16,71],"frontiermath_t4":[0.125,31.7,17,56],"aime":[0.9139,91.2,42,186],"math_l5":[0.9813,100,1,90],"proofbench":[0.18,18.2,38,64],"swebench":[0.7355,70.6,19,32],"terminalbench":[0.496,55.8,18,45],"scicode":[0.4294,61.1,56,112],"gso":[0.0686,12.6,16,28],"aider":[88,100,1,56],"alebench":[1162.45,49.3,29,102],"algotune":[1.67,48.9,8,18],"apex_agents":[0.33,47,30,53],"metr":[0.6961,74.5,10,35],"gdpval":[0.348,48.5,6,11],"deepresearch":[0.496,72.5,8,25],"balrog":[0.328,30.5,9,32],"weirdml":[0.607,52.6,29,128],"rli":[0.0167,5.5,9,11],"vpct":[0.66,61,4,27],"geobench":[3937,80.8,5,28],"fiction120k":[0.969,99,2,40],"lech_writing":[8.6,100,1,45],"webdev_arena":[1419.14,47.3,52,94]},"ar":{"text_style_control":[1435,31428,95,87],"webdev":[1420,3032,69,48.9],"vision_style_control":[1211,34351,72,73.8]}},"grok-4-20-multi-agent":{"ar":{"text_style_control":[1470,60777,40,94.9],"vision_style_control":[1251,22925,44,85.5],"search_style_control":[1205,109553,7,79.7]}},"glm-5-2":{"bs":{"gpqa":[0.9186,96.1,20,205],"arc_agi_2":[0.2278,24.9,34,82],"arc_agi":[0.77,77.9,34,84],"simpleqa":[0.342,37.8,46,72],"simplebench":[0.588,61.9,27,82],"critpt":[0.2086,67.3,14,121],"chess":[0.21,33.3,51,138],"aime":[0.8639,86.1,61,186],"proofbench":[0.35,35.4,27,64],"swebench":[0.787,89.1,5,32],"scicode":[0.5046,79.5,27,112],"cursorbench":[0.55,48.8,16,22],"frontiercode":[0.245,35.1,22,31],"alebench":[1046.95,43.3,33,102],"deepswe":[0.4378,43.2,22,26],"apex_agents":[0.522,82.1,12,53],"vending2":[8313.7783,76.8,5,55],"weirdml":[0.7012,66.9,17,128],"gbaeval":[0.0002,0,21,23],"posttrain":[0.317,57.4,6,11],"surface_evolver":[0.5563,50.4,11,23],"webdev_arena":[1593.25,79.8,12,94]},"ar":{"text_style_control":[1472,36798,38,95.4],"webdev":[1592,10516,19,82],"agent":[0.0456,73382,12,68.7]}},"muse-spark-1-3":{"bs":{"chess":[0.38,60.3,23,138],"aime":[0.9917,99.1,11,186]},"ar":{"text_style_control":[1493,4723,8,100],"webdev":[1652,2972,8,93.5],"agent":[0.0423,8770,13,67.4],"vision_style_control":[1294,1804,6,98.4],"document_style_control":[1468,1006,19,66.5]}},"gpt-5-2-chat":{"ar":{"text_style_control":[1476,34176,27,96.3],"vision_style_control":[1278,15432,27,93.7]}},"claude-opus-4-5":{"bs":{"gpqa":[0.8605,88.1,54,205],"hle":[0.252,48.5,12,43],"arc_agi_2":[0.3764,41.2,30,82],"arc_agi":[0.8,81,32,84],"simpleqa":[0.457,56.5,32,72],"simplebench":[0.62,67.6,18,82],"enigma":[0.1191,30.4,11,42],"forecastbench":[60.7,80.6,20,75],"chess":[0.12,19.1,76,138],"frontiermath":[0.2069,39.8,30,71],"frontiermath_t4":[0.0417,10.6,27,56],"aime":[0.8611,85.8,62,186],"proofbench":[0.36,36.4,25,64],"swebench":[0.7665,81.7,9,32],"terminalbench":[0.631,74.1,11,45],"gso":[0.265,56.9,8,28],"alebench":[1025.38,42.2,34,102],"algotune":[1.77,62.7,5,18],"apex_agents":[0.371,54.5,26,53],"metr":[0.7497,85.3,5,35],"osworld":[66.3,89.4,2,9],"gdpval":[0.455,87.5,2,11],"deepresearch":[0.548,98.5,3,25],"vending2":[4967.0567,46,25,55],"balrog":[0.435,60.2,5,32],"cybench":[0.82,88.2,2,21],"weirdml":[0.6374,57.2,23,128],"rli":[0.0375,20.8,6,11],"vpct":[0.4,14.7,15,27],"geobench":[3877,77.3,10,28],"webdev_arena":[1494.39,61.4,34,94]},"ar":{"text_style_control":[1473,36239,36,95.5],"webdev":[1495,10592,45,63.3],"document_style_control":[1465,7981,21,62.6]}},"qwen3-5-397b-a17b":{"bs":{"gpqa":[0.8636,88.5,52,205],"chess":[0.13,20.6,72,138],"aime":[0.8889,88.6,48,186]},"ar":{"text_style_control":[1442,77007,82,88.6],"webdev":[1399,19922,76,44.9],"vision_style_control":[1248,27569,47,84.8]}},"dola-seed-2-0-pro":{"ar":{"text_style_control":[1456,74159,61,91.7],"vision_style_control":[1257,10280,41,87.3]}},"gemini-3-6-flash":{"bs":{"gpqa":[0.9413,99.3,6,205],"arc_agi_2":[0.6042,66.1,24,82],"arc_agi":[0.9117,92.7,20,84],"simpleqa":[0.662,89.7,10,72],"critpt":[0.1057,34.1,35,121],"chess":[0.43,68.3,15,138],"aime":[0.9417,94,33,186],"proofbench":[0.36,36.4,26,64],"scicode":[0.5266,84.8,24,112],"cursorbench":[0.535,44.4,17,22],"frontiercode":[0.3437,57.3,17,31],"alebench":[715.52,26.1,63,102],"deepswe":[0.4668,48.6,21,26],"weirdml":[0.561,45.6,36,128],"blueprint2":[0.3124,77.4,7,24],"webdev_arena":[1538.91,69.7,22,94]},"ar":{"text_style_control":[1480,26445,23,97.1],"webdev":[1537,8259,32,71.4],"agent":[-0.0541,19631,36,30.4],"vision_style_control":[1283,5159,21,95],"document_style_control":[1453,2975,28,49.4]}},"ernie-5-1":{"ar":{"text_style_control":[1468,37058,43,94.4],"search_style_control":[1193,3788,16,72.7]}},"gemini-3-flash":{"ar":{"text_style_control":[1474,30225,33,95.7],"webdev":[1438,10453,62,52.4],"vision_style_control":[1272,36679,31,92],"document_style_control":[1439,7158,36,32.5]}},"chatgpt-4o":{"ar":{"text_style_control":[1443,80677,80,88.9],"vision_style_control":[1240,23057,54,82.4]}},"ernie-5-0":{"ar":{"text_style_control":[1449,9561,72,90.2],"vision_style_control":[1219,3229,65,76.1]}},"gpt-5-3-codex":{"bs":{"swebench":[0.7479,75,15,32],"terminalbench":[0.784,94.9,6,45],"alebench":[1655.22,74.8,8,102],"apex_agents":[0.469,72.4,19,53],"metr":[0.7454,84.4,6,35],"vending2":[5940.124,54.9,15,55],"weirdml":[0.793,80.8,9,128],"webdev_arena":[1369,37.9,65,94]}},"gpt-5-4-pro":{"bs":{"gpqa":[0.946,99.9,4,205],"hle":[0.4432,94.8,3,43],"arc_agi_2":[0.8333,91.2,11,82],"arc_agi":[0.945,96.1,14,84],"simpleqa":[0.463,57.4,30,72],"simplebench":[0.741,89,9,82],"enigma":[0.2382,62.5,5,42],"critpt":[0.3,96.9,6,121],"chess":[0.586,93,5,138],"frontiermath":[0.5,97.4,3,71],"weirdml":[0.5744,47.7,34,128]}},"mimo-v2-omni":{"ar":{"text_style_control":[1430,19414,103,86],"vision_style_control":[1217,10120,67,75.4]}},"kimi-k2-5-instant":{"ar":{"text_style_control":[1431,7987,100,86.2],"webdev":[1406,3095,74,46.2],"vision_style_control":[1237,3872,55,81.6]}},"muse-spark-1-1":{"bs":{"simpleqa":[0.5779,76,14,72],"critpt":[0.151,48.8,27,121],"proofbench":[0.39,39.4,24,64],"scicode":[0.5822,98.4,5,112],"deepswe":[0.5332,61.1,19,26],"apex_agents":[0.581,92.9,6,53],"vending2":[6520.475,60.3,11,55],"gbaeval":[0.0792,10.2,13,23],"surface_evolver":[0.525,46.5,13,23],"webdev_arena":[1539.02,69.7,21,94]},"ar":{"text_style_control":[1493,27615,11,99.9],"webdev":[1542,7549,29,72.3],"agent":[-0.0297,95367,31,39.8],"vision_style_control":[1281,8447,22,94.6],"document_style_control":[1479,4885,12,80.2]}},"gemini-3-deep":{"bs":{"arc_agi_2":[0.8458,92.6,9,82],"arc_agi":[0.96,97.7,9,84],"critpt":[0.2571,83,10,121]}},"qwen3-vl-235b-a22b-instruct":{"ar":{"text_style_control":[1414,11219,131,82.5],"vision_style_control":[1215,12250,70,74.9]}},"hy4-preview":{"ar":{"webdev":[1624,2321,11,88.2],"agent":[0.0523,19613,10,71.3]}},"gemma-4-31b":{"ar":{"text_style_control":[1451,5894,68,90.7],"webdev":[1364,10139,90,38.2],"vision_style_control":[1261,35713,38,88.7],"document_style_control":[1445,12326,34,38.8]}},"claude-sonnet-4-6":{"bs":{"gpqa":[0.8737,89.9,48,205],"arc_agi_2":[0.6042,66.1,22,82],"arc_agi":[0.865,87.8,28,84],"simpleqa":[0.355,39.9,43,72],"critpt":[0.0314,10.1,54,121],"forecastbench":[61.2,88.1,13,75],"chess":[0.13,20.6,73,138],"frontiermath":[0.324,62.8,17,71],"frontiermath_t4":[0.083,21,22,56],"aime":[0.8579,85.4,63,186],"proofbench":[0.45,45.5,22,64],"swebench":[0.7521,76.5,14,32],"terminalbench":[0.534,61,16,45],"scicode":[0.4676,70.4,42,112],"cursorbench":[0.49,31.1,20,22],"frontiercode":[0.2431,34.7,23,31],"alebench":[1327.3,57.8,16,102],"deepswe":[0.2993,17.1,25,26],"apex_agents":[0.407,61.1,23,53],"osworld2":[0.093,22.4,6,9],"osworld":[72.1,100,1,9],"deepresearch":[0.549,99,2,25],"vending2":[7204.14,66.6,10,55],"exploitbench":[0.236,18.2,5,9],"weirdml":[0.6607,60.8,22,128],"blueprint2":[0.0672,16.7,18,24],"gbaeval":[0.4876,63,8,23],"webdev_arena":[1522.47,66.6,25,94]},"ar":{"text_style_control":[1473,66208,37,95.5],"webdev":[1521,21642,36,68.4],"agent":[-0.0127,39399,29,46.3],"vision_style_control":[1275,25552,29,92.9],"document_style_control":[1478,57813,13,78.1]}},"deepseek-v4-pro-0813":{"bs":{"gpqa":[0.9167,95.9,21,205],"arc_agi_2":[0.6125,67,21,82],"arc_agi":[0.905,92,21,84],"simpleqa":[0.5291,68.1,17,72],"critpt":[0.18,58.1,20,121],"chess":[0.47,74.6,13,138],"aime":[0.9861,98.6,14,186],"proofbench":[0.5,50.5,19,64],"scicode":[0.4919,76.4,33,112],"alebench":[1403.15,61.7,14,102],"weirdml":[0.6622,61,21,128],"webdev_arena":[1581.64,77.7,14,94]}},"qwen3-vl-235b-a22b-thinking":{"ar":{"text_style_control":[1395,7780,154,78.2],"vision_style_control":[1188,2389,87,66.9]}},"qwen3-5":{"ar":{"text_style_control":[1465,21476,49,93.8]}},"hy3":{"ar":{"text_style_control":[1456,8047,60,91.7],"webdev":[1513,3586,40,66.8],"agent":[-0.0469,26255,33,33.2]}},"hunyuan-vision-1-5":{"ar":{"text_style_control":[1395,2171,155,78.2],"vision_style_control":[1156,2433,100,57.5]}},"gpt-5-5-search":{"ar":{"search_style_control":[1224,89873,3,91.2]}},"qwen3-8-flash-next":{"ar":{"webdev":[1635,2779,9,90.3],"agent":[0.004,30755,26,52.7]}},"claude-opus-4-6-search":{"ar":{"search_style_control":[1223,134699,4,91]}},"gemini-2-5-flash-lite-preview-09-2025-no":{"ar":{"text_style_control":[1380,46382,174,74.8],"vision_style_control":[1173,4779,93,62.5]}},"gpt-5-3-chat":{"ar":{"text_style_control":[1449,32727,71,90.3]}},"muse-spark-1-2":{"bs":{"simpleqa":[0.603,80.1,12,72],"simplebench":[0.745,89.7,8,82],"critpt":[0.1771,57.2,22,121],"proofbench":[0.43,43.4,23,64],"scicode":[0.5637,93.9,11,112],"deepswe":[0.5487,64.1,16,26],"weirdml":[0.603,52,31,128],"webdev_arena":[1533.68,68.7,24,94]},"ar":{"text_style_control":[1500,3227,4,100],"webdev":[1534,2065,34,70.9],"agent":[-0.0176,24050,30,44.4],"vision_style_control":[1292,1841,9,97.7]}},"gpt-5-5-instant":{"bs":{"gpqa":[0.8251,83.2,69,205],"critpt":[0,0,90,121],"chess":[0.12,19.1,77,138],"aime":[0.6806,67.3,91,186],"scicode":[0.4861,74.9,37,112]},"ar":{"text_style_control":[1474,25850,32,95.8],"vision_style_control":[1278,7226,28,93.6],"document_style_control":[1460,8497,26,57.5]}},"glm-4-6v":{"ar":{"text_style_control":[1378,2762,175,74.5],"vision_style_control":[1161,2352,97,59]}},"longcat-flash-chat-2602":{"ar":{"text_style_control":[1435,27962,93,87.2]}},"qwen3-next-80b-a3b-instruct":{"bs":{"fiction120k":[0.625,54.1,16,40]},"ar":{"text_style_control":[1399,22529,150,79.2]}},"gemini-3-1-flash-lite-preview":{"ar":{"text_style_control":[1432,60405,98,86.5],"webdev":[1254,13634,114,17.1],"vision_style_control":[1235,25958,57,80.9]}},"gpt-5-6-sol-xhigh-codex-harness":{"ar":{"webdev":[1617,11916,14,86.9]}},"deepseek-v4-1-flash":{"ar":{"webdev":[1614,1361,16,86.2]}},"amazon-nova-experimental-chat-26-02-10":{"ar":{"text_style_control":[1426,3369,108,85.1]}},"nvidia-nemotron-3-ultra-550b-a55b-nvfp4":{"ar":{"text_style_control":[1426,10693,109,85]}},"grok-4-fast-chat":{"ar":{"text_style_control":[1418,6335,119,83.4]}},"amazon-nova-experimental-chat-26-01-10":{"ar":{"text_style_control":[1415,3346,128,82.6]}},"grok-3-preview-02-24":{"ar":{"text_style_control":[1412,32414,135,81.9]}},"gemini-3-1-pro-grounding":{"ar":{"search_style_control":[1208,113282,6,81.4]}},"muse-glimmer":{"ar":{"text_style_control":[1427,3666,104,85.4],"webdev":[1360,1512,93,37.3]}},"qwen3-235b-a22b-no":{"ar":{"text_style_control":[1403,37389,144,79.9]}},"longcat-flash-chat":{"ar":{"text_style_control":[1401,11154,147,79.6]}},"qwen2-5":{"bs":{"livebench":[62.29,50.7,14,48],"lech_writing":[7.29,46.7,34,45]},"ar":{"text_style_control":[1374,32417,181,73.5]}},"deepseek-reasoner":{"bs":{"gpqa":[0.8342,84.4,65,205],"chess":[0.14,22.2,69,138],"aime":[0.8782,87.5,53,186],"aider":[74.2,85.4,7,56]}},"glm-4-5v":{"ar":{"text_style_control":[1353,4817,200,68.8],"vision_style_control":[1154,3255,103,56.8]}},"amazon-nova-experimental-chat-12-10":{"ar":{"text_style_control":[1395,3632,157,78.1]}},"step-3-5-flash":{"ar":{"text_style_control":[1394,57137,158,78]}},"gemini-3-pro-grounding":{"ar":{"search_style_control":[1201,37024,9,77.6]}},"claude-sonnet-4-6-search":{"ar":{"search_style_control":[1201,134905,10,77.4]}},"hunyuan-hy3":{"ar":{"text_style_control":[1413,6614,134,82.2],"webdev":[1356,1395,97,36.7]}},"gemini-2-5-pro-exp-03-25":{"bs":{"gpqa":[0.8384,85,63,205],"hle":[0.1816,31.5,18,43],"simplebench":[0.516,49.2,40,82],"enigma":[0.0414,9.5,26,42],"aider":[72.9,83.7,9,56],"livebench":[82.35,100,1,48],"balrog":[0.433,59.6,6,32],"geobench":[4019,85.6,4,28],"fiction120k":[0.906,90.8,4,40],"lech_writing":[8.05,78.2,17,45]}},"claude-mythos-preview-early":{"bs":{"metr":[0.8521,100,1,35],"exploitbench":[0.738,100,1,9]}},"hunyuan-t1":{"ar":{"text_style_control":[1387,4580,167,76.5]}},"minimax-m1":{"bs":{"fiction120k":[0.594,50,21,40]},"ar":{"text_style_control":[1364,34030,189,71.3]}},"glm-5v-turbo":{"ar":{"text_style_control":[1433,9361,97,86.6],"webdev":[1401,2185,75,45.2],"vision_style_control":[1228,37424,61,78.9],"document_style_control":[1400,6995,44,0]}},"gdm-ai-co-mathematician":{"bs":{"frontiermath_t4":[0.479,100,1,56]}},"step-3":{"ar":{"text_style_control":[1349,6273,205,68.1],"vision_style_control":[1145,3209,108,54.2]}},"hunyuan-turbos":{"ar":{"text_style_control":[1383,10586,171,75.4]}},"trinity-large":{"ar":{"text_style_control":[1378,29742,176,74.5]}},"claude-sonnet-5-search":{"ar":{"search_style_control":[1196,40230,12,74.3]}},"gpt-5-4-search":{"ar":{"search_style_control":[1195,110116,14,73.4]}},"grok-4-1-fast-search":{"ar":{"search_style_control":[1194,81507,15,73.2]}},"qwen3-next-80b-a3b-thinking":{"ar":{"text_style_control":[1369,13380,184,72.4]}},"o3-search":{"ar":{"search_style_control":[1192,20644,18,71.8]}},"amazon-nova-experimental-chat-11-10":{"ar":{"text_style_control":[1365,25086,188,71.6]}},"gemini-3-flash-grounding":{"ar":{"search_style_control":[1191,149334,19,71.4]}},"o3":{"bs":{"gpqa":[0.8182,82.2,73,205],"hle":[0.2032,36.7,16,43],"arc_agi_2":[0.0653,7.1,44,82],"arc_agi":[0.757,76.5,35,84],"simpleqa":[0.494,62.5,22,72],"simplebench":[0.531,51.8,38,82],"enigma":[0.1309,33.6,10,42],"critpt":[0.014,4.5,66,121],"forecastbench":[62.5,100,1,75],"chess":[0.38,60.3,24,138],"frontiermath":[0.1869,35.9,33,71],"frontiermath_t4":[0.0208,5.3,39,56],"aime":[0.8444,84.1,64,186],"math_l5":[0.9777,99.7,4,90],"swebench":[0.6232,30.1,27,32],"gso":[0.088,16.9,14,28],"aider":[81.3,94.5,4,56],"alebench":[933.55,37.4,40,102],"apex_agents":[0.314,44.1,32,53],"metr":[0.6544,66.1,14,35],"osworld":[23,0,8,9],"gdpval":[0.308,33.9,7,11],"deepresearch":[0.452,50.5,16,25],"weirdml":[0.5242,40.1,43,128],"vpct":[0.52,36,7,27],"geobench":[3930,80.4,7,28],"cad_eval":[0.74,100,1,15],"fiction120k":[1,100,1,40],"lech_writing":[8.39,92.3,5,45]},"ar":{"text_style_control":[1432,58579,99,86.4],"vision_style_control":[1215,45554,68,75.1]}},"gpt-5-4-pro-web-app":{"bs":{"frontiermath_t4":[0.375,95.1,3,56]}},"nvidia-nemotron-3-super-120b-a12b":{"ar":{"text_style_control":[1361,7458,192,70.5]}},"step-1o-turbo":{"ar":{"text_style_control":[1320,8858,247,61.5],"vision_style_control":[1156,1900,101,57.5]}},"mistral-large-3":{"ar":{"text_style_control":[1413,69028,133,82.2],"webdev":[1230,812,120,12.3],"vision_style_control":[1201,6186,77,70.9]}},"solar-pro4":{"ar":{"text_style_control":[1376,2420,177,74.1],"webdev":[1371,1403,88,39.6]}},"intellect-3":{"ar":{"text_style_control":[1356,5279,197,69.6]}},"command-a-03":{"ar":{"text_style_control":[1354,55449,198,69]}},"claude-opus-4-5-search":{"ar":{"search_style_control":[1187,61573,20,68.9]}},"nvidia-nemotron-3-5-lightning-30b-a3b-nvfp4":{"ar":{"text_style_control":[1351,8338,202,68.5]}},"gpt-5-6-terra-xhigh-codex-harness":{"ar":{"webdev":[1521,7694,35,68.4]}},"qwen3-7-flash":{"bs":{"gpqa":[0.8232,82.9,70,205],"chess":[0.23,36.5,46,138],"aime":[0.8667,86.3,55,186]}},"amazon-nova-experimental-chat-10-20":{"ar":{"text_style_control":[1350,11368,204,68.1]}},"gpt-5-6-luna-xhigh-codex-harness":{"ar":{"webdev":[1519,7828,37,68]}},"seed-2-1-pro":{"ar":{"webdev":[1519,9333,38,67.9]}},"gpt-5-2-pro":{"bs":{"arc_agi_2":[0.5416,59.3,26,82],"arc_agi":[0.905,92,22,84],"simplebench":[0.574,59.4,30,82],"frontiermath_t4":[0.313,79.4,5,56]}},"llama-3-1-nemotron-ultra-253b-v1":{"ar":{"text_style_control":[1348,2549,208,67.6]}},"amazon-nova-experimental-chat-10-09":{"ar":{"text_style_control":[1347,2775,210,67.5]}},"mimo-v2-flash-non":{"ar":{"text_style_control":[1392,46116,159,77.5],"webdev":[1331,5401,103,31.8]}},"ling-flash-2-0":{"ar":{"text_style_control":[1344,6850,215,66.9]}},"nvidia-llama-3-3-nemotron-super-49b-v1-5":{"ar":{"text_style_control":[1343,3313,216,66.7]}},"glm-4-plus":{"ar":{"text_style_control":[1343,5760,218,66.5]}},"gpt-5-1-search":{"ar":{"search_style_control":[1183,59909,21,66.4]}},"granite-4-2-30b":{"ar":{"text_style_control":[1342,3255,219,66.4]}},"gpt-5-5-xhigh-codex-harness":{"ar":{"webdev":[1510,14946,41,66.3]}},"gpt-5-search":{"ar":{"search_style_control":[1183,20781,22,66.2]}},"hunyuan-turbo":{"ar":{"text_style_control":[1341,2290,221,66.1]}},"gemini-2-5-pro-preview-03-25":{"bs":{"arc_agi":[0.33,32,61,84],"simplebench":[0.516,49.2,41,82],"forecastbench":[61.3,89.6,11,75],"math_l5":[0.9556,95.4,11,90],"aider":[72.9,83.7,10,56],"vpct":[0.48,28.9,8,27],"cad_eval":[0.64,84.9,2,15],"fiction120k":[0.719,66.3,9,40]}},"nova-2-lite":{"ar":{"text_style_control":[1336,12120,224,65.1]}},"gemini-advanced":{"ar":{"text_style_control":[1336,50148,226,65]}},"llama-3-1-405b-instruct-bf16":{"ar":{"text_style_control":[1335,41375,229,64.9]}},"step-2":{"ar":{"text_style_control":[1334,4833,230,64.5]}},"llama-3-1-405b-instruct-fp8":{"ar":{"text_style_control":[1333,59656,231,64.5]}},"olmo-3-1-32b-instruct":{"ar":{"text_style_control":[1330,11452,232,63.7]}},"gemini-3-flash-preview":{"bs":{"gpqa":[0.8939,92.7,37,205],"arc_agi_2":[0.3361,36.8,32,82],"arc_agi":[0.8467,85.9,30,84],"simpleqa":[0.668,90.6,8,72],"simplebench":[0.611,66,21,82],"forecastbench":[58.5,47.8,48,75],"chess":[0.4,63.5,21,138],"frontiermath":[0.3564,69.2,14,71],"frontiermath_t4":[0.0417,10.6,28,56],"aime":[0.9556,95.4,27,186],"proofbench":[0.15,15.2,46,64],"swebench":[0.7541,77.2,13,32],"terminalbench":[0.643,75.8,10,45],"gso":[0.098,19.2,13,28],"alebench":[1367.2,59.9,15,102],"apex_agents":[0.395,58.9,24,53],"deepresearch":[0.498,73.5,7,25],"vending2":[3634.716,33.7,33,55],"balrog":[0.481,73,3,32],"weirdml":[0.616,54,26,128],"blueprint2":[0,0,20,24],"vpct":[0.726,72.7,3,27],"geobench":[4333,100,1,28],"webdev_arena":[1382.78,40.5,63,94]}},"glm-5-3-flash":{"bs":{"gpqa":[0.9015,93.8,34,205],"critpt":[0.1543,49.8,26,121],"chess":[0.14,22.2,70,138],"aime":[0.9389,93.7,34,186],"proofbench":[0.21,21.2,34,64],"scicode":[0.4606,68.7,43,112],"alebench":[303.55,4.8,94,102],"deepswe":[0.6339,80.1,13,26],"surface_evolver":[0.525,46.5,14,23],"webdev_arena":[1604.43,81.9,9,94]},"ar":{"text_style_control":[1475,10038,29,96.1],"webdev":[1607,2925,17,84.9],"agent":[0.0189,27007,22,58.5],"vision_style_control":[1275,3110,30,92.7]}},"llama-3-3-nemotron-49b-super-v1":{"ar":{"text_style_control":[1328,2218,235,63.2]}},"hunyuan-large":{"ar":{"text_style_control":[1326,3738,238,62.9]}},"gpt-5-5-high-codex-harness":{"ar":{"webdev":[1487,17020,47,61.8]}},"ring-flash-2-0":{"ar":{"text_style_control":[1321,6899,246,61.7]}},"claude-sonnet-4-5-search":{"ar":{"search_style_control":[1175,127378,23,61.6]}},"molmo-2-8b":{"ar":{"text_style_control":[1328,791,234,63.3],"vision_style_control":[1107,1134,121,43]}},"gemma-3n-e4b-it":{"ar":{"text_style_control":[1317,22082,253,60.9]}},"hunyuan-large-vision":{"ar":{"text_style_control":[1294,5259,274,55.7],"vision_style_control":[1149,1275,104,55.4]}},"qwen2-5-plus":{"ar":{"text_style_control":[1315,10187,254,60.3]}},"nvidia-nemotron-3-nano-30b-a3b-bf16":{"ar":{"text_style_control":[1314,15325,255,60.2]}},"athene-v2-chat":{"ar":{"text_style_control":[1314,24739,257,60.2]}},"hunyuan-standard":{"ar":{"text_style_control":[1311,3904,260,59.6]}},"grok-2-mini":{"ar":{"text_style_control":[1308,52567,262,58.9]}},"mercury":{"ar":{"text_style_control":[1308,1930,263,58.8]}},"olmo-3-32b":{"ar":{"text_style_control":[1307,5682,265,58.6]}},"mistral-small-3-1-24b-instruct-2503":{"ar":{"text_style_control":[1303,32618,271,57.7],"vision_style_control":[1127,28542,112,49.1]}},"athene-70b":{"ar":{"text_style_control":[1306,19621,266,58.5]}},"gpt-5-4-high-codex-harness":{"ar":{"webdev":[1463,1277,54,57.2]}},"llama-3-1-nemotron-70b-instruct":{"ar":{"text_style_control":[1299,7140,273,56.8]}},"claude-opus-4-1-search":{"ar":{"search_style_control":[1167,76933,24,56.6]}},"gpt-5-5-codex-harness":{"ar":{"webdev":[1458,15012,56,56.2]}},"granite-4-2-3b":{"ar":{"text_style_control":[1294,3072,275,55.7]}},"jamba-1-5-large":{"ar":{"text_style_control":[1289,8662,278,54.7]}},"reka-core":{"ar":{"text_style_control":[1288,7312,280,54.4]}},"granite-4-2-8b":{"ar":{"text_style_control":[1287,3087,282,54.1]}},"llama-3-1-nemotron-51b-instruct":{"ar":{"text_style_control":[1286,3749,283,54]}},"llama-3-1-tulu-3-70b":{"ar":{"text_style_control":[1286,2846,285,53.9]}},"ibm-granite-h-small":{"ar":{"text_style_control":[1286,5532,286,53.8]}},"olmo-3-1-32b":{"ar":{"text_style_control":[1286,8117,287,53.8]}},"gpt-5-4-medium-codex-harness":{"ar":{"webdev":[1443,1316,60,53.3]}},"gpt-5-2-search":{"ar":{"search_style_control":[1162,52712,25,53.2]}},"gemma-2-9b-it-simpo":{"ar":{"text_style_control":[1280,10072,289,52.6]}},"grok-4-fast-search":{"ar":{"search_style_control":[1160,41794,26,52.5]}},"nemotron-4-340b-instruct":{"ar":{"text_style_control":[1277,19659,290,51.9]}},"llama-3-70b-instruct":{"ar":{"text_style_control":[1276,156876,291,51.8]}},"command-r-plus-08-2024":{"ar":{"text_style_control":[1276,9866,292,51.7]}},"mistral-small-24b-instruct-2501":{"ar":{"text_style_control":[1274,14681,294,51.3]}},"glm-4":{"ar":{"text_style_control":[1273,9788,295,51.1]}},"qwen-3-8-27b":{"ar":{"agent":[-0.0008,28536,27,50.9]}},"reka-flash":{"ar":{"text_style_control":[1272,7536,296,50.9]}},"kimi-k2-thinking-turbo":{"bs":{"gpqa":[0.8422,85.5,62,205],"chess":[0.2,31.8,55,138],"aime":[0.8306,82.6,70,186],"webdev_arena":[1337,32,74,94]},"ar":{"text_style_control":[1430,61088,102,86],"webdev":[1323,12631,106,30.2]}},"c4ai-aya-expanse-32b":{"ar":{"text_style_control":[1267,27124,298,49.7]}},"deepseek-coder-v2":{"ar":{"text_style_control":[1265,15147,300,49.3]}},"command-r-plus":{"ar":{"text_style_control":[1262,77554,302,48.5]}},"step-1o-vision-32k-highres":{"ar":{"vision_style_control":[1125,2833,115,48.2]}},"gpt-5-3-codex-codex-harness":{"ar":{"webdev":[1409,2514,72,46.8]}},"qwen2-5-vl-32b-instruct":{"ar":{"vision_style_control":[1119,1490,119,46.5]}},"claude-opus-4-search":{"ar":{"search_style_control":[1151,31037,27,46.5]}},"olmo-2-0325-32b-instruct":{"ar":{"text_style_control":[1251,3334,307,46.3]}},"command-r-08-2024":{"ar":{"text_style_control":[1250,10140,308,46]}},"qwq-32b":{"bs":{"gpqa":[0.6534,59.3,111,205],"forecastbench":[58.3,44.8,51,75],"chess":[0.05,7.9,94,138],"aime":[0.5917,58.2,103,186],"aider":[20.9,16.5,45,56],"livebench":[71.96,76.2,6,48],"lech_writing":[8.02,77,19,45]},"ar":{"text_style_control":[1336,25090,225,65]}},"jamba-1-5-mini":{"ar":{"text_style_control":[1240,8858,311,43.6]}},"gemini-pro-dev-api":{"ar":{"text_style_control":[1236,18354,313,42.9]}},"qwen3-6-max-preview":{"bs":{"gpqa":[0.8737,89.9,49,205],"simpleqa":[0.52,66.7,18,72],"simplebench":[0.63,69.4,16,82],"chess":[0.2,31.8,56,138],"frontiermath":[0.231,44.6,26,71],"frontiermath_t4":[0.0417,10.6,29,56],"aime":[0.9111,90.9,44,186],"swebench":[0.7665,81.7,10,32],"vending2":[4254.1867,39.4,28,55],"webdev_arena":[1478.88,58.5,37,94]},"ar":{"text_style_control":[1460,5186,53,92.7],"webdev":[1479,2601,49,60.3]}},"reka-flash-21b-20240226-online":{"ar":{"text_style_control":[1233,15450,315,42.2]}},"ppl-sonar-pro":{"ar":{"search_style_control":[1143,28519,28,41.8]}},"video-salmonn-2plus":{"bs":{"video_mme":[0.797,100,1,48]}},"gemini-2-5-pro-grounding":{"ar":{"search_style_control":[1142,83404,29,41.3]}},"command-r":{"ar":{"text_style_control":[1227,54036,319,40.7]}},"reka-flash-21b":{"ar":{"text_style_control":[1227,24806,320,40.7]}},"mimo-v2-pro":{"bs":{"alebench":[785.17,29.7,56,102],"webdev_arena":[1433.51,50,50,94]},"ar":{"text_style_control":[1448,24365,73,90.1],"webdev":[1433,6963,67,51.5]}},"llama-3-8b-instruct":{"ar":{"text_style_control":[1223,104642,322,40]}},"gemini-pro":{"ar":{"text_style_control":[1223,6390,323,40]}},"c4ai-aya-expanse-8b":{"ar":{"text_style_control":[1223,9818,324,39.9]}},"mistral":{"ar":{"text_style_control":[1222,34550,325,39.8]}},"llama-3-1-tulu-3-8b":{"ar":{"text_style_control":[1220,2896,326,39.3]}},"ppl-sonar-reasoning-pro":{"ar":{"search_style_control":[1138,29055,30,38.9]}},"mistral-medium-3-5":{"ar":{"text_style_control":[1426,10996,106,85.2],"webdev":[1265,2154,112,19.1],"agent":[-0.1012,9879,41,12.3],"vision_style_control":[1199,5090,80,70.3]}},"gpt-5-2-search-non":{"ar":{"search_style_control":[1137,75658,31,38.1]}},"zephyr-orpo-141b-a35b-v0-1":{"ar":{"text_style_control":[1213,4652,327,37.6]}},"deepseek-v4-flash-0731":{"bs":{"gpqa":[0.9104,95,25,205],"arc_agi_2":[0.6139,67.2,20,82],"arc_agi":[0.89,90.4,24,84],"simpleqa":[0.3363,36.9,49,72],"simplebench":[0.611,66,22,82],"critpt":[0.1657,53.5,24,121],"chess":[0.33,52.4,29,138],"aime":[0.9444,94.3,32,186],"proofbench":[0.56,56.6,14,64],"scicode":[0.4988,78.1,31,112],"frontiercode":[0.188,22.3,24,31],"alebench":[1306.08,56.7,20,102],"weirdml":[0.6296,56.1,24,128],"webdev_arena":[1579.1,77.2,15,94]}},"qwen3-7-max":{"bs":{"gpqa":[0.9091,94.8,27,205],"simpleqa":[0.5577,72.8,15,72],"simplebench":[0.704,82.5,11,82],"critpt":[0.1343,43.4,29,121],"chess":[0.19,30.2,62,138],"aime":[0.9556,95.4,28,186],"proofbench":[0.26,26.3,31,64],"swebench":[0.7727,83.9,7,32],"scicode":[0.4884,75.5,35,112],"alebench":[1189.4,50.7,26,102],"gbaeval":[0.0041,0.5,20,23],"webdev_arena":[1516.65,65.5,28,94]},"ar":{"text_style_control":[1473,3705,34,95.6],"webdev":[1517,8363,39,67.6],"agent":[-0.0312,37494,32,39.2]}},"granite-3-1-8b-instruct":{"ar":{"text_style_control":[1208,3090,330,36.6]}},"qwen2-vl-72b":{"ar":{"vision_style_control":[1085,5937,125,36.5]}},"gemma-2-2b-it":{"ar":{"text_style_control":[1200,46616,333,34.8]}},"phi-3-medium-4k-instruct":{"ar":{"text_style_control":[1198,25055,334,34.3]}},"kimi-k2-0905":{"bs":{"aider":[59.1,65.9,21,56],"alebench":[267.12,2.9,95,102]},"ar":{"text_style_control":[1418,11568,120,83.3]}},"gemini-3-deep-think-2-26":{"bs":{"arc_agi":[0.96,97.7,10,84]}},"gemini-2-5-pro-preview-05-06":{"bs":{"gpqa":[0.6667,61.1,106,205],"hle":[0.178,30.6,20,43],"enigma":[0.0236,4.7,32,42],"math_l5":[0.959,96.1,10,90],"aider":[76.9,88.9,6,56],"tac":[0.393,58.4,5,14],"vpct":[0.405,15.6,13,27],"geobench":[4085,89.4,3,28],"fiction120k":[0.719,66.3,10,40],"lech_writing":[8.09,79.9,16,45]}},"qwen1-5-14b-chat":{"ar":{"text_style_control":[1191,17839,337,32.8]}},"internlm2-5-20b-chat":{"ar":{"text_style_control":[1191,9901,338,32.7]}},"gemma-4-26b-a4b-it":{"bs":{"gpqa":[0.7323,70.3,92,205],"chess":[0.06,9.5,90,138],"aime":[0.8222,81.8,71,186]}},"wizardlm-70b":{"ar":{"text_style_control":[1184,8214,340,31.3]}},"granite-3-0-8b-instruct":{"ar":{"text_style_control":[1183,6638,342,31]}},"openchat-3-5":{"ar":{"text_style_control":[1183,7968,343,30.9]}},"gemma-1-1-7b-it":{"ar":{"text_style_control":[1182,23893,345,30.8]}},"step-1v":{"ar":{"vision_style_control":[1064,1534,128,30.4]}},"snowflake-arctic-instruct":{"ar":{"text_style_control":[1180,32832,346,30.3]}},"granite-3-1-2b-instruct":{"ar":{"text_style_control":[1179,3188,347,30]}},"swe-1-7":{"bs":{"frontiercode":[0.4233,75.1,13,31]}},"tulu-2-dpo-70b":{"ar":{"text_style_control":[1177,6535,348,29.8]}},"openhermes-2-5-mistral-7b":{"ar":{"text_style_control":[1176,5006,349,29.4]}},"vicuna-33b":{"ar":{"text_style_control":[1173,22479,350,28.7]}},"grok-4-search":{"ar":{"search_style_control":[1121,19108,32,28.7]}},"starling-lm-7b":{"ar":{"text_style_control":[1171,16056,351,28.3]}},"llama-2-70b-chat":{"ar":{"text_style_control":[1170,38492,353,28.2]}},"qwen3-5-4b":{"bs":{"aime":[0.5583,54.8,108,186]}},"fireworks-kimi-k2p5":{"bs":{"gpqa":[0.876,90.2,47,205],"chess":[0.12,19.1,78,138],"frontiermath":[0.279,54,21,71],"frontiermath_t4":[0.042,10.7,26,56],"aime":[0.922,92,40,186]}},"nous-hermes-2-mixtral-8x7b-dpo":{"ar":{"text_style_control":[1164,3777,356,26.8]}},"inkling-small":{"bs":{"gpqa":[0.8851,91.5,40,205],"arc_agi_2":[0.4014,43.9,29,82],"arc_agi":[0.84,85.2,31,84],"simpleqa":[0.191,13.4,61,72],"critpt":[0.0829,26.8,41,121],"chess":[0.18,28.6,64,138],"aime":[0.9,89.8,46,186],"proofbench":[0.06,6.1,55,64],"scicode":[0.4873,75.2,36,112],"webdev_arena":[1401.56,44,54,94]},"ar":{"text_style_control":[1405,18844,141,80.4],"webdev":[1407,5058,73,46.4],"agent":[-0.0709,12366,39,24],"vision_style_control":[1208,5002,73,72.9]}},"granite-3-0-2b-instruct":{"ar":{"text_style_control":[1156,6837,357,25.1]}},"molmo-72b":{"ar":{"vision_style_control":[1045,3048,131,24.7]}},"llama2-70b-steerlm-chat":{"ar":{"text_style_control":[1154,3585,358,24.7]}},"solar-10-7b-instruct-v1-0":{"ar":{"text_style_control":[1152,4155,360,24.1]}},"dolphin-2-2-1-mistral-7b":{"ar":{"text_style_control":[1152,1679,361,24.1]}},"hunyuan-standard-vision":{"ar":{"vision_style_control":[1042,809,132,23.8]}},"mpt-30b-chat":{"ar":{"text_style_control":[1150,2572,362,23.8]}},"wizardlm-13b":{"ar":{"text_style_control":[1149,7044,363,23.5]}},"mistral-7b-instruct-v0-2":{"ar":{"text_style_control":[1149,19402,364,23.5]}},"glm-4-7-flash":{"bs":{"gpqa":[0.6054,52.6,118,205],"chess":[0,0,115,138],"aime":[0.5833,57.3,104,186]},"ar":{"text_style_control":[1366,11491,186,71.8]}},"falcon-180b-chat":{"ar":{"text_style_control":[1148,1295,365,23.2]}},"grok-4":{"bs":{"gpqa":[0.87,89.4,50,205],"arc_agi_2":[0.1598,17.5,38,82],"arc_agi":[0.6667,67.1,39,84],"simplebench":[0.605,64.9,25,82],"forecastbench":[60.9,83.6,19,75],"chess":[0.28,44.5,36,138],"frontiermath":[0.1966,37.8,31,71],"frontiermath_t4":[0.0208,5.3,40,56],"aime":[0.84,83.6,68,186],"terminalbench":[0.272,25.4,35,45],"aider":[79.6,92.4,5,56],"apex_agents":[0.303,42,34,53],"metr":[0.6658,68.4,13,35],"gdpval":[0.211,0,10,11],"deepresearch":[0.473,61,11,25],"balrog":[0.436,60.5,4,32],"cybench":[0.43,34.4,4,21],"weirdml":[0.4573,29.9,58,128],"geobench":[2719,9.4,25,28],"fiction120k":[0.969,99,3,40],"lech_writing":[7.69,63.3,24,45]},"ar":{"text_style_control":[1411,39297,137,81.8],"vision_style_control":[1183,30167,89,65.6]}},"qwen3-30b-a3b-instruct-2507":{"bs":{"gpqa":[0.5562,45.8,127,205],"chess":[0.02,3.2,107,138],"aime":[0.6222,61.3,101,186]},"ar":{"text_style_control":[1382,23222,173,75.4]}},"qwen1-5-7b-chat":{"ar":{"text_style_control":[1144,4737,366,22.2]}},"phi-3-mini-4k-instruct-june":{"ar":{"text_style_control":[1143,12297,367,22.1]}},"vicuna-13b":{"ar":{"text_style_control":[1141,19367,368,21.7]}},"granite-4-1-8b":{"ar":{"text_style_control":[1306,4023,267,58.4],"webdev":[1192,1701,124,5.1]}},"qwen-14b-chat":{"ar":{"text_style_control":[1139,4964,370,21.2]}},"palm-2":{"ar":{"text_style_control":[1139,8554,371,21.2]}},"llama-3-2-vision-90b-instruct":{"ar":{"vision_style_control":[1033,8682,133,20.9]}},"gemma-7b-it":{"ar":{"text_style_control":[1137,8925,372,20.9]}},"codellama-34b-instruct":{"ar":{"text_style_control":[1137,7366,373,20.7]}},"zephyr-7b":{"ar":{"text_style_control":[1131,11118,374,19.3]}},"phi-3-mini-128k-instruct":{"ar":{"text_style_control":[1129,20685,375,19.1]}},"internvl2-26b":{"ar":{"vision_style_control":[1025,5148,136,18.7]}},"guanaco-33b":{"ar":{"text_style_control":[1127,2921,377,18.6]}},"kimi-k2-7-code":{"bs":{"gpqa":[0.8788,90.6,43,205],"simpleqa":[0.365,41.6,42,72],"simplebench":[0.579,60.3,29,82],"critpt":[0.1,32.3,36,121],"chess":[0.21,33.3,52,138],"aime":[0.9556,95.4,29,186],"scicode":[0.4745,72.1,38,112],"cursorbench":[0.497,33.1,19,22],"frontiercode":[0.3006,47.6,18,31],"alebench":[886.23,35,47,102],"deepswe":[0.3053,18.3,24,26],"apex_agents":[0.419,63.3,22,53],"vending2":[5082.936,47,24,55],"weirdml":[0.5412,42.6,39,128],"gbaeval":[0.0085,1.1,18,23],"surface_evolver":[0.4875,41.7,15,23],"webdev_arena":[1472.65,57.3,39,94]},"ar":{"webdev":[1473,4683,51,59.1]}},"stripedhyena-nous-7b":{"ar":{"text_style_control":[1121,5182,379,17.3]}},"kat-coder-pro-v1":{"ar":{"webdev":[1255,1458,113,17.2]}},"seed-oss-36b-instruct":{"bs":{"gpqa":[0.7153,67.9,94,205],"chess":[0.13,20.6,74,138],"aime":[0.675,66.7,92,186]}},"codellama-70b-instruct":{"ar":{"text_style_control":[1119,1143,380,16.7]}},"deepseek-v4-pro":{"bs":{"gpqa":[0.9091,94.8,28,205],"simpleqa":[0.4699,58.6,29,72],"critpt":[0.1286,41.5,31,121],"forecastbench":[55.3,0,68,75],"chess":[0.2,31.8,57,138],"aime":[0.9667,96.6,22,186],"proofbench":[0.16,16.2,41,64],"swebench":[0.7764,85.3,6,32],"scicode":[0.5,78.3,30,112],"frontiercode":[0.1764,19.7,25,31],"alebench":[1006.08,41.2,35,102],"vending2":[3284.52,30.5,35,55],"weirdml":[0.489,34.7,49,128],"surface_evolver":[0.4,30.7,18,23],"webdev_arena":[1463.8,55.7,40,94]},"ar":{"text_style_control":[1463,9008,50,93.4],"webdev":[1581,4258,21,79.8],"agent":[0.0414,39047,14,67.1]}},"gemma-1-1-2b-it":{"ar":{"text_style_control":[1116,10854,381,16.2]}},"vicuna-7b":{"ar":{"text_style_control":[1115,6923,382,15.9]}},"smollm2-1-7b-instruct":{"ar":{"text_style_control":[1114,2199,383,15.7]}},"kimi-k2-6":{"bs":{"gpqa":[0.9078,94.6,30,205],"simpleqa":[0.349,39,44,72],"critpt":[0.08,25.8,42,121],"chess":[0.26,41.3,38,138],"frontiermath":[0.3897,75.7,11,71],"frontiermath_t4":[0.1458,37,16,56],"aime":[0.9611,96,24,186],"proofbench":[0.16,16.2,42,64],"swebench":[0.7665,81.7,11,32],"scicode":[0.5347,86.8,21,112],"cursorbench":[0.476,26.9,21,22],"alebench":[1092.67,45.7,32,102],"apex_agents":[0.332,47.3,29,53],"osworld2":[0.046,5.5,7,9],"vending2":[6204.57,57.4,13,55],"exploitbench":[0.184,9,6,9],"weirdml":[0.5586,45.3,37,128],"blueprint2":[0.039,9.7,19,24],"gbaeval":[0.0086,1.1,17,23],"webdev_arena":[1508.71,64,31,94]},"ar":{"text_style_control":[1460,37502,52,92.8],"webdev":[1509,9585,42,66],"vision_style_control":[1262,15347,37,89],"document_style_control":[1450,11291,32,45.1]}},"mistral-7b-instruct":{"ar":{"text_style_control":[1110,8977,385,14.8]}},"qwen3-6-27b":{"bs":{"gpqa":[0.8586,87.8,56,205],"critpt":[0.0086,2.8,73,121],"chess":[0.22,34.9,47,138],"aime":[0.9111,90.9,45,186],"scicode":[0.3727,47.3,80,112]}},"grok-4-20":{"bs":{"gpqa":[0.8933,92.6,38,205],"arc_agi_2":[0.6514,71.3,19,82],"arc_agi":[0.895,90.9,23,84],"simpleqa":[0.302,31.4,54,72],"forecastbench":[61.4,91,9,75],"chess":[0.24,38.1,43,138],"aime":[0.9222,92,39,186],"proofbench":[0.14,14.1,47,64],"terminalbench":[0.573,66.3,15,45],"alebench":[1150.28,48.6,31,102],"vending2":[4662.8467,43.2,26,55],"weirdml":[0.5226,39.8,44,128],"blueprint2":[0,0,21,24],"webdev_arena":[1373.56,38.8,64,94]},"ar":{"text_style_control":[1475,26599,30,95.9],"webdev":[1374,14571,87,40.1],"vision_style_control":[1256,25123,42,87.1],"search_style_control":[1197,53921,11,75.1],"document_style_control":[1439,20948,35,32.8]}},"yi-vision":{"ar":{"vision_style_control":[1003,1219,140,12.1]}},"c4ai-aya-vision-32b":{"ar":{"vision_style_control":[1000,847,142,11.3]}},"parasail-qwen3-235b-a22b-instruct-2507":{"bs":{"fiction120k":[0.444,30.4,28,40]}},"gemma-2b-it":{"ar":{"text_style_control":[1093,4780,387,11]}},"qwen1-5-4b-chat":{"ar":{"text_style_control":[1091,7597,388,10.5]}},"molmo-7b-d":{"ar":{"vision_style_control":[994,2815,143,9.5]}},"llama-3-2-vision-11b-instruct":{"ar":{"vision_style_control":[993,4817,144,9.2]}},"deepseek-r1-0528":{"bs":{"gpqa":[0.7633,74.6,85,205],"arc_agi_2":[0.0112,1.2,66,82],"arc_agi":[0.2121,19.7,69,84],"simplebench":[0.408,30,55,82],"aime":[0.6639,65.6,95,186],"math_l5":[0.9664,97.5,7,90],"aider":[71.4,81.8,13,56],"alebench":[804.12,30.7,50,102],"metr":[0.5378,42.6,22,35],"deepresearch":[0.351,0,25,25],"weirdml":[0.4163,23.7,71,128],"lech_writing":[8.19,84,12,45]},"ar":{"text_style_control":[1421,18091,117,84.1]}},"nvila-internal-15b-v1":{"ar":{"vision_style_control":[986,1077,145,7.1]}},"olmo-7b-instruct":{"ar":{"text_style_control":[1073,6328,389,6.6]}},"koala-13b":{"ar":{"text_style_control":[1071,6965,390,6]}},"alpaca-13b":{"ar":{"text_style_control":[1070,5745,391,5.8]}},"devstral-2":{"ar":{"webdev":[1194,1147,123,5.5]}},"gpt4all-13b-snoozy":{"ar":{"text_style_control":[1067,1743,392,5.3]}},"llava-onevision-qwen2-72b-ov":{"ar":{"vision_style_control":[979,1321,146,5]}},"deepseek-chat":{"bs":{"gpqa":[0.7121,67.5,95,205],"chess":[0.01,1.6,108,138],"aime":[0.4889,47.6,115,186],"aider":[70.2,80.2,14,56]}},"mpt-7b-chat":{"ar":{"text_style_control":[1063,3924,393,4.3]}},"gemini-2-5-deep":{"bs":{"frontiermath":[0.29,56.1,19,71],"frontiermath_t4":[0.104,26.4,20,56]}},"gemini-2-0-flash-lite-preview-02-05":{"bs":{"livebench":[53.24,26.8,23,48]},"ar":{"text_style_control":[1353,24955,199,69],"vision_style_control":[1136,3991,111,51.7]}},"api-gpt-4o-search":{"ar":{"search_style_control":[1081,3411,33,3.9]}},"chatglm3-6b":{"ar":{"text_style_control":[1056,4658,394,2.8]}},"internvl2-5-78b":{"bs":{"video_mme":[0.721,55,5,48]}},"o3-pro":{"bs":{"arc_agi_2":[0.0486,5.3,50,82],"arc_agi":[0.5933,59.5,45,84],"aider":[84.9,99.2,2,56],"weirdml":[0.5821,48.8,33,128],"fiction120k":[0.889,88.6,5,40],"lech_writing":[8.44,94.4,4,45]}},"llava-v1-6-34b":{"ar":{"vision_style_control":[965,4531,147,0.8]}},"cogvlm2-llama3-chat-19b":{"ar":{"vision_style_control":[964,1991,148,0.6]}},"rwkv-4-raven-14b":{"ar":{"text_style_control":[1042,4845,395,0]}},"chatglm2-6b":{"ar":{"text_style_control":[1024,2658,396,0]}},"oasst-pythia-12b":{"ar":{"text_style_control":[1023,6310,397,0]}},"chatglm-6b":{"ar":{"text_style_control":[995,4914,398,0]}},"fastchat-t5-3b":{"ar":{"text_style_control":[992,4203,399,0]}},"dolly-v2-12b":{"ar":{"text_style_control":[982,3412,400,0]}},"llama-13b":{"ar":{"text_style_control":[975,2391,401,0]}},"stablelm-tuned-alpha-7b":{"ar":{"text_style_control":[953,3287,402,0]}},"devstral-medium-2507":{"ar":{"webdev":[1081,831,128,0]}},"internvl2-4b":{"ar":{"vision_style_control":[958,3703,150,0]}},"phi-3-5-vision-instruct":{"ar":{"vision_style_control":[920,2592,151,0]}},"phi-3-vision-128k-instruct":{"ar":{"vision_style_control":[882,1401,152,0]}},"diffbot-small-xl":{"ar":{"search_style_control":[1062,6388,34,0]}},"minimax-m2-1":{"bs":{"terminalbench":[0.366,38.2,27,45],"alebench":[623.83,21.4,72,102],"webdev_arena":[1386.99,41.3,61,94]},"ar":{"text_style_control":[1384,16622,170,75.7],"webdev":[1387,7281,82,42.7]}},"glm-5-1":{"bs":{"gpqa":[0.899,93.4,35,205],"simpleqa":[0.34,37.5,47,72],"simplebench":[0.551,55.4,34,82],"critpt":[0.0457,14.8,49,121],"chess":[0.19,30.2,63,138],"frontiermath":[0.3345,64.9,15,71],"frontiermath_t4":[0.125,31.7,18,56],"aime":[0.9333,93.2,35,186],"proofbench":[0.2222,22.4,32,64],"swebench":[0.7417,72.8,16,32],"scicode":[0.4375,63.1,51,112],"alebench":[887.1,35,46,102],"vending2":[5634.406,52.1,18,55],"exploitbench":[0.181,8.4,7,9],"weirdml":[0.571,47.2,35,128],"gbaeval":[0,0,22,23],"webdev_arena":[1508.93,64.1,30,94]},"ar":{"text_style_control":[1466,48901,47,93.9],"webdev":[1508,10220,43,65.9]}},"chatgpt-4o-03-27":{"bs":{"aider":[45.3,48,32,56]}},"llava-video-72b-qwen2":{"bs":{"video_mme":[0.706,44.8,8,48]}},"linvt":{"bs":{"video_mme":[0.703,42.7,9,48]}},"gpt-5-1-codex-mini":{"bs":{"terminalbench":[0.616,72.1,12,45],"webdev_arena":[1247,15.1,85,94]},"ar":{"webdev":[1244,1133,116,15.1]}},"qwq-plus":{"bs":{"gpqa":[0.654,59.4,110,205]}},"deepseek-v2-5":{"bs":{"aider":[17.8,12.5,47,56]},"ar":{"text_style_control":[1323,6795,242,62.3]}},"grok-4-1-fast-non":{"bs":{"simplebench":[0.56,57,32,82]}},"gpt-5-2-codex":{"bs":{"terminalbench":[0.665,78.8,8,45],"alebench":[1299.9,56.4,21,102],"apex_agents":[0.425,64.4,21,53],"webdev_arena":[1338.28,32.2,73,94]},"ar":{"webdev":[1339,6402,101,33.3]}},"qwen-vl":{"bs":{"video_mme":[0.513,0,39,48],"spatialviz":[0.3203,0.7,7,8]},"ar":{"vision_style_control":[1185,3179,88,66.1]}},"composer-2-5":{"bs":{"cursorbench":[0.561,52.1,15,22],"frontiercode":[0.2564,37.7,21,31]}},"qwen3-235b-a22b":{"bs":{"gpqa":[0.7071,66.8,97,205],"simplebench":[0.31,12.7,62,82],"forecastbench":[59.7,65.7,34,75],"math_l5":[0.6886,43.8,35,90],"aider":[59.6,66.5,19,56],"weirdml":[0.3728,17.1,92,128],"lech_writing":[8.3,88.6,9,45]},"ar":{"text_style_control":[1375,25865,178,73.7]}},"yi-lightning":{"bs":{"aider":[12.9,6.2,50,56]},"ar":{"text_style_control":[1328,27332,233,63.3]}},"qwen1-5-110b-chat":{"bs":{"forecastbench":[57.7,35.8,55,75]},"ar":{"text_style_control":[1234,26195,314,42.3]}},"mistral-medium-2505":{"bs":{"gpqa":[0.5953,51.2,119,205],"hle":[0.0452,0,39,43],"frontiermath":[0.0035,0,66,71],"aime":[0.3222,30.6,122,186],"math_l5":[0.8163,68.5,28,90],"lech_writing":[7.73,65,21,45]},"ar":{"text_style_control":[1387,32662,168,76.5],"vision_style_control":[1155,10826,102,57.3]}},"o4-mini":{"bs":{"gpqa":[0.7778,76.6,81,205],"hle":[0.1428,22.1,21,43],"arc_agi_2":[0.0236,2.6,60,82],"arc_agi":[0.4183,41.2,54,84],"simpleqa":[0.196,14.2,60,72],"enigma":[0.0681,16.7,19,42],"forecastbench":[61.8,97,4,75],"chess":[0.2,31.8,58,138],"frontiermath":[0.1897,36.4,32,71],"frontiermath_t4":[0.0208,5.3,41,56],"aime":[0.7333,72.7,79,186],"metr":[0.6393,63,16,35],"vpct":[0.575,45.8,6,27],"geobench":[3651,64,17,28],"cad_eval":[0.62,81.3,3,15],"fiction120k":[0.625,54.1,17,40],"lech_writing":[7.5,55.4,29,45]},"ar":{"text_style_control":[1391,44639,160,77.3],"vision_style_control":[1200,41341,79,70.6]}},"gpt-5-chat":{"bs":{"weirdml":[0.3977,20.9,79,128]},"ar":{"text_style_control":[1427,30957,105,85.3],"vision_style_control":[1225,39846,64,77.9]}},"qwen3-32b":{"bs":{"gpqa":[0.6572,59.8,108,205],"critpt":[0.0029,0.9,81,121],"chess":[0.05,7.9,95,138],"aime":[0.6694,66.1,93,186],"scicode":[0.3542,42.8,88,112],"aider":[40,41.2,35,56]},"ar":{"text_style_control":[1347,3926,209,67.5]}},"qwen3-5-35b-a3b":{"bs":{"gpqa":[0.8346,84.5,64,205],"critpt":[0.0057,1.8,78,121],"chess":[0.1,15.9,83,138],"aime":[0.7,69.3,89,186],"scicode":[0.2928,27.8,96,112]},"ar":{"text_style_control":[1395,29043,156,78.2],"webdev":[1250,1535,115,16.3]}},"deepseek-r1":{"bs":{"gpqa":[0.6922,64.7,100,205],"arc_agi_2":[0.013,1.4,62,82],"arc_agi":[0.158,14.1,72,84],"simplebench":[0.309,12.5,63,82],"critpt":[0.011,3.6,71,121],"forecastbench":[60,70.1,31,75],"aime":[0.5333,52.2,111,186],"math_l5":[0.9305,90.6,15,90],"scicode":[0.3571,43.5,86,112],"aider":[56.9,63,23,56],"algotune":[1.7,53,7,18],"livebench":[71.57,75.1,7,48],"metr":[0.5193,38.9,23,35],"balrog":[0.349,36.3,7,32],"weirdml":[0.3649,15.9,95,128],"fiction120k":[0.333,15.9,36,40],"lech_writing":[8.3,88.6,10,45]},"ar":{"text_style_control":[1398,18524,151,78.9]}},"gemini-2-0-flash-lite":{"bs":{"livebench":[54.29,29.6,22,48]}},"kimi-k2":{"bs":{"weirdml":[0.3936,20.3,83,128]},"ar":{"text_style_control":[1418,27029,121,83.3]}},"aria":{"bs":{"video_mme":[0.676,24.4,11,48]}},"grok-4-heavy-web-app":{"bs":{"frontiermath_t4":[0.0208,5.3,46,56]}},"vilamp-llava-qwen":{"bs":{"video_mme":[0.675,23.7,12,48]}},"oryx-1-5-32b":{"bs":{"video_mme":[0.673,22.3,13,48]}},"chatgpt-4o-01-29":{"bs":{"aider":[27.1,24.5,41,56],"fiction120k":[0.656,58.1,13,40]}},"dracarys2-72b-instruct":{"bs":{"livebench":[52.64,25.2,24,48]}},"learnlm-1-5-pro":{"bs":{"livebench":[52.19,24,25,48]}},"claude-opus-4-1":{"bs":{"gpqa":[0.7727,75.9,82,205],"hle":[0.1152,15.4,24,43],"simplebench":[0.6,64,26,82],"enigma":[0.0718,17.7,18,42],"forecastbench":[62,100,2,75],"chess":[0.07,11.1,88,138],"frontiermath":[0.0724,13.4,44,71],"frontiermath_t4":[0.0417,10.6,30,56],"aime":[0.6889,68.1,90,186],"swebench":[0.7335,69.8,20,32],"terminalbench":[0.38,40.1,26,45],"alebench":[674.77,24,66,102],"algotune":[1.34,3.2,16,18],"metr":[0.6681,68.8,12,35],"gdpval":[0.436,80.5,3,11],"deepresearch":[0.483,66,9,25],"cybench":[0.42,33,5,21],"weirdml":[0.4586,30.1,57,128],"vpct":[0.35,5.8,23,27],"lech_writing":[8.47,95.6,3,45],"webdev_arena":[1388.83,41.6,60,94]},"ar":{"text_style_control":[1450,48811,70,90.4],"webdev":[1389,6769,81,43]}},"gemini-robotics-er-1-5":{"bs":{"vpct":[0.408,16.1,12,27]}},"llava-onevision-72b":{"bs":{"video_mme":[0.663,15.6,14,48]}},"videollama3-7b":{"bs":{"video_mme":[0.662,14.9,15,48]}},"llava-video-7b-qwen2":{"bs":{"video_mme":[0.659,12.8,16,48],"mindcube":[0.4196,null,4,5]}},"llava-video-7b-qwen2-tpo":{"bs":{"video_mme":[0.656,10.8,17,48]}},"videochat-flash-qwen2-7b-res448":{"bs":{"video_mme":[0.653,8.8,18,48]}},"ml-elephant":{"bs":{"cad_eval":[0.2,6,13,15]}},"pixtral-12b-2409":{"bs":{"geobench":[2131,0,28,28]},"ar":{"vision_style_control":[1025,7511,135,18.8]}},"mistral-small-2603":{"bs":{"alebench":[497.62,14.9,82,102]}},"amazon-nova-micro-v1-0":{"bs":{"livebench":[29.59,0,43,48]},"ar":{"text_style_control":[1241,19364,310,43.8]}},"gpt-5-1-codex-max":{"bs":{"proofbench":[0.09,9.1,51,64],"terminalbench":[0.604,70.5,13,45],"alebench":[1208.83,51.7,24,102],"metr":[0.7083,76.9,9,35]}},"bytevideollm-14b":{"bs":{"video_mme":[0.646,4,20,48]}},"gemini-2-5-flash-preview-09":{"bs":{"terminalbench":[0.171,11.7,42,45],"tac":[0.518,98.3,2,14],"weirdml":[0.4191,24.1,70,128],"vpct":[0.462,25.7,10,27]},"ar":{"text_style_control":[1404,32364,143,80.1],"vision_style_control":[1229,4723,60,79.2]}},"gemini-3-1-pro-preview-customtools":{"bs":{"swebench":[0.7562,78,12,32],"vending2":[3774.254,35,32,55]}},"qwen3-coder-plus":{"bs":{"alebench":[456.5,12.7,84,102]}},"o1":{"bs":{"gpqa":[0.7677,75.2,84,205],"hle":[0.0796,6.8,32,43],"arc_agi":[0.307,29.6,64,84],"simpleqa":[0.411,49,36,72],"simplebench":[0.417,31.6,52,82],"enigma":[0.0565,13.6,22,42],"chess":[0.15,23.8,68,138],"frontiermath":[0.0931,17.5,40,71],"aime":[0.7333,72.7,80,186],"math_l5":[0.9471,93.8,14,90],"aider":[61.7,69.2,16,56],"livebench":[75.67,85.9,5,48],"apex_agents":[0.055,0,52,53],"metr":[0.5105,37.1,24,35],"cybench":[0.1,0,15,21],"weirdml":[0.4756,32.7,53,128],"vpct":[0.37,9.3,22,27],"geobench":[3925,80.1,8,28],"cad_eval":[0.56,70.6,4,15],"spatialviz":[0.4136,77.9,2,8],"fiction120k":[0.531,41.8,23,40],"lech_writing":[7.02,35.5,36,45]},"ar":{"text_style_control":[1402,27807,145,79.8],"vision_style_control":[1193,3694,82,68.5]}},"nvila-8b":{"bs":{"video_mme":[0.642,1.3,21,48]}},"livecc-7b-instruct":{"bs":{"video_mme":[0.641,0.6,22,48]}},"minicpm-o-2-6":{"bs":{"video_mme":[0.639,0,23,48]}},"videollama2-7b":{"bs":{"video_mme":[0.624,0,25,48]}},"internvl2-40b":{"bs":{"video_mme":[0.612,0,26,48]}},"gpt-4-1106-vision":{"bs":{"video_mme":[0.599,0,29,48]}},"mplug-owl3-7b":{"bs":{"video_mme":[0.593,0,30,48],"mindcube":[0.4485,null,2,5]}},"timemarker":{"bs":{"video_mme":[0.573,0,31,48]}},"vita-1-5":{"bs":{"video_mme":[0.561,0,32,48]}},"kangaroo":{"bs":{"video_mme":[0.56,0,33,48]}},"vita":{"bs":{"video_mme":[0.558,0,34,48]}},"video-xl-7b":{"bs":{"video_mme":[0.555,0,35,48]}},"video-ccam-7b-v1-2":{"bs":{"video_mme":[0.532,0,36,48]}},"long-llava-qwen2-7b":{"bs":{"video_mme":[0.529,0,37,48]}},"longva-7b":{"bs":{"video_mme":[0.526,0,38,48],"mindcube":[0.2946,null,5,5]}},"internvl-chat-v1-5":{"bs":{"video_mme":[0.507,0,40,48]}},"slime-llama3-8b":{"bs":{"video_mme":[0.453,0,41,48]}},"chat-uni-vi-7b-v1-5-100k-sg-wv":{"bs":{"video_mme":[0.432,0,42,48]}},"qwen-vl-chat":{"bs":{"video_mme":[0.411,0,43,48]}},"chat-univi-7b-v1-5":{"bs":{"video_mme":[0.406,0,44,48]}},"sharegpt4video-8b":{"bs":{"video_mme":[0.399,0,45,48]}},"video-llava-7b":{"bs":{"video_mme":[0.399,0,46,48]}},"video-chat2-mistral":{"bs":{"video_mme":[0.395,0,47,48]}},"st-llm":{"bs":{"video_mme":[0.379,0,48,48]}},"gemini-2-5-flash-lite-preview-09":{"bs":{"vpct":[0.3,0,27,27]}},"meta-llama-3-70b":{"bs":{"forecastbench":[57.1,26.9,61,75]}},"gemini-2-0-flash-lite-001":{"bs":{"forecastbench":[57.1,26.9,62,75]}},"gpt-5-1":{"bs":{"gpqa":[0.8763,90.3,46,205],"hle":[0.2368,44.9,14,43],"arc_agi_2":[0.1764,19.3,37,82],"arc_agi":[0.7283,73.5,37,84],"simpleqa":[0.48,60.2,26,72],"simplebench":[0.532,52,36,82],"enigma":[0.1123,28.6,12,42],"critpt":[0.0486,15.7,48,121],"forecastbench":[58.1,41.8,52,75],"chess":[0.32,50.8,30,138],"frontiermath":[0.3103,60.1,18,71],"frontiermath_t4":[0.125,31.7,19,56],"aime":[0.8861,88.3,52,186],"swebench":[0.6798,50.5,25,32],"terminalbench":[0.476,53.1,19,45],"scicode":[0.4329,62,53,112],"gso":[0.1373,28.1,12,28],"alebench":[1192.15,50.8,25,102],"livebench":[78.79,94.2,2,48],"apex_agents":[0.315,44.2,31,53],"deepresearch":[0.428,38.5,18,25],"vending2":[1473.432,13.8,38,55],"weirdml":[0.6077,52.7,28,128],"vpct":[0.587,48,5,27],"webdev_arena":[1391.01,42.1,58,94]},"ar":{"text_style_control":[1455,40284,64,91.6],"webdev":[1392,4751,80,43.6],"vision_style_control":[1250,9336,45,85.4],"document_style_control":[1416,8244,43,4.9]}},"deepseek-v3-1-terminus":{"bs":{"critpt":[0.0171,5.5,62,121],"scicode":[0.4063,55.5,65,112],"alebench":[745.17,27.7,60,102]},"ar":{"text_style_control":[1417,3369,122,83.2]}},"gpt-5-1-codex":{"bs":{"terminalbench":[0.578,66.9,14,45],"alebench":[1244.92,53.5,23,102],"apex_agents":[0.349,50.5,27,53],"webdev_arena":[1336.28,31.8,75,94]},"ar":{"webdev":[1336,4861,102,32.8]}},"sonar":{"bs":{"livebench":[46.88,10,30,48]}},"glm-5":{"bs":{"gpqa":[0.8782,90.5,45,205],"arc_agi_2":[0.0486,5.3,51,82],"arc_agi":[0.4467,44.2,53,84],"simplebench":[0.532,52,37,82],"forecastbench":[61,85.1,16,75],"chess":[0.1,15.9,84,138],"frontiermath":[0.1643,31.5,34,71],"frontiermath_t4":[0.021,5.3,37,56],"aime":[0.8,79.5,74,186],"swebench":[0.7208,65.2,22,32],"terminalbench":[0.524,59.6,17,45],"alebench":[765.62,28.7,57,102],"apex_agents":[0.308,43,33,53],"vending2":[4432.122,41,27,55],"weirdml":[0.4817,33.6,50,128],"webdev_arena":[1435.46,50.4,48,94]},"ar":{"text_style_control":[1458,27605,56,92.2],"webdev":[1436,7056,65,52]}},"mimo-v2-5-pro":{"bs":{"critpt":[0.04,12.9,50,121],"proofbench":[0.22,22.2,33,64],"scicode":[0.5023,78.9,28,112],"alebench":[899.8,35.7,45,102],"webdev_arena":[1475.65,57.9,38,94]},"ar":{"text_style_control":[1467,60919,44,94.3],"webdev":[1475,15843,50,59.5],"agent":[-0.0542,38911,37,30.4]}},"qwen1-5-72b-chat":{"bs":{"gpqa":[0.2882,8.6,186,205]},"ar":{"text_style_control":[1233,39302,316,42.2]}},"qwen3-30b-a3b":{"bs":{"gpqa":[0.6168,54.2,116,205],"chess":[0.04,6.4,99,138],"aime":[0.6278,61.9,100,186],"weirdml":[0.2975,5.7,106,128],"lech_writing":[7.53,56.7,28,45]},"ar":{"text_style_control":[1327,26089,237,63]}},"deepseek-r1-distill-llama-70b":{"bs":{"gpqa":[0.5574,46,126,205],"aime":[0.5139,50.2,113,186],"math_l5":[0.899,84.5,18,90],"livebench":[54.5,30.1,20,48]}},"dracarys2-llama-3-1-70b-instruct":{"bs":{"livebench":[46.21,8.2,32,48]}},"gemini-2-0-pro-exp-02-05":{"bs":{"gpqa":[0.6566,59.7,109,205],"enigma":[0.0069,0.2,39,42],"math_l5":[0.8346,72,25,90],"aider":[35.6,35.5,37,56],"livebench":[65.13,58.1,12,48],"fiction120k":[0.375,21.4,31,40]}},"qwen1-5-32b-chat":{"bs":{"gpqa":[0.3074,11.3,182,205]},"ar":{"text_style_control":[1204,21741,332,35.6]}},"c4ai-command-a-03":{"bs":{"aider":[12,5,51,56]}},"deepseek-r1-distill-qwen-14b":{"bs":{"gpqa":[0.447,30.6,153,205],"chess":[0.01,1.6,109,138],"aime":[0.5056,49.4,114,186],"math_l5":[0.8712,79.1,22,90]}},"gpt-5-4-mini":{"bs":{"gpqa":[0.8687,89.2,51,205],"arc_agi_2":[0.189,20.7,35,82],"arc_agi":[0.6367,64,42,84],"simpleqa":[0.294,30.1,55,72],"critpt":[0.1,32.3,37,121],"forecastbench":[57,25.4,64,75],"chess":[0.24,38.1,44,138],"frontiermath":[0.2828,54.7,20,71],"frontiermath_t4":[0.0208,5.3,47,56],"aime":[0.8889,88.6,49,186],"proofbench":[0.21,21.2,35,64],"scicode":[0.4988,78.1,32,112],"frontiercode":[0.2704,40.8,19,31],"alebench":[1188.58,50.6,27,102],"apex_agents":[0.375,55.2,25,53],"deepresearch":[0.363,6,23,25],"weirdml":[0.603,52,32,128],"webdev_arena":[1397.08,43.2,57,94]},"ar":{"text_style_control":[1448,59387,74,90],"webdev":[1397,11279,78,44.6],"vision_style_control":[1252,24041,43,85.8]}},"codestral-2501":{"bs":{"aider":[11.1,3.9,52,56]}},"phi-3-small-8k-instruct":{"bs":{"livebench":[24.03,0,46,48]},"ar":{"text_style_control":[1171,17766,352,28.3]}},"qwen-3-7-plus":{"bs":{"frontiercode":[0.102,3.1,28,31]}},"openhands-lm-32b-v0-1":{"bs":{"aider":[10.2,2.7,53,56]}},"qwen3-30b-a3b-thinking-2507":{"bs":{"gpqa":[0.7008,65.9,98,205],"critpt":[0.0029,0.9,82,121],"chess":[0.08,12.7,86,138],"aime":[0.7028,69.6,88,186],"scicode":[0.3333,37.7,92,112]}},"swe-1-6":{"bs":{"frontiercode":[0.094,1.3,30,31]}},"qwen2-5-coder-32b-instruct":{"bs":{"aider":[16.4,10.7,48,56],"livebench":[46.23,8.3,31,48]},"ar":{"text_style_control":[1270,5432,297,50.5]}},"eurus-2-7b-prime":{"bs":{"gpqa":[0.339,15.6,176,205]}},"codestral-2508":{"bs":{"alebench":[137.78,0,102,102]}},"c4ai-command-r-08":{"bs":{"livebench":[27.48,0,45,48]}},"olmo-2-1124-13b-instruct":{"bs":{"livebench":[22.12,0,48,48]}},"minicpm-v-2-6":{"bs":{"video_mme":[0.609,0,27,48]},"ar":{"vision_style_control":[963,1987,149,0.4]}},"pixtral-large-2411":{"bs":{"enigma":[0.0084,0.6,36,42]},"ar":{"vision_style_control":[1095,5423,123,39.5]}},"qwen3-4b-instruct-2507":{"bs":{"gpqa":[0.4583,32.2,151,205],"chess":[0.04,6.4,100,138],"aime":[0.5222,51.1,112,186]}},"qwen3-6-plus":{"bs":{"gpqa":[0.8838,91.3,41,205],"simpleqa":[0.4414,53.9,34,72],"critpt":[0.0286,9.2,58,121],"chess":[0.17,27,66,138],"frontiermath":[0.2621,50.7,23,71],"frontiermath_t4":[0.0833,21.1,21,56],"aime":[0.9333,93.2,36,186],"swebench":[0.5785,14,29,32],"scicode":[0.4074,55.7,64,112],"alebench":[670.15,23.8,67,102],"vending2":[5114.872,47.3,23,55],"webdev_arena":[1459.74,54.9,42,94]},"ar":{"text_style_control":[1443,45319,79,89],"webdev":[1461,17562,55,56.7]}},"grok-3-mini":{"bs":{"gpqa":[0.7626,74.5,86,205],"arc_agi_2":[0.0042,0.5,71,82],"arc_agi":[0.165,14.8,71,84],"frontiermath":[0.0586,10.7,47,71],"aime":[0.7778,77.2,76,186],"math_l5":[0.9094,86.5,17,90],"aider":[49.3,53.2,30,56],"weirdml":[0.4258,25.1,69,128],"fiction120k":[0.656,58.1,14,40],"lech_writing":[7.35,49.2,31,45]},"ar":{"text_style_control":[1364,15536,190,71.2]}},"gpt-5-codex":{"bs":{"terminalbench":[0.443,48.6,22,45],"apex_agents":[0.348,50.3,28,53],"weirdml":[0.5453,43.3,38,128]}},"qwen3-4b":{"bs":{"gpqa":[0.5234,41.2,130,205],"chess":[0.01,1.6,110,138]}},"qwen3-5-122b-a10b":{"bs":{"critpt":[0.0086,2.8,74,121],"scicode":[0.3565,43.3,87,112]},"ar":{"text_style_control":[1417,28359,124,83.1],"webdev":[1358,7831,94,37],"vision_style_control":[1227,12465,62,78.4]}},"qwen3-8-27b":{"bs":{"critpt":[0.0543,17.5,46,121],"proofbench":[0.16,16.2,43,64],"scicode":[0.4468,65.3,49,112],"surface_evolver":[0.45,37,16,23],"webdev_arena":[1594.78,80.1,11,94]},"ar":{"text_style_control":[1437,10697,90,87.6],"webdev":[1593,4913,18,82.3],"vision_style_control":[1244,4577,49,83.6]}},"qwen3-235b-a22b-thinking-2507":{"bs":{"gpqa":[0.8005,79.7,75,205],"simpleqa":[0.4044,47.9,39,72],"critpt":[0,0,91,121],"chess":[0.12,19.1,79,138],"frontiermath":[0.0848,15.8,41,71],"frontiermath_t4":[0,0,48,56],"aime":[0.8667,86.3,56,186],"scicode":[0.4236,59.7,59,112],"vending2":[-11.34,0.1,52,55],"weirdml":[0.4104,22.8,73,128],"fiction120k":[0.688,62.3,11,40],"lech_writing":[8.24,86.1,11,45]},"ar":{"text_style_control":[1400,8796,149,79.3]}},"qwen3-7-plus":{"bs":{"gpqa":[0.8788,90.6,44,205],"critpt":[0.0914,29.5,39,121],"chess":[0.24,38.1,45,138],"aime":[0.9333,93.2,37,186],"scicode":[0.4549,67.3,45,112],"frontiercode":[0.102,3.1,29,31],"osworld2":[0.028,0,9,9]},"ar":{"text_style_control":[1456,39334,62,91.7],"agent":[-0.0538,20606,35,30.5],"vision_style_control":[1263,10656,36,89.1],"document_style_control":[1453,4591,30,48.3]}},"laguna-xs-2":{"bs":{"proofbench":[0,0,62,64],"webdev_arena":[1301.97,25.4,79,94]},"ar":{"webdev":[1302,3934,107,26.3]}},"claude-sonnet-4-5":{"bs":{"gpqa":[0.8232,82.9,71,205],"hle":[0.1372,20.7,22,43],"arc_agi_2":[0.1361,14.9,39,82],"arc_agi":[0.6367,64,43,84],"simpleqa":[0.307,32.2,53,72],"simplebench":[0.543,53.9,35,82],"enigma":[0.06,14.5,21,42],"critpt":[0.0114,3.7,67,121],"forecastbench":[61.9,98.5,3,75],"chess":[0.12,19.1,80,138],"frontiermath":[0.1522,29.1,35,71],"frontiermath_t4":[0.0417,10.6,31,56],"aime":[0.7778,77.2,77,186],"math_l5":[0.9773,99.6,5,90],"proofbench":[0.19,19.2,37,64],"swebench":[0.7128,62.4,23,32],"terminalbench":[0.465,51.6,20,45],"scicode":[0.4468,65.3,50,112],"gso":[0.1471,30.3,11,28],"alebench":[796.15,30.3,53,102],"algotune":[1.52,28.1,9,18],"metr":[0.6738,70,11,35],"osworld":[62.9,82.2,4,9],"gdpval":[0.425,76.5,4,11],"deepresearch":[0.526,87.5,5,25],"vending2":[3838.74,35.6,31,55],"cybench":[0.6,57.8,3,21],"weirdml":[0.4771,32.9,52,128],"rli":[0.0208,8.6,8,11],"vpct":[0.398,14.3,17,27],"webdev_arena":[1391,42.1,59,94]},"ar":{"text_style_control":[1456,80980,58,91.8],"webdev":[1393,12764,79,43.7],"document_style_control":[1449,31455,33,44.2]}},"mimo-v2-5":{"bs":{"critpt":[0.0371,12,51,121],"proofbench":[0.16,16.2,44,64],"scicode":[0.4306,61.4,55,112],"alebench":[513.95,15.7,81,102],"webdev_arena":[1437.8,50.8,46,94]},"ar":{"text_style_control":[1434,44466,96,86.8],"webdev":[1437,14117,63,52.2],"vision_style_control":[1233,24771,58,80.4]}},"fireworks-deepseek-v3p2":{"bs":{"frontiermath":[0.221,42.6,27,71],"frontiermath_t4":[0.021,5.3,38,56],"proofbench":[0.08,8.1,54,64]}},"claude-3-7-sonnet":{"bs":{"gpqa":[0.785,77.6,78,205],"hle":[0.0804,7,31,43],"arc_agi_2":[0.009,1,67,82],"arc_agi":[0.286,27.4,65,84],"simplebench":[0.464,39.9,47,82],"enigma":[0.0423,9.7,25,42],"forecastbench":[61.8,97,5,75],"frontiermath":[0.0414,7.3,52,71],"aime":[0.5778,56.7,105,186],"math_l5":[0.9116,86.9,16,90],"swebench":[0.6095,25.2,28,32],"gso":[0.038,5.6,23,28],"aider":[64.9,73.4,15,56],"livebench":[76.1,87.1,3,48],"metr":[0.5997,55.1,18,35],"osworld":[35.8,24.7,6,9],"tac":[0.402,61.2,4,14],"deepresearch":[0.436,42.5,17,25],"cybench":[0.2,2.7,11,21],"vpct":[0.39,12.9,18,27],"geobench":[3844,75.3,12,28],"cad_eval":[0.54,67,5,15],"spatialviz":[0.339,16.1,5,8],"fiction120k":[0.531,41.8,24,40],"lech_writing":[8.11,80.7,15,45]},"ar":{"text_style_control":[1388,38081,165,76.7],"vision_style_control":[1193,1439,83,68.4]}},"qwen3-max":{"bs":{"gpqa":[0.726,69.4,93,205],"simpleqa":[0.4875,61.4,24,72],"chess":[0.04,6.4,101,138],"aime":[0.7333,72.7,81,186],"math_l5":[0.9713,98.4,6,90],"alebench":[370.45,8.3,88,102],"vending2":[71.565,0.9,49,55]},"ar":{"text_style_control":[1435,27194,94,87]}},"qwen-plus":{"bs":{"gpqa":[0.4811,35.4,139,205],"frontiermath":[0.0172,2.6,58,71],"aime":[0.1778,15.8,132,186],"math_l5":[0.6528,36.9,37,90]},"ar":{"text_style_control":[1346,5819,213,67.3]}},"reka-flash-3":{"bs":{"balrog":[0.292,20.5,14,32]}},"llama-2-13b-chat":{"bs":{"chess":[0,0,116,138]},"ar":{"text_style_control":[1141,19174,369,21.7]}},"gemini-2-0-flash-02-05":{"bs":{"enigma":[0.0063,0,40,42]}},"meta-llama-3-8b":{"bs":{"forecastbench":[52.9,0,73,75]}},"qwen3-5-2b":{"bs":{"chess":[0,0,117,138]}},"magistral-medium-2506":{"bs":{"arc_agi_2":[0,0,73,82],"arc_agi":[0.0612,4,76,84]},"ar":{"text_style_control":[1305,11468,269,58.1]}},"nova-2-0-pro":{"bs":{"critpt":[0,0,92,121],"scicode":[0.4271,60.5,58,112]}},"grok-4-3":{"bs":{"gpqa":[0.8883,91.9,39,205],"simpleqa":[0.332,36.2,50,72],"critpt":[0.08,25.8,43,121],"forecastbench":[60.4,76.1,24,75],"chess":[0.25,39.7,41,138],"aime":[0.9333,93.2,38,186],"proofbench":[0.11,11.1,50,64],"scicode":[0.4734,71.8,39,112],"alebench":[944.17,38,39,102],"vending2":[35.2617,0.5,50,55],"weirdml":[0.4989,36.2,47,128],"blueprint2":[0,0,22,24],"webdev_arena":[1356.73,35.7,70,94]},"ar":{"text_style_control":[1443,66801,81,88.8],"webdev":[1357,14192,96,36.9],"vision_style_control":[1243,22688,51,83.3],"search_style_control":[1193,91483,17,72.6]}},"qwen3-14b":{"bs":{"gpqa":[0.6376,57.1,114,205],"critpt":[0,0,93,121],"chess":[0.04,6.4,102,138],"aime":[0.6639,65.6,96,186],"scicode":[0.316,33.4,95,112]}},"kimi-k2-5":{"bs":{"hle":[0.2437,46.5,13,43],"arc_agi_2":[0.1181,12.9,40,82],"arc_agi":[0.6533,65.7,41,84],"simpleqa":[0.343,38,45,72],"simplebench":[0.468,40.7,46,82],"enigma":[0.0338,7.4,27,42],"critpt":[0.0314,10.1,55,121],"swebench":[0.7376,71.3,18,32],"terminalbench":[0.432,47.1,23,45],"scicode":[0.4896,75.8,34,112],"cursorbench":[0.319,0,22,22],"alebench":[821.65,31.6,49,102],"apex_agents":[0.292,40,35,53],"osworld":[63.3,83,3,9],"vending2":[1198.458,11.3,39,55],"weirdml":[0.456,29.7,60,128],"fiction120k":[0.781,74.4,7,40],"webdev_arena":[1435.92,50.4,47,94]},"ar":{"text_style_control":[1450,70513,69,90.5],"webdev":[1436,19042,64,52.1],"vision_style_control":[1250,26646,46,85.3],"document_style_control":[1436,21569,37,28.7]}},"mistral-small-3-2-2506":{"bs":{"gpqa":[0.4905,36.7,136,205],"chess":[0.01,1.6,111,138],"aime":[0.3028,28.6,124,186]}},"computer-use":{"bs":{"osworld":[31.3,15.1,7,9]}},"cogito-671b-v2-1":{"bs":{"critpt":[0,0,94,121],"scicode":[0.4097,56.3,62,112]}},"llama-2-7b-chat":{"bs":{"chess":[0,0,118,138]},"ar":{"text_style_control":[1108,14148,386,14.3]}},"magistral-medium-2509":{"bs":{"critpt":[0.0029,0.9,83,121],"scicode":[0.3924,52.1,73,112]}},"deepseek-v3-2-exp":{"bs":{"critpt":[0.0286,9.2,59,121],"scicode":[0.3889,51.2,75,112],"aider":[74.2,85.4,8,56],"tac":[0.524,100,1,14],"vending2":[1034.004,9.7,41,55],"weirdml":[0.3948,20.4,81,128],"webdev_arena":[1367,37.6,66,94]},"ar":{"text_style_control":[1425,8905,110,85],"webdev":[1272,3865,111,20.4]}},"mistral-large-2407":{"bs":{"gpqa":[0.4902,36.6,137,205],"simplebench":[0.225,0,75,82],"forecastbench":[57.1,26.9,63,75],"aime":[0.0847,6.2,139,186],"math_l5":[0.4482,0,53,90],"lech_writing":[6.9,30.6,37,45]},"ar":{"text_style_control":[1314,45459,256,60.2]}},"wizardlm-2-8x22b":{"bs":{"gpqa":[0.4343,28.9,155,205],"math_l5":[0.2574,0,64,90]}},"command-a-plus-05":{"bs":{"critpt":[0.0029,0.9,84,121],"scicode":[0.3785,48.7,79,112]}},"claude-opus-4":{"bs":{"gpqa":[0.7626,74.5,87,205],"hle":[0.1072,13.5,26,43],"arc_agi_2":[0.0861,9.4,43,82],"arc_agi":[0.3567,34.8,58,84],"simplebench":[0.588,61.9,28,82],"enigma":[0.0557,13.3,23,42],"critpt":[0.003,1,80,121],"forecastbench":[61.1,86.6,15,75],"frontiermath":[0.0448,8,50,71],"frontiermath_t4":[0.0417,10.6,32,56],"aime":[0.6444,63.6,98,186],"math_l5":[0.8505,75.1,23,90],"swebench":[0.7066,60.1,24,32],"gso":[0.069,12.6,15,28],"aider":[72,82.5,11,56],"algotune":[1.33,1.8,17,18],"metr":[0.6393,63,15,35],"deepresearch":[0.468,58.5,12,25],"cybench":[0.38,27.5,7,21],"weirdml":[0.4372,26.9,62,128],"vpct":[0.38,11.1,19,27],"geobench":[2915,20.9,23,28],"fiction120k":[0.375,21.4,32,40],"lech_writing":[8.36,91.1,7,45]},"ar":{"text_style_control":[1426,35735,107,85.1],"vision_style_control":[1207,1292,74,72.6]}},"yi-1-5-34b-chat":{"bs":{"gpqa":[0.3198,13,181,205],"math_l5":[0.2548,0,65,90]},"ar":{"text_style_control":[1213,24146,328,37.6]}},"deepseek-v3-1":{"bs":{"simplebench":[0.4,28.6,56,82],"forecastbench":[58,40.3,53,75],"weirdml":[0.3836,18.7,88,128],"fiction120k":[0.531,41.8,25,40]},"ar":{"text_style_control":[1417,14607,123,83.2]}},"dbrx-instruct":{"bs":{"gpqa":[0.3289,14.2,180,205],"math_l5":[0.1165,0,80,90]},"ar":{"text_style_control":[1195,32191,336,33.7]}},"ministral-8b-2410":{"bs":{"gpqa":[0.2715,6.3,191,205],"math_l5":[0.1494,0,76,90]},"ar":{"text_style_control":[1237,4781,312,43.1]}},"gemini-1-5-pro-001":{"bs":{"gpqa":[0.4586,32.3,150,205],"forecastbench":[58.5,47.8,49,75],"aime":[0.0681,4.5,148,186],"math_l5":[0.4075,0,57,90],"video_mme":[0.75,74.7,2,48]},"ar":{"text_style_control":[1324,79138,241,62.4],"vision_style_control":[1120,16734,117,46.8]}},"glm-4-5-air":{"bs":{"hle":[0.0812,7.2,29,43],"forecastbench":[59.2,58.2,41,75],"gso":[0.0294,3.7,25,28]},"ar":{"text_style_control":[1373,30367,182,73.4]}},"tiny-recursion-model":{"bs":{"arc_agi_2":[0.0625,6.8,45,82],"arc_agi":[0.4,39.3,56,84]}},"gemini":{"bs":{"simplebench":[0.311,12.8,61,82],"aider":[38.2,38.9,36,56],"livebench":[64.09,55.4,13,48]}},"llama-3-2-3b-instruct":{"bs":{"balrog":[0.101,0,29,32]},"ar":{"text_style_control":[1167,7936,355,27.3]}},"deepseek-v3":{"bs":{"gpqa":[0.6761,62.5,102,205],"simplebench":[0.272,5.9,66,82],"critpt":[0,0,95,121],"forecastbench":[59.1,56.7,42,75],"frontiermath":[0.0172,2.6,59,71],"aime":[0.3778,36.3,120,186],"math_l5":[0.7555,56.7,30,90],"scicode":[0.3576,43.6,84,112],"aider":[55.1,60.7,24,56],"livebench":[66.86,62.7,11,48],"metr":[0.4958,34.1,25,35],"weirdml":[0.3608,15.3,97,128],"lech_writing":[7.7,63.7,23,45]},"ar":{"text_style_control":[1396,44787,153,78.4]}},"deepseek-v3-2-speciale":{"bs":{"simplebench":[0.526,50.9,39,82],"weirdml":[0.4673,31.4,54,128]}},"mistral-small-2506":{"bs":{"critpt":[0,0,96,121],"scicode":[0.2639,20.7,101,112]},"ar":{"text_style_control":[1357,17391,196,69.7],"vision_style_control":[1140,10869,110,52.7]}},"deepseek-v4-flash":{"bs":{"simplebench":[0.463,39.8,48,82],"critpt":[0.0714,23.1,44,121],"scicode":[0.4491,65.9,48,112],"alebench":[678.2,24.2,65,102],"weirdml":[0.4563,29.8,59,128],"webdev_arena":[1431.07,49.5,51,94]},"ar":{"text_style_control":[1438,48597,87,87.8],"webdev":[1580,4723,22,79.8],"agent":[0.0217,63940,21,59.5]}},"gpt-3-5-turbo-instruct":{"bs":{"metr":[0.2146,0,33,35]}},"davinci-002":{"bs":{"metr":[0.1619,0,34,35]}},"gpt2-xl":{"bs":{"metr":[0.101,0,35,35]}},"mistral-nemo-instruct-2407":{"bs":{"balrog":[0.176,0,21,32]}},"llama-3-2-11b-vision-instruct":{"bs":{"balrog":[0.168,0,23,32]}},"gemini-robotics-er-1-6":{"bs":{"blueprint2":[0,0,23,24]}},"gpt-oss-120b":{"bs":{"gpqa":[0.7576,73.8,88,205],"simplebench":[0.221,0,76,82],"critpt":[0.0114,3.7,68,121],"chess":[0.2,31.8,59,138],"aime":[0.8889,88.6,50,186],"terminalbench":[0.187,13.8,41,45],"scicode":[0.3889,51.2,76,112],"aider":[41.8,43.5,34,56],"alebench":[575.62,18.9,78,102],"algotune":[1.41,12.9,14,18],"apex_agents":[0.145,13.2,47,53],"metr":[0.5663,48.3,20,35],"vending2":[-21.532,0,53,55],"weirdml":[0.4817,33.6,51,128],"surface_evolver":[0.25,11.8,21,23],"lech_writing":[7.71,64.1,22,45]},"ar":{"text_style_control":[1352,29955,201,68.7]}},"gemini-2-0-flash-thinking-exp-01-21":{"bs":{"gpqa":[0.5707,47.8,121,205],"hle":[0.0656,3.4,34,43],"simplebench":[0.307,12.1,64,82],"enigma":[0.011,1.3,34,42],"aime":[0.5778,56.7,106,186],"aider":[18.2,13,46,56],"livebench":[66.92,62.9,10,48],"fiction120k":[0.375,21.4,33,40],"lech_writing":[7.38,50.5,30,45]}},"open-mixtral-8x22b":{"bs":{"gpqa":[0.3406,15.9,174,205],"math_l5":[0.2424,0,68,90]}},"gemini-1-5-flash-8b-001":{"bs":{"gpqa":[0.3295,14.3,178,205],"aime":[0.0458,2.3,157,186]},"ar":{"text_style_control":[1259,35558,305,47.8],"vision_style_control":[1071,6243,127,32.5]}},"gpt-5-4-nano":{"bs":{"gpqa":[0.7847,77.5,79,205],"arc_agi_2":[0.0569,6.2,48,82],"arc_agi":[0.515,51.3,50,84],"simpleqa":[0.117,1.4,68,72],"critpt":[0.0925,29.9,38,121],"forecastbench":[57.3,29.9,60,75],"chess":[0.3,47.6,33,138],"frontiermath":[0.2586,50,24,71],"frontiermath_t4":[0.0625,15.9,23,56],"aime":[0.8778,87.5,54,186],"proofbench":[0.05,5.1,57,64],"scicode":[0.4688,70.7,41,112],"alebench":[1004.52,41.1,36,102],"apex_agents":[0.255,33.3,38,53],"weirdml":[0.4923,35.2,48,128]},"ar":{"text_style_control":[1402,58424,146,79.8],"vision_style_control":[1201,23906,76,70.9]}},"gemini-2-5-flash-preview-04-17":{"bs":{"hle":[0.1208,16.8,23,43],"arc_agi":[0.323,31.3,62,84],"forecastbench":[60.6,79.1,22,75],"aime":[0.7306,72.4,83,186],"aider":[47.1,50.4,31,56],"weirdml":[0.4095,22.7,74,128],"vpct":[0.38,11.1,20,27],"geobench":[3854,75.9,11,28],"fiction120k":[0.531,41.8,26,40],"lech_writing":[7.65,61.7,25,45]}},"yi-34b-chat":{"bs":{"gpqa":[0.1474,0,202,205],"math_l5":[0.0515,0,87,90]},"ar":{"text_style_control":[1183,15483,341,31.1]}},"ring-2-6-1t":{"bs":{"critpt":[0.0371,12,52,121],"scicode":[0.4236,59.7,60,112],"alebench":[432.57,11.5,85,102]}},"open-mistral-nemo-2407":{"bs":{"gpqa":[0.2989,10.1,184,205],"math_l5":[0.1083,0,82,90]}},"open-mixtral-8x7b":{"bs":{"gpqa":[0.2983,10,185,205],"math_l5":[0.0995,0,83,90]}},"step-3-7-flash":{"bs":{"critpt":[0.0229,7.4,60,121],"scicode":[0.4005,54,67,112],"alebench":[694.12,25,64,102]}},"gemini-1-5-pro-001-feb24":{"bs":{"cybench":[0.075,0,18,21],"video_mme":[0.75,74.7,3,48]}},"gemini-2-0-flash":{"bs":{"simplebench":[0.189,0,78,82],"aider":[22.2,18.2,43,56],"livebench":[59.26,42.7,16,48],"lech_writing":[7.15,40.9,35,45]}},"mistral-small-3-2501":{"bs":{"gpqa":[0.4729,34.2,145,205],"chess":[0,0,119,138],"aime":[0.0667,4.4,149,186]}},"qwen3-5-9b":{"bs":{"gpqa":[0.7898,78.2,77,205],"critpt":[0.0029,0.9,85,121],"chess":[0.12,19.1,81,138],"aime":[0.6167,60.7,102,186],"terminalbench":[0.092,0.9,44,45],"scicode":[0.2755,23.5,98,112]}},"phi-3-medium-128k-instruct":{"bs":{"gpqa":[0.2759,6.9,189,205],"math_l5":[0.1756,0,74,90]}},"mistral-large-2402":{"bs":{"gpqa":[0.3876,22.4,165,205],"aime":[0.0194,0,171,186],"math_l5":[0.2446,0,67,90]},"ar":{"text_style_control":[1242,62436,309,44.2]}},"gemma-3-4b-it":{"bs":{"gpqa":[0.2323,0.8,199,205],"chess":[0,0,120,138],"aime":[0.075,5.2,145,186]},"ar":{"text_style_control":[1303,4171,270,57.8]}},"codex-mini":{"bs":{"arc_agi_2":[0.0127,1.4,64,82],"arc_agi":[0.2733,26.1,66,84]}},"devstral-small-2512":{"bs":{"critpt":[0,0,97,121],"scicode":[0.2882,26.7,97,112]}},"grok-4-1":{"bs":{"apex_agents":[0.248,32,40,53],"cybench":[0.39,28.9,6,21],"webdev_arena":[1209.85,8.2,91,94]},"ar":{"text_style_control":[1465,64152,48,93.9],"webdev":[1211,939,122,8.7]}},"qwen2-5-vl-72b-instruct":{"bs":{"osworld":[5,0,9,9],"video_mme":[0.735,64.5,4,48],"geobench":[3448,52.1,18,28],"spatialviz":[0.3331,11.3,6,8]},"ar":{"vision_style_control":[1121,3768,116,47.3]}},"ministral-3b-2410":{"bs":{"gpqa":[0.2525,3.6,195,205],"math_l5":[0.1444,0,78,90]}},"magistral-small-2506":{"bs":{"gpqa":[0.5606,46.4,124,205],"arc_agi_2":[0,0,74,82],"arc_agi":[0.05,2.8,79,84],"aime":[0.3,28.3,125,186]}},"nemotron-3-ultra":{"bs":{"gpqa":[0.8535,87.1,57,205],"critpt":[0.0314,10.1,56,121],"chess":[0.12,19.1,82,138],"aime":[0.8667,86.3,57,186],"proofbench":[0.02,2,61,64],"scicode":[0.3993,53.8,70,112],"apex_agents":[0.262,34.6,37,53],"weirdml":[0.4345,26.5,65,128]}},"qwen":{"bs":{"gpqa":[0.5612,46.5,123,205],"frontiermath":[0.0103,1.2,62,71],"aime":[0.1611,14.1,135,186],"math_l5":[0.6718,40.6,36,90],"aider":[21.8,17.7,44,56]},"ar":{"text_style_control":[1318,16478,249,61.1]}},"deepseek-r1-0528-qwen3-8b":{"bs":{"gpqa":[0.0928,0,205,205],"chess":[0.03,4.8,105,138],"aime":[0.4389,42.5,118,186]}},"gpt-4-5":{"bs":{"gpqa":[0.6869,64,101,205],"hle":[0.0544,0.7,36,43],"arc_agi_2":[0.008,0.9,69,82],"arc_agi":[0.103,8.3,75,84],"simplebench":[0.345,18.9,60,82],"enigma":[0.0318,6.9,28,42],"forecastbench":[61.7,95.5,6,75],"aime":[0.3778,36.3,121,186],"math_l5":[0.7863,62.7,29,90],"aider":[44.9,47.5,33,56],"livebench":[68.95,68.2,9,48],"cybench":[0.175,0,12,21],"weirdml":[0.3937,20.3,82,128],"vpct":[0.45,23.6,11,27],"fiction120k":[0.639,55.9,15,40],"lech_writing":[7.56,57.9,27,45]},"ar":{"text_style_control":[1445,14547,78,89.3],"vision_style_control":[1226,2925,63,78.1]}},"open-mistral-7b":{"bs":{"gpqa":[0.1323,0,203,205],"math_l5":[0.0368,0,88,90]}},"mixtral-8x7b-instruct-v0-1":{"bs":{"gpqa":[0.3059,11,183,205],"forecastbench":[56.3,14.9,66,75],"math_l5":[0.0929,0,84,90]},"ar":{"text_style_control":[1197,73503,335,34.1]}},"deepseek-r1-distill-qwen-1-5b":{"bs":{"gpqa":[0.3359,15.2,177,205],"chess":[0,0,121,138],"aime":[0.2139,19.5,130,186]}},"granite-4-1-30b":{"bs":{"critpt":[0,0,98,121],"scicode":[0.2581,19.3,105,112]}},"qwen-turbo":{"bs":{"gpqa":[0.4179,26.6,158,205],"aime":[0.0611,3.8,152,186],"math_l5":[0.5623,19.4,44,90]}},"mistral-small-3-1-2503":{"bs":{"gpqa":[0.4192,26.8,157,205],"chess":[0.01,1.6,112,138],"aime":[0.0389,1.5,161,186]}},"qwen3-235b-a22b-instruct-2507":{"bs":{"arc_agi_2":[0.0125,1.4,65,82],"arc_agi":[0.11,9.1,74,84],"aider":[59.6,66.5,20,56],"weirdml":[0.387,19.3,87,128]},"ar":{"text_style_control":[1423,95670,114,84.5]}},"solar-pro-3":{"bs":{"critpt":[0,0,99,121],"scicode":[0.2465,16.5,106,112]}},"qwen2-vl-72b-instruct":{"bs":{"balrog":[0.128,0,27,32],"video_mme":[0.712,48.9,7,48]}},"qwen3-8b":{"bs":{"gpqa":[0.5676,47.4,122,205],"critpt":[0,0,100,121],"chess":[0.05,7.9,96,138],"aime":[0.5611,55,107,186],"scicode":[0.2257,11.4,107,112]}},"grok-build-0-1":{"bs":{"critpt":[0.0914,29.5,40,121],"scicode":[0.5023,78.9,29,112],"gbaeval":[0.0238,3.1,15,23]}},"qwen3-1-7b":{"bs":{"gpqa":[0.3801,21.3,167,205],"chess":[0,0,122,138],"aime":[0.0806,5.8,141,186]}},"llama-3-1-tulu-3-70b-dpo":{"bs":{"gpqa":[0.4628,32.8,148,205],"aime":[0.0444,2.1,158,186],"math_l5":[0.4266,0,55,90]}},"gpt-5-mini":{"bs":{"gpqa":[0.75,72.7,90,205],"hle":[0.1944,34.6,17,43],"arc_agi_2":[0.0444,4.9,54,82],"arc_agi":[0.5433,54.3,48,84],"simpleqa":[0.216,17.4,58,72],"enigma":[0.0819,20.4,16,42],"critpt":[0,0,101,121],"forecastbench":[61,85.1,17,75],"chess":[0.3,47.6,34,138],"frontiermath":[0.2724,52.7,22,71],"frontiermath_t4":[0.0625,15.9,24,56],"aime":[0.8667,86.3,58,186],"math_l5":[0.9785,99.8,2,90],"proofbench":[0.09,9.1,52,64],"swebench":[0.6467,38.6,26,32],"terminalbench":[0.348,35.7,30,45],"scicode":[0.3924,52.1,74,112],"alebench":[799.77,30.5,51,102],"algotune":[1.38,8.7,15,18],"vending2":[-31.184,0,55,55],"weirdml":[0.5267,40.4,41,128],"vpct":[0.402,15,14,27],"fiction120k":[0.625,54.1,18,40],"lech_writing":[8.31,89,8,45]},"ar":{"text_style_control":[1390,26569,163,77],"vision_style_control":[1183,28970,90,65.4]}},"magistral-small-2509":{"bs":{"gpqa":[0.476,34.7,141,205],"critpt":[0.0029,0.9,86,121],"chess":[0.03,4.8,106,138],"aime":[0.2806,26.3,127,186],"scicode":[0.3519,42.2,89,112]}},"gemini-2-5-flash-lite-preview-06-17":{"bs":{"alebench":[325.9,6,93,102],"weirdml":[0.3522,14,98,128],"fiction120k":[0.219,1,38,40]},"ar":{"text_style_control":[1375,32216,179,73.7],"vision_style_control":[1188,35949,85,67]}},"inkling":{"bs":{"gpqa":[0.8826,91.1,42,205],"arc_agi_2":[0.3653,40,31,82],"arc_agi":[0.795,80.5,33,84],"simpleqa":[0.403,47.7,40,72],"simplebench":[0.5,46.3,42,82],"critpt":[0.0543,17.5,47,121],"chess":[0.21,33.3,53,138],"aime":[0.8889,88.6,51,186],"proofbench":[0,0,63,64],"scicode":[0.4606,68.7,44,112],"frontiercode":[0.14,11.6,27,31],"alebench":[946,38.1,38,102],"weirdml":[0.3229,9.5,104,128],"webdev_arena":[1407.6,45.2,53,94]},"ar":{"text_style_control":[1440,25922,85,88.3],"webdev":[1410,8970,71,47],"agent":[-0.0912,41981,40,16.2]}},"gemini-3-5-flash-lite":{"bs":{"gpqa":[0.8333,84.3,66,205],"arc_agi_2":[0.1028,11.2,41,82],"arc_agi":[0.535,53.4,49,84],"critpt":[0,0,102,121],"chess":[0.22,34.9,48,138],"aime":[0.7111,70.4,84,186],"proofbench":[0.13,13.1,48,64],"scicode":[0.4086,56,63,112],"alebench":[765.27,28.7,58,102],"weirdml":[0.39,19.7,86,128],"webdev_arena":[1449.14,52.9,43,94]},"ar":{"text_style_control":[1456,26165,59,91.8],"webdev":[1447,228,58,54.1],"agent":[-0.1373,23216,43,0],"vision_style_control":[1266,5254,34,90.1]}},"mimo-v2-flash":{"bs":{"critpt":[0,0,103,121],"scicode":[0.2593,19.6,103,112],"alebench":[737.95,27.3,61,102],"webdev_arena":[1330.17,30.7,76,94]},"ar":{"text_style_control":[1386,10739,169,76.2],"webdev":[1293,1658,109,24.5]}},"glm-4-5":{"bs":{"hle":[0.0832,7.7,28,43],"alebench":[344.82,7,90,102],"algotune":[1.52,28.1,10,18],"weirdml":[0.4058,22.1,77,128],"lech_writing":[7.34,48.8,33,45]},"ar":{"text_style_control":[1411,23712,136,81.8]}},"o1-pro":{"bs":{"hle":[0.0812,7.2,30,43],"arc_agi":[0.233,21.9,67,84],"enigma":[0.0614,14.9,20,42]}},"claude-sonnet-4":{"bs":{"gpqa":[0.7828,77.3,80,205],"hle":[0.0776,6.3,33,43],"arc_agi_2":[0.0593,6.5,47,82],"arc_agi":[0.4,39.3,57,84],"simplebench":[0.455,38.4,51,82],"enigma":[0.0312,6.7,29,42],"critpt":[0.0029,0.9,87,121],"forecastbench":[60.2,73.1,27,75],"frontiermath":[0.0414,7.3,53,71],"frontiermath_t4":[0,0,49,56],"aime":[0.7111,70.4,85,186],"math_l5":[0.8437,73.8,24,90],"scicode":[0.4005,54,68,112],"gso":[0.049,8.1,17,28],"aider":[61.3,68.7,17,56],"alebench":[655.35,23,69,102],"apex_agents":[0.23,28.7,41,53],"metr":[0.6197,59.1,17,35],"osworld":[43.9,41.9,5,9],"tac":[0.432,70.8,3,14],"deepresearch":[0.466,57.5,13,25],"cybench":[0.35,23.4,8,21],"weirdml":[0.4611,30.5,56,128],"vpct":[0.34,4,24,27],"geobench":[2468,0,27,28],"mindcube":[0.4475,null,3,5],"fiction120k":[0.364,19.9,34,40],"lech_writing":[8.14,82,14,45]},"ar":{"text_style_control":[1401,33944,148,79.5],"vision_style_control":[1206,1145,75,72.3]}},"c4ai-command-r-plus-08":{"bs":{"simplebench":[0.174,0,81,82],"livebench":[31.76,0,42,48]}},"phi-4-mini-instruct":{"bs":{"critpt":[0,0,104,121],"scicode":[0.1076,0,112,112]}},"phi-3-mini-4k-instruct":{"bs":{"chess":[0,0,123,138],"livebench":[22.36,0,47,48]},"ar":{"text_style_control":[1128,20118,376,18.7]}},"minimax-m3":{"bs":{"gpqa":[0.9091,94.8,29,205],"simplebench":[0.458,38.9,50,82],"critpt":[0.0371,12,53,121],"forecastbench":[60.4,76.1,25,75],"chess":[0.14,22.2,71,138],"aime":[0.7111,70.4,86,186],"proofbench":[0.18,18.2,39,64],"scicode":[0.4537,67,46,112],"frontiercode":[0.147,13.1,26,31],"alebench":[640.02,22.2,71,102],"osworld2":[0.046,5.5,8,9],"vending2":[2157.7717,20.1,37,55],"gbaeval":[0.0091,1.2,16,23],"surface_evolver":[0.55,49.6,12,23],"webdev_arena":[1487.64,60.1,35,94]},"ar":{"text_style_control":[1441,48540,84,88.5],"webdev":[1487,12686,48,61.8],"agent":[-0.0538,37895,34,30.5],"vision_style_control":[1237,15192,56,81.4],"document_style_control":[1433,6314,38,25.1]}},"o3-mini":{"bs":{"gpqa":[0.7427,71.7,91,205],"arc_agi_2":[0.0208,2.3,61,82],"arc_agi":[0.2233,20.9,68,84],"forecastbench":[59.6,64.2,36,75],"chess":[0.09,14.3,85,138],"frontiermath":[0.0808,15,43,71],"aime":[0.6389,63,99,186],"math_l5":[0.9517,94.7,13,90],"gso":[0.013,0,26,28],"aider":[53.8,59,26,56],"livebench":[70.01,71,8,48],"cybench":[0.225,6.1,10,21],"cad_eval":[0.54,67,6,15],"fiction120k":[0.438,29.6,29,40],"lech_writing":[6.15,0,44,45]},"ar":{"text_style_control":[1348,56655,207,67.7]}},"qwen2-5-32b-instruct":{"bs":{"gpqa":[0.4609,32.6,149,205],"chess":[0,0,124,138],"aime":[0.0736,5.1,146,186],"math_l5":[0.5607,19.1,45,90]}},"qwen3-6-35b-a3b":{"bs":{"gpqa":[0.8485,86.4,59,205],"critpt":[0.0029,0.9,88,121],"chess":[0.26,41.3,39,138],"aime":[0.8667,86.3,59,186],"terminalbench":[0.23,19.7,39,45],"scicode":[0.3576,43.6,85,112],"weirdml":[0.3449,12.9,101,128],"surface_evolver":[0.4438,36.2,17,23],"webdev_arena":[1249.75,15.7,84,94]}},"gemma-4-31b-it":{"bs":{"gpqa":[0.7576,73.8,89,205],"simpleqa":[0.104,0,70,72],"critpt":[0.0143,4.6,64,121],"chess":[0.05,7.9,97,138],"aime":[0.7333,72.7,82,186],"scicode":[0.434,62.2,52,112],"alebench":[925.5,37,42,102],"weirdml":[0.5226,39.8,45,128],"surface_evolver":[0.3062,18.9,19,23],"webdev_arena":[1363.56,36.9,67,94]}},"hermes-2-theta-llama-3-70b":{"bs":{"gpqa":[0.3747,20.6,169,205],"aime":[0.025,0.1,166,186],"math_l5":[0.2269,0,70,90]}},"o3-mini-high":{"bs":{"gpqa":[0.7702,75.5,83,205],"arc_agi_2":[0.0299,3.3,57,82],"arc_agi":[0.345,33.6,59,84],"simpleqa":[0.153,7.2,64,72],"simplebench":[0.228,0,73,82],"critpt":[0.0029,0.9,89,121],"chess":[0.17,27,67,138],"frontiermath":[0.1241,23.6,37,71],"frontiermath_t4":[0.0417,10.6,33,56],"aime":[0.7694,76.4,78,186],"math_l5":[0.9649,97.2,8,90],"scicode":[0.3979,53.4,71,112],"gso":[0.013,0,27,28],"aider":[60.4,67.6,18,56],"livebench":[75.88,86.5,4,48],"weirdml":[0.437,26.8,64,128],"lech_writing":[6.17,0.3,43,45]},"ar":{"text_style_control":[1363,18589,191,71.2]}},"kimi-k2-instruct":{"bs":{"simplebench":[0.263,4.3,69,82],"forecastbench":[60.2,73.1,28,75],"terminalbench":[0.278,26.2,34,45],"gso":[0.049,8.1,18,28],"aider":[59.1,65.9,22,56],"weirdml":[0.3936,20.3,84,128],"fiction120k":[0.406,25.4,30,40],"lech_writing":[8.56,99.4,2,45]}},"gemma-3-27b-it":{"bs":{"gpqa":[0.4773,34.8,140,205],"critpt":[0,0,105,121],"chess":[0,0,125,138],"aime":[0.225,20.6,129,186],"math_l5":[0.7404,53.8,31,90],"scicode":[0.2118,8,108,112],"aider":[4.9,0,55,56],"livebench":[49.99,18.2,27,48],"geobench":[3087,31,21,28],"lech_writing":[7.99,75.7,20,45]},"ar":{"text_style_control":[1365,46422,187,71.6],"vision_style_control":[1159,16992,99,58.3]}},"gpt-5-pro":{"bs":{"hle":[0.3164,64.1,9,43],"arc_agi_2":[0.1833,20.1,36,82],"arc_agi":[0.702,70.8,38,84],"simplebench":[0.616,66.9,20,82],"enigma":[0.1875,48.8,7,42],"frontiermath_t4":[0.146,37,14,56],"algotune":[1.31,0,18,18],"weirdml":[0.6039,52.2,30,128]}},"minimax-m2":{"bs":{"terminalbench":[0.3,29.2,33,45],"vending2":[160.596,1.7,48,55],"webdev_arena":[1297,24.5,80,94]},"ar":{"text_style_control":[1346,6753,214,67.3],"webdev":[1298,6539,108,25.4]}},"claude-2-0":{"bs":{"gpqa":[0.3466,16.7,173,205],"aime":[0.025,0.1,167,186],"math_l5":[0.1173,0,79,90]}},"qwen2-vl-7b-instruct":{"bs":{"balrog":[0.037,0,32,32],"video_mme":[0.639,0,24,48]},"ar":{"vision_style_control":[1031,5766,134,20.6]}},"gemini-1-0-pro-001":{"bs":{"gpqa":[0.3396,15.7,175,205],"aime":[0.0111,0,177,186],"math_l5":[0.1124,0,81,90]}},"granite-4-0-micro":{"bs":{"gpqa":[0.2828,7.8,187,205],"chess":[0,0,126,138],"aime":[0.0278,0.4,164,186]}},"qwen3-5-27b":{"bs":{"alebench":[349.45,7.2,89,102],"vending2":[201.976,2.1,47,55],"weirdml":[0.3953,20.5,80,128],"webdev_arena":[1357.46,35.8,69,94]},"ar":{"text_style_control":[1408,27227,140,81.1],"webdev":[1357,7427,95,36.9],"vision_style_control":[1218,25350,66,75.8]}},"laguna-m-1":{"bs":{"proofbench":[0,0,64,64],"surface_evolver":[0.1563,0,22,23],"webdev_arena":[1347.31,33.9,71,94]},"ar":{"webdev":[1347,5062,98,35]}},"gemini-2-5-pro":{"bs":{"gpqa":[0.8529,87,58,205],"arc_agi_2":[0.0486,5.3,52,82],"arc_agi":[0.41,40.4,55,84],"critpt":[0.02,6.5,61,121],"forecastbench":[60.4,76.1,26,75],"chess":[0.2,31.8,60,138],"frontiermath":[0.1414,26.9,36,71],"frontiermath_t4":[0.0417,10.6,34,56],"aime":[0.8417,83.8,67,186],"swebench":[0.5756,13,30,32],"terminalbench":[0.326,32.7,32,45],"scicode":[0.4282,60.8,57,112],"gso":[0.0392,5.9,21,28],"alebench":[785.52,29.8,55,102],"algotune":[1.51,26.7,11,18],"apex_agents":[0.17,17.7,46,53],"gdpval":[0.233,6.6,9,11],"deepresearch":[0.415,32,20,25],"vending2":[573.642,5.5,43,55],"weirdml":[0.5403,42.5,40,128],"spatialviz":[0.4466,100,1,8],"lech_writing":[8.38,91.9,6,45],"webdev_arena":[1225.69,11.2,89,94]},"ar":{"text_style_control":[1445,122554,77,89.5],"webdev":[1226,2667,121,11.6],"vision_style_control":[1246,87635,48,84.3],"document_style_control":[1431,25110,39,22.3]}},"gemini-2-5-flash-preview-05-20":{"bs":{"hle":[0.1096,14.1,25,43],"arc_agi_2":[0.0254,2.8,59,82],"arc_agi":[0.3333,32.4,60,84],"enigma":[0.027,5.6,31,42],"aime":[0.7083,70.1,87,186],"aider":[55.1,60.7,25,56],"weirdml":[0.4095,22.7,75,128],"geobench":[3786,71.9,14,28],"fiction120k":[0.688,62.3,12,40]}},"deepseek-v3-2":{"bs":{"arc_agi_2":[0.0403,4.4,55,82],"arc_agi":[0.57,57,47,84],"terminalbench":[0.396,42.2,25,45],"apex_agents":[0.188,21,44,53],"webdev_arena":[1324.54,29.6,78,94]},"ar":{"text_style_control":[1425,46458,111,84.9],"webdev":[1361,6633,92,37.5]}},"gemma-3-12b-it":{"bs":{"gpqa":[0.3946,23.4,164,205],"critpt":[0,0,106,121],"chess":[0,0,127,138],"aime":[0.1667,14.6,133,186],"scicode":[0.1736,0,109,112],"mindcube":[0.4667,null,1,5]},"ar":{"text_style_control":[1342,3829,220,66.3]}},"mistral-large-2411":{"bs":{"gpqa":[0.5133,39.8,132,205],"forecastbench":[56.9,23.9,65,75],"frontiermath":[0.0034,0,67,71],"aime":[0.0778,5.5,143,186],"math_l5":[0.5028,7.9,48,90],"livebench":[48.43,14.1,29,48]},"ar":{"text_style_control":[1305,28073,268,58.3]}},"granite-4-0-1b":{"bs":{"gpqa":[0.2399,1.9,197,205],"chess":[0,0,128,138],"aime":[0.0083,0,180,186]}},"granite-4-0-350m":{"bs":{"gpqa":[0.1124,0,204,205],"chess":[0,0,129,138],"aime":[0.0028,0,184,186]}},"gemma-3-1b-it":{"bs":{"gpqa":[0.1995,0,200,205],"chess":[0,0,130,138],"aime":[0.0111,0,178,186]}},"qwen3-6-flash":{"bs":{"gpqa":[0.8333,84.3,67,205],"simpleqa":[0.1592,8.2,63,72],"simplebench":[0.352,20.1,59,82],"chess":[0.2,31.8,61,138],"frontiermath":[0.1034,19.5,38,71],"frontiermath_t4":[0,0,50,56],"aime":[0.8444,84.1,65,186],"alebench":[326.4,6,92,102]}},"llama-4-maverick-17b-128e-instruct-fp8":{"bs":{"gpqa":[0.6698,61.6,104,205],"forecastbench":[57.5,32.8,57,75],"frontiermath":[0.0069,0.5,64,71],"aime":[0.2056,18.6,131,186],"math_l5":[0.7302,51.9,32,90],"alebench":[172.97,0,101,102]}},"gemma-4-26b-a4b":{"bs":{"critpt":[0,0,107,121],"scicode":[0.4005,54,69,112],"alebench":[927.17,37.1,41,102],"weirdml":[0.3517,13.9,99,128],"webdev_arena":[1361.65,36.6,68,94]},"ar":{"text_style_control":[1438,5804,88,87.8],"webdev":[1361,1442,91,37.7],"vision_style_control":[1241,22658,52,82.7]}},"gemini-1-5-flash-001":{"bs":{"gpqa":[0.4037,24.6,163,205],"forecastbench":[53.9,0,71,75],"aime":[0.0389,1.5,162,186],"math_l5":[0.2512,0,66,90],"video_mme":[0.703,42.7,10,48]},"ar":{"text_style_control":[1286,62833,284,54],"vision_style_control":[1060,13260,130,29.1]}},"gemma-2-27b-it":{"bs":{"gpqa":[0.3649,19.2,170,205],"aime":[0.0139,0,176,186],"math_l5":[0.2789,0,63,90],"livebench":[38.18,0,40,48]},"ar":{"text_style_control":[1289,75754,279,54.7]}},"gpt-oss-20b":{"bs":{"gpqa":[0.608,53,117,205],"critpt":[0.0143,4.6,65,121],"chess":[0.04,6.4,103,138],"aime":[0.6528,64.4,97,186],"terminalbench":[0.034,0,45,45],"scicode":[0.3438,40.2,90,112],"alebench":[566.05,18.4,79,102],"weirdml":[0.4093,22.6,76,128]},"ar":{"text_style_control":[1317,10393,252,60.9]}},"qwen3-5-plus":{"bs":{"gpqa":[0.8485,86.4,60,205],"simpleqa":[0.2535,23.5,57,72],"chess":[0.22,34.9,49,138],"frontiermath":[0.2103,40.5,29,71],"frontiermath_t4":[0.0208,5.3,42,56],"aime":[0.8667,86.3,60,186],"alebench":[621.92,21.3,73,102],"apex_agents":[0.277,37.3,36,53],"vending2":[0.544,0.2,51,55],"webdev_arena":[1399.23,43.6,55,94]}},"glm-4-7":{"bs":{"gpqa":[0.8333,84.3,68,205],"simpleqa":[0.322,34.6,51,72],"simplebench":[0.477,42.2,44,82],"critpt":[0.0171,5.5,63,121],"chess":[0.06,9.5,91,138],"frontiermath":[0.0244,4,56,71],"frontiermath_t4":[0,0,51,56],"aime":[0.8333,82.9,69,186],"proofbench":[0.06,6.1,56,64],"terminalbench":[0.334,33.8,31,45],"scicode":[0.4514,66.5,47,112],"alebench":[399.48,9.8,86,102],"apex_agents":[0.212,25.4,43,53],"vending2":[2376.816,22.1,36,55],"webdev_arena":[1434.29,50.1,49,94]},"ar":{"text_style_control":[1442,11893,83,88.6],"webdev":[1435,3811,66,51.8]}},"deepseek-llm-67b-chat":{"bs":{"gpqa":[0.2462,2.7,196,205],"chess":[0,0,131,138],"aime":[0.0083,0,181,186],"math_l5":[0.0639,0,85,90]},"ar":{"text_style_control":[1185,4932,339,31.4]}},"gemini-2-5-pro-preview-06-05":{"bs":{"gpqa":[0.8485,86.4,61,205],"hle":[0.2164,39.9,15,43],"arc_agi_2":[0,0,75,82],"arc_agi":[0.313,30.2,63,84],"simplebench":[0.624,68.3,17,82],"enigma":[0.0557,13.3,24,42],"frontiermath":[0.1034,19.5,39,71],"frontiermath_t4":[0.0208,5.3,43,56],"gso":[0.0392,5.9,22,28],"aider":[83.1,96.9,3,56],"metr":[0.5544,45.9,21,35],"deepresearch":[0.428,38.5,19,25],"rli":[0.0083,0,11,11],"vpct":[0.464,26.1,9,27],"fiction120k":[0.875,86.7,6,40]}},"mistral-large-2512":{"bs":{"critpt":[0,0,108,121],"scicode":[0.3623,44.7,81,112],"alebench":[264.7,2.8,96,102],"webdev_arena":[1230.14,12,88,94]}},"mixtral-8x22b-instruct-v0-1":{"bs":{"forecastbench":[56.3,14.9,67,75],"cybench":[0.075,0,19,21],"weirdml":[0.0317,0,127,128]},"ar":{"text_style_control":[1229,51416,318,41.3]}},"gemini-3-1-flash-lite":{"bs":{"gpqa":[0.8182,82.2,74,205],"hle":[0.0864,8.4,27,43],"enigma":[0.0304,6.5,30,42],"critpt":[0.0114,3.7,69,121],"forecastbench":[54.4,0,69,75],"chess":[0.25,39.7,42,138],"aime":[0.8,79.5,75,186],"scicode":[0.419,58.6,61,112],"alebench":[797.73,30.4,52,102],"apex_agents":[0.25,32.4,39,53],"deepresearch":[0.373,11,22,25],"weirdml":[0.5219,39.7,46,128],"webdev_arena":[1254.07,16.5,83,94]}},"gemma-2-9b-it":{"bs":{"gpqa":[0.2746,6.7,190,205],"aime":[0.0056,0,182,186],"math_l5":[0.2101,0,72,90],"livebench":[28.66,0,44,48]},"ar":{"text_style_control":[1267,54611,299,49.7]}},"qwen3-coder-480b-a35b-instruct":{"bs":{"terminalbench":[0.272,25.4,36,45],"gso":[0.049,8.1,19,28],"alebench":[461.45,13,83,102],"algotune":[1.44,17,13,18],"weirdml":[0.4117,23,72,128],"webdev_arena":[1273.25,20.1,81,94]},"ar":{"text_style_control":[1388,25089,166,76.5],"webdev":[1274,12265,110,20.8]}},"grok-4-1-fast":{"bs":{"simplebench":[0.56,57,33,82],"forecastbench":[61,85.1,18,75],"proofbench":[0.04,4,58,64],"alebench":[394.93,9.6,87,102],"vending2":[1106.628,10.4,40,55],"webdev_arena":[1223,10.7,90,94]},"ar":{"text_style_control":[1430,55363,101,86.1],"webdev":[1240,5314,117,14.4],"vision_style_control":[1195,12485,81,68.9]}},"kimi-k2-thinking":{"bs":{"frontiermath":[0.214,41.2,28,71],"frontiermath_t4":[0,0,52,56],"terminalbench":[0.357,36.9,28,45],"alebench":[597.5,20,76,102],"apex_agents":[0.115,7.7,49,53],"metr":[0.5919,53.5,19,35],"weirdml":[0.4279,25.5,68,128]}},"deepseek-r1-distill-qwen-32b":{"bs":{"gpqa":[0.6414,57.6,112,205],"chess":[0.01,1.6,113,138],"aime":[0.5556,54.5,109,186],"livebench":[45.55,6.5,33,48],"balrog":[0.195,0,19,32]}},"qwen3-coder-next":{"bs":{"critpt":[0,0,109,121],"scicode":[0.3229,35.1,94,112],"weirdml":[0.344,12.7,102,128]}},"mistral-small-2501":{"bs":{"gpqa":[0.453,31.5,152,205],"aime":[0.0528,3,154,186],"math_l5":[0.4482,0,54,90],"livebench":[42.55,0,37,48]}},"mistral-medium-2508":{"bs":{"critpt":[0,0,110,121],"scicode":[0.338,38.8,91,112],"alebench":[210.18,0,100,102],"weirdml":[0.3313,10.8,103,128]},"ar":{"text_style_control":[1409,92697,139,81.2],"vision_style_control":[1159,41260,98,58.4]}},"o4-mini-high":{"bs":{"gpqa":[0.7961,79.1,76,205],"hle":[0.1808,31.3,19,43],"arc_agi_2":[0.0611,6.7,46,82],"arc_agi":[0.5867,58.8,46,84],"simpleqa":[0.188,12.9,62,72],"simplebench":[0.387,26.3,57,82],"enigma":[0.0921,23.1,15,42],"critpt":[0.006,1.9,77,121],"chess":[0.26,41.3,40,138],"frontiermath":[0.2483,47.9,25,71],"frontiermath_t4":[0.0625,15.9,25,56],"aime":[0.8167,81.2,72,186],"math_l5":[0.9783,99.8,3,90],"gso":[0.036,5.2,24,28],"aider":[72,82.5,12,56],"alebench":[826.17,31.9,48,102],"algotune":[1.72,55.8,6,18],"gdpval":[0.253,13.9,8,11],"weirdml":[0.5256,40.3,42,128],"geobench":[3717,67.9,15,28]}},"grok-4-fast":{"bs":{"arc_agi_2":[0.0528,5.8,49,82],"arc_agi":[0.485,48.2,51,84],"forecastbench":[60.5,77.6,23,75],"cybench":[0.3,16.5,9,21],"weirdml":[0.4286,25.6,67,128],"fiction120k":[0.75,70.4,8,40],"webdev_arena":[1149,0,94,94]},"ar":{"text_style_control":[1405,17975,142,80.3],"webdev":[1161,731,127,0]}},"amazon-nova-lite-v1-0":{"bs":{"hle":[0.0364,0,42,43],"alebench":[236.25,1.3,97,102],"livebench":[36.35,0,41,48]},"ar":{"text_style_control":[1260,19372,304,48.2],"vision_style_control":[1019,1854,138,16.9]}},"gemini-2-0-flash-001":{"bs":{"gpqa":[0.6414,57.6,113,205],"arc_agi_2":[0.013,1.4,63,82],"frontiermath":[0.0172,2.6,60,71],"aime":[0.3111,29.4,123,186],"math_l5":[0.8217,69.5,27,90],"livebench":[61.47,48.5,15,48],"tac":[0.19,0,7,14],"weirdml":[0.2577,0,107,128],"geobench":[3897,78.4,9,28],"cad_eval":[0.3,24,11,15],"fiction120k":[0.625,54.1,19,40]},"ar":{"text_style_control":[1360,43351,193,70.4],"vision_style_control":[1172,10119,94,62.2]}},"llama-2-70b-chat-hf":{"bs":{"gpqa":[0.2633,5.1,193,205],"forecastbench":[51.4,0,74,75],"aime":[0,0,186,186],"math_l5":[0.0329,0,90,90]}},"grok-code-fast-1":{"bs":{"terminalbench":[0.258,23.5,37,45],"alebench":[587.73,19.5,77,102],"weirdml":[0.3506,13.7,100,128],"webdev_arena":[1164.51,0,93,94]},"ar":{"webdev":[1165,783,126,0]}},"grok-3":{"bs":{"gpqa":[0.6758,62.4,103,205],"arc_agi_2":[0,0,76,82],"arc_agi":[0.055,3.3,77,84],"simplebench":[0.361,21.7,58,82],"frontiermath":[0.0379,6.6,55,71],"frontiermath_t4":[0,0,53,56],"aime":[0.5556,54.5,110,186],"math_l5":[0.8875,82.2,20,90],"aider":[53.3,58.4,27,56],"apex_agents":[0.073,0,50,53],"balrog":[0.295,21.3,13,32],"weirdml":[0.3724,17,93,128],"fiction120k":[0.583,48.6,22,40],"lech_writing":[7.64,61.2,26,45]}},"meta-llama-3-8b-instruct":{"bs":{"gpqa":[0.2607,4.8,194,205],"forecastbench":[58.6,49.3,46,75],"chess":[0,0,132,138],"aime":[0.0194,0,172,186],"math_l5":[0.0613,0,86,90]}},"minimax-m2-5":{"bs":{"arc_agi_2":[0.0486,5.3,53,82],"arc_agi":[0.6367,64,44,84],"proofbench":[0.04,4,59,64],"terminalbench":[0.427,46.4,24,45],"alebench":[618.17,21.1,74,102],"apex_agents":[0.187,20.8,45,53],"vending2":[-23.16,0,54,55],"webdev_arena":[1383.9,40.7,62,94]},"ar":{"text_style_control":[1390,40843,162,77.2],"webdev":[1384,7186,85,42]}},"nemotron-3-super":{"bs":{"critpt":[0.0314,10.1,57,121],"scicode":[0.36,44.2,83,112],"alebench":[213.9,0.2,99,102],"weirdml":[0.3801,18.2,90,128]}},"o1-mini":{"bs":{"gpqa":[0.6237,55.2,115,205],"arc_agi_2":[0.0083,0.9,68,82],"arc_agi":[0.14,12.2,73,84],"simplebench":[0.181,0,79,82],"frontiermath":[0.0172,2.6,61,71],"aime":[0.4694,45.7,116,186],"math_l5":[0.8918,83.1,19,90],"aider":[32.9,32,38,56],"livebench":[57.76,38.7,18,48],"cybench":[0.1,0,16,21],"weirdml":[0.3632,15.6,96,128],"lech_writing":[6.49,13.6,39,45]},"ar":{"text_style_control":[1337,51981,223,65.3]}},"mistral-7b-instruct-v0-3":{"bs":{"gpqa":[0.1518,0,201,205],"chess":[0,0,133,138],"aime":[0.0028,0,185,186],"math_l5":[0.036,0,89,90]}},"phi-4":{"bs":{"gpqa":[0.5606,46.4,125,205],"chess":[0.01,1.6,114,138],"aime":[0.1375,11.6,136,186],"math_l5":[0.6494,36.2,38,90],"livebench":[41.61,0,38,48],"balrog":[0.116,0,28,32],"lech_writing":[6.26,4,41,45]},"ar":{"text_style_control":[1256,24126,306,47.3]}},"grok-2":{"bs":{"gpqa":[0.5379,43.3,129,205],"simplebench":[0.227,0,74,82],"frontiermath":[0.0069,0.5,65,71],"aime":[0.1153,9.4,137,186],"math_l5":[0.6352,33.5,39,90],"livebench":[54.3,29.6,21,48],"weirdml":[0.2224,0,111,128],"lech_writing":[6.36,8.2,40,45]},"ar":{"text_style_control":[1336,63498,227,65]}},"trinity-large-thinking":{"bs":{"critpt":[0.0086,2.8,75,121],"scicode":[0.3611,44.4,82,112],"surface_evolver":[0.1563,0,23,23],"webdev_arena":[1238.37,13.5,86,94]},"ar":{"text_style_control":[1369,28967,185,72.4],"webdev":[1237,1303,119,13.7]}},"qwen2-72b-instruct":{"bs":{"gpqa":[0.4078,25.2,160,205],"math_l5":[0.3907,0,60,90],"metr":[0.299,0,31,35],"tac":[0.042,0,14,14],"weirdml":[0.113,0,121,128]},"ar":{"text_style_control":[1262,37325,301,48.5]}},"mercury-2":{"bs":{"critpt":[0.0085,2.7,76,121],"scicode":[0.3866,50.7,77,112],"alebench":[785.58,29.8,54,102],"weirdml":[0.432,26.1,66,128],"webdev_arena":[1166.17,0,92,94]},"ar":{"text_style_control":[1346,3042,211,67.4],"webdev":[1167,904,125,0.2]}},"gemini-1-5-flash-002":{"bs":{"gpqa":[0.4732,34.3,144,205],"frontiermath":[0,0,70,71],"aime":[0.1625,14.2,134,186],"math_l5":[0.6187,30.3,42,90],"balrog":[0.146,0,26,32],"weirdml":[0.2487,0,109,128],"geobench":[3934,80.6,6,28]},"ar":{"text_style_control":[1309,34902,261,59.1],"vision_style_control":[1141,7241,109,53.1]}},"qwen2-5-72b-instruct":{"bs":{"gpqa":[0.4915,36.8,135,205],"forecastbench":[57.5,32.8,58,75],"aime":[0.0806,5.8,142,186],"math_l5":[0.6317,32.8,40,90],"metr":[0.3578,6.3,30,35],"tac":[0.118,0,11,14],"balrog":[0.162,0,24,32],"weirdml":[0.1597,0,117,128]},"ar":{"text_style_control":[1303,39406,272,57.7]}},"amazon-nova-pro-v1-0":{"bs":{"hle":[0.044,0,40,43],"livebench":[43.53,1.2,35,48],"tac":[0.057,0,13,14],"lech_writing":[6.05,0,45,45]},"ar":{"text_style_control":[1290,24745,277,54.8],"vision_style_control":[1019,2335,137,17]}},"claude-3-sonnet":{"bs":{"gpqa":[0.4059,24.9,161,205],"aime":[0.025,0.1,168,186],"math_l5":[0.1817,0,73,90],"weirdml":[0.1016,0,122,128]},"ar":{"text_style_control":[1281,109284,288,52.9],"vision_style_control":[1017,12314,139,16.2]}},"llama-3-1-70b-instruct":{"bs":{"gpqa":[0.4419,29.9,154,205],"aime":[0.0361,1.3,163,186],"math_l5":[0.3668,0,62,90],"tac":[0.128,0,10,14],"balrog":[0.279,16.9,15,32],"weirdml":[0.0897,0,124,128]},"ar":{"text_style_control":[1293,55240,276,55.5]}},"qwen2-5-7b-instruct":{"bs":{"gpqa":[0.3548,17.8,172,205],"chess":[0,0,134,138],"aime":[0.025,0.1,169,186],"balrog":[0.078,0,30,32]}},"meta-llama-3-70b-instruct":{"bs":{"gpqa":[0.4056,24.9,162,205],"aime":[0.0431,2,159,186],"math_l5":[0.2255,0,71,90],"cybench":[0.05,0,21,21]}},"gpt-4-1-mini":{"bs":{"gpqa":[0.6585,60,107,205],"arc_agi_2":[0,0,77,82],"arc_agi":[0.035,1.3,82,84],"simpleqa":[0.127,3,66,72],"critpt":[0,0,111,121],"chess":[0.07,11.1,89,138],"frontiermath":[0.0448,8,51,71],"aime":[0.4472,43.4,117,186],"math_l5":[0.8729,79.4,21,90],"scicode":[0.4039,54.9,66,112],"aider":[32.4,31.4,39,56],"weirdml":[0.3761,17.6,91,128],"cad_eval":[0.16,0,14,15],"fiction120k":[0.469,33.7,27,40]},"ar":{"text_style_control":[1383,38631,172,75.4],"vision_style_control":[1201,40274,78,70.8]}},"qwen3-5-flash":{"bs":{"gpqa":[0.8232,82.9,72,205],"simpleqa":[0.2032,15.4,59,72],"chess":[0.21,33.3,54,138],"frontiermath":[0.0621,11.4,45,71],"frontiermath_t4":[0,0,54,56],"aime":[0.8444,84.1,66,186],"alebench":[221.8,0.6,98,102],"vending2":[462.685,4.5,45,55],"webdev_arena":[1238.12,13.5,87,94]},"ar":{"text_style_control":[1397,58193,152,78.6],"webdev":[1238,1270,118,14]}},"mistral-small-2503":{"bs":{"gpqa":[0.4747,34.5,142,205],"critpt":[0,0,112,121],"aime":[0.0583,3.5,153,186],"math_l5":[0.4677,1.1,50,90],"scicode":[0.265,21,100,112],"livebench":[43.96,2.3,34,48]}},"claude-2-1":{"bs":{"gpqa":[0.3295,14.3,179,205],"forecastbench":[54.2,0,70,75],"aime":[0.0194,0,173,186],"weirdml":[0.0706,0,125,128]}},"gpt-4":{"bs":{"gpqa":[0.4236,27.4,156,205],"forecastbench":[57.8,37.3,54,75],"chess":[0.04,6.4,104,138],"aime":[0.0111,0,179,186],"math_l5":[0.4002,0,58,90],"metr":[0.3611,7,29,35],"weirdml":[0.1236,0,119,128]},"ar":{"text_style_control":[1313,93439,258,60]}},"claude-haiku-4-5":{"bs":{"gpqa":[0.7121,67.5,96,205],"arc_agi_2":[0.0403,4.4,56,82],"arc_agi":[0.4767,47.3,52,84],"simpleqa":[0.132,3.8,65,72],"critpt":[0,0,113,121],"forecastbench":[61.4,91,10,75],"chess":[0.08,12.7,87,138],"frontiermath":[0.059,10.8,46,71],"frontiermath_t4":[0.0208,5.3,44,56],"aime":[0.6667,65.9,94,186],"math_l5":[0.9636,97,9,90],"terminalbench":[0.355,36.7,29,45],"scicode":[0.4329,62,54,112],"alebench":[653.48,22.9,70,102],"apex_agents":[0.214,25.8,42,53],"deepresearch":[0.455,52,15,25],"vending2":[458.886,4.4,46,55],"balrog":[0.312,26,12,32],"exploitbench":[0.137,0.6,8,9],"weirdml":[0.454,29.4,61,128],"blueprint2":[0,0,24,24],"webdev_arena":[1327.41,30.2,77,94]},"ar":{"text_style_control":[1415,129278,129,82.6],"webdev":[1329,27785,104,31.5],"document_style_control":[1419,34677,42,8.3]}},"llama-3-2-1b-instruct":{"bs":{"gpqa":[0.2393,1.8,198,205],"chess":[0,0,135,138],"aime":[0.0056,0,183,186],"balrog":[0.066,0,31,32]},"ar":{"text_style_control":[1111,8045,384,15]}},"gpt-4-1":{"bs":{"gpqa":[0.6692,61.5,105,205],"hle":[0.054,0.6,37,43],"arc_agi_2":[0.0042,0.5,72,82],"arc_agi":[0.055,3.3,78,84],"simpleqa":[0.311,32.8,52,72],"simplebench":[0.27,5.6,68,82],"enigma":[0.0217,4.2,33,42],"forecastbench":[61.5,92.5,7,75],"chess":[0.06,9.5,92,138],"frontiermath":[0.0552,10,48,71],"frontiermath_t4":[0,0,55,56],"aime":[0.3833,36.8,119,186],"math_l5":[0.8301,71.2,26,90],"swebench":[0.4854,0,31,32],"aider":[52.4,57.2,28,56],"alebench":[558.1,18,80,102],"weirdml":[0.3904,19.8,85,128],"geobench":[3791,72.2,13,28],"cad_eval":[0.42,45.5,8,15],"fiction120k":[0.625,54.1,20,40]},"ar":{"text_style_control":[1414,49941,130,82.5],"vision_style_control":[1214,41012,71,74.6]}},"claude-3-5-sonnet":{"bs":{"gpqa":[0.553,45.4,128,205],"hle":[0.0408,0,41,43],"simplebench":[0.414,31.1,53,82],"enigma":[0.0091,0.8,35,42],"forecastbench":[60.7,80.6,21,75],"frontiermath":[0.0207,3.2,57,71],"frontiermath_t4":[0,0,56,56],"aime":[0.0847,6.2,140,186],"math_l5":[0.5695,20.8,43,90],"gso":[0.046,7.5,20,28],"aider":[51.6,56.2,29,56],"livebench":[59.03,42.1,17,48],"metr":[0.4524,25.4,26,35],"tac":[0.344,42.7,6,14],"balrog":[0.326,29.9,10,32],"cybench":[0.175,0,13,21],"weirdml":[0.3997,21.2,78,128],"video_mme":[0.6,0,28,48],"vpct":[0.33,2.2,26,27],"geobench":[3327,45,20,28],"cad_eval":[0.48,56.2,7,15],"lech_writing":[8.03,77.4,18,45]},"ar":{"text_style_control":[1374,87694,180,73.5],"vision_style_control":[1161,10377,96,59]}},"gpt-4-turbo":{"bs":{"gpqa":[0.4659,33.3,147,205],"simplebench":[0.251,2.2,70,82],"forecastbench":[59.4,61.2,38,75],"chess":[0.06,9.5,93,138],"aime":[0.0667,4.4,150,186],"math_l5":[0.4673,1.1,51,90],"metr":[0.3674,8.3,28,35],"weirdml":[0.1801,0,116,128]},"ar":{"text_style_control":[1324,98114,240,62.5],"vision_style_control":[1112,13391,120,44.5]}},"minimax-m2-7":{"bs":{"critpt":[0.0057,1.8,79,121],"proofbench":[0.03,3,60,64],"terminalbench":[0.451,49.7,21,45],"scicode":[0.4699,71,40,112],"alebench":[599.25,20.1,75,102],"exploitbench":[0.133,0,9,9],"weirdml":[0.3695,16.6,94,128],"gbaeval":[0,0,23,23],"webdev_arena":[1398.14,43.4,56,94]},"ar":{"text_style_control":[1415,69169,126,82.7],"webdev":[1398,15194,77,44.6],"agent":[-0.1322,37514,42,0.4]}},"glm-4-6":{"bs":{"critpt":[0.0114,3.7,70,121],"frontiermath":[0.0382,6.7,54,71],"frontiermath_t4":[0.0213,5.4,36,56],"terminalbench":[0.245,21.7,38,45],"scicode":[0.3843,50.1,78,112],"alebench":[340.82,6.8,91,102],"apex_agents":[0.118,8.2,48,53],"webdev_arena":[1340.18,32.6,72,94]},"ar":{"text_style_control":[1425,35061,112,84.8],"webdev":[1341,6600,100,33.7]}},"gemini-1-5-pro-002":{"bs":{"gpqa":[0.5723,48,120,205],"hle":[0.046,0,38,43],"arc_agi_2":[0.008,0.9,70,82],"simplebench":[0.271,5.8,67,82],"aime":[0.2306,21.2,128,186],"math_l5":[0.7039,46.8,33,90],"tac":[0.08,0,12,14],"balrog":[0.21,0,18,32],"weirdml":[0.222,0,112,128],"cad_eval":[0.34,31.1,9,15]},"ar":{"text_style_control":[1351,55606,203,68.4],"vision_style_control":[1179,8902,91,64.5]}},"llama-4-scout-17b-16e-instruct":{"bs":{"gpqa":[0.5183,40.5,131,205],"arc_agi_2":[0,0,78,82],"arc_agi":[0.005,0,83,84],"critpt":[0,0,114,121],"forecastbench":[57.5,32.8,59,75],"frontiermath":[0,0,71,71],"aime":[0.0778,5.5,144,186],"math_l5":[0.6227,31.1,41,90],"scicode":[0.1701,0,110,112],"spatialviz":[0.3424,19,4,8],"fiction120k":[0.273,8,37,40]},"ar":{"text_style_control":[1321,29740,245,61.8],"vision_style_control":[1127,6466,113,49]}},"gpt-5-nano":{"bs":{"gpqa":[0.6944,65,99,205],"arc_agi_2":[0.0261,2.9,58,82],"arc_agi":[0.2071,19.2,70,84],"simpleqa":[0.117,1.4,69,72],"forecastbench":[59.1,56.7,43,75],"chess":[0.27,42.9,37,138],"frontiermath":[0.0828,15.4,42,71],"frontiermath_t4":[0.0208,5.3,45,56],"aime":[0.8111,80.7,73,186],"math_l5":[0.9524,94.8,12,90],"proofbench":[0.12,12.1,49,64],"terminalbench":[0.218,18.1,40,45],"alebench":[718.67,26.3,62,102],"weirdml":[0.3806,18.3,89,128],"vpct":[0.372,9.7,21,27],"fiction120k":[0.219,1,39,40]},"ar":{"text_style_control":[1337,8128,222,65.4],"vision_style_control":[1146,3948,105,54.5]}},"gemini-2-5-flash":{"bs":{"simplebench":[0.412,30.7,54,82],"critpt":[0.011,3.6,72,121],"forecastbench":[59,55.2,45,75],"frontiermath":[0.0484,8.7,49,71],"frontiermath_t4":[0.0417,10.6,35,56],"terminalbench":[0.171,11.7,43,45],"alebench":[661.88,23.4,68,102],"apex_agents":[0.064,0,51,53],"vending2":[548.836,5.3,44,55],"balrog":[0.335,32.4,8,32],"spatialviz":[0.3686,40.6,3,8]},"ar":{"text_style_control":[1410,122732,138,81.5],"vision_style_control":[1215,58893,69,75]}},"gpt-3-5-turbo":{"bs":{"gpqa":[0.2803,7.5,188,205],"forecastbench":[50.4,0,75,75],"chess":[0,0,136,138],"aime":[0.0222,0,170,186],"math_l5":[0.1589,0,75,90],"weirdml":[0.0348,0,126,128]},"ar":{"text_style_control":[1225,66207,321,40.4]}},"llama-3-2-90b-vision-instruct":{"bs":{"gpqa":[0.4104,25.5,159,205],"enigma":[0.0038,0,42,42],"aime":[0.0264,0.3,165,186],"math_l5":[0.3944,0,59,90],"balrog":[0.273,15.2,16,32],"geobench":[2798,14,24,28]}},"mistral-medium-2604":{"bs":{"critpt":[0,0,115,121],"proofbench":[0.09,9.1,53,64],"scicode":[0.3958,52.9,72,112],"frontiercode":[0.08,0,31,31],"alebench":[763.98,28.6,59,102],"weirdml":[0.4371,26.9,63,128],"surface_evolver":[0.2688,14.2,20,23],"webdev_arena":[1265.04,18.5,82,94]}},"llama-3-1-405b-instruct":{"bs":{"gpqa":[0.5092,39.3,133,205],"simplebench":[0.23,0,72,82],"forecastbench":[59.9,68.7,33,75],"aime":[0.0972,7.5,138,186],"math_l5":[0.4977,6.9,49,90],"tac":[0.141,0,9,14],"cybench":[0.075,0,20,21],"weirdml":[0.2138,0,113,128]}},"claude-3-haiku":{"bs":{"gpqa":[0.363,19,171,205],"forecastbench":[53.2,0,72,75],"aime":[0.0181,0,174,186],"math_l5":[0.1488,0,77,90],"weirdml":[0.0984,0,123,128],"cad_eval":[0.12,0,15,15]},"ar":{"text_style_control":[1261,117701,303,48.5],"vision_style_control":[1000,13380,141,11.4]}},"llama-3-3-70b-instruct":{"bs":{"gpqa":[0.4744,34.4,143,205],"simplebench":[0.199,0,77,82],"critpt":[0,0,116,121],"forecastbench":[58.6,49.3,47,75],"aime":[0.0514,2.8,155,186],"math_l5":[0.416,0,56,90],"scicode":[0.2604,19.9,102,112],"livebench":[50.16,18.7,26,48],"balrog":[0.23,3.3,17,32],"weirdml":[0.1444,0,118,128]},"ar":{"text_style_control":[1318,54412,250,61]}},"llama-4-maverick-17b-128e-instruct":{"bs":{"hle":[0.0568,1.3,35,43],"arc_agi_2":[0,0,79,82],"arc_agi":[0.0438,2.2,81,84],"simplebench":[0.277,6.8,65,82],"enigma":[0.0058,0,41,42],"critpt":[0,0,117,121],"scicode":[0.331,37.1,93,112],"aider":[15.6,9.7,49,56],"weirdml":[0.2447,0,110,128],"geobench":[3069,29.9,22,28],"spatialviz":[0.3178,0,8,8],"fiction120k":[0.364,19.9,35,40],"lech_writing":[6.2,1.6,42,45]},"ar":{"text_style_control":[1327,39359,236,63],"vision_style_control":[1145,6937,107,54.3]}},"claude-3-5-haiku":{"bs":{"gpqa":[0.3813,21.5,166,205],"critpt":[0,0,118,121],"frontiermath":[0.0034,0,68,71],"aime":[0.0431,2,160,186],"math_l5":[0.4636,0.3,52,90],"scicode":[0.2743,23.3,99,112],"aider":[28,25.7,40,56],"livebench":[43.45,1,36,48],"balrog":[0.193,0,20,32],"weirdml":[0.3073,7.2,105,128],"geobench":[2507,0,26,28],"cad_eval":[0.32,27.5,10,15],"lech_writing":[7.35,49.2,32,45]},"ar":{"text_style_control":[1324,68964,239,62.5],"vision_style_control":[1127,1400,114,48.9]}},"gpt-4-1-nano":{"bs":{"gpqa":[0.4893,36.5,138,205],"arc_agi_2":[0,0,80,82],"arc_agi":[0,0,84,84],"simpleqa":[0.06,0,72,72],"critpt":[0,0,119,121],"frontiermath":[0.0103,1.2,63,71],"aime":[0.2889,27.2,126,186],"math_l5":[0.7,46,34,90],"scicode":[0.2593,19.6,104,112],"aider":[8.9,1,54,56],"weirdml":[0.1898,0,115,128],"fiction120k":[0.188,0,40,40]},"ar":{"text_style_control":[1322,6103,243,62],"vision_style_control":[1089,1211,124,37.6]}},"llama-3-1-8b-instruct":{"bs":{"gpqa":[0.2696,6,192,205],"critpt":[0,0,120,121],"chess":[0,0,137,138],"aime":[0.0167,0,175,186],"math_l5":[0.2288,0,69,90],"scicode":[0.1319,0,111,112],"balrog":[0.151,0,25,32],"weirdml":[0.0173,0,128,128]},"ar":{"text_style_control":[1211,49605,329,37.3]}},"claude-3-opus":{"bs":{"gpqa":[0.4716,34.1,146,205],"simpleqa":[0.126,2.8,67,72],"simplebench":[0.235,0,71,82],"enigma":[0.0082,0.6,37,42],"forecastbench":[58.4,46.3,50,75],"chess":[0.05,7.9,98,138],"aime":[0.0472,2.4,156,186],"math_l5":[0.3748,0,61,90],"livebench":[49.16,16,28,48],"metr":[0.2948,0,32,35],"cybench":[0.1,0,17,21],"weirdml":[0.1922,0,114,128]},"ar":{"text_style_control":[1322,194909,244,61.9],"vision_style_control":[1062,15565,129,29.7]}},"gpt-4o":{"bs":{"gpqa":[0.4921,36.9,134,205],"hle":[0.0272,0,43,43],"arc_agi_2":[0,0,81,82],"arc_agi":[0.045,2.3,80,84],"simpleqa":[0.26,24.6,56,72],"simplebench":[0.178,0,80,82],"enigma":[0.008,0.5,38,42],"critpt":[0,0,121,121],"forecastbench":[57.7,35.8,56,75],"chess":[0.13,20.6,75,138],"frontiermath":[0.0034,0,69,71],"aime":[0.0639,4.1,151,186],"math_l5":[0.5328,13.7,46,90],"swebench":[0.3099,0,32,32],"gso":[0,0,28,28],"aider":[23.1,19.4,42,56],"livebench":[55.33,32.3,19,48],"apex_agents":[0.054,0,53,53],"metr":[0.4076,16.4,27,35],"tac":[0.167,0,8,14],"gdpval":[0.099,0,11,11],"balrog":[0.323,29.1,11,32],"cybench":[0.125,0,14,21],"weirdml":[0.2512,0,108,128],"video_mme":[0.719,53.6,6,48],"vpct":[0.4,14.7,16,27],"geobench":[3696,66.6,16,28],"cad_eval":[0.26,16.8,12,15],"lech_writing":[8.18,83.6,13,45]},"ar":{"text_style_control":[1346,112881,212,67.3],"vision_style_control":[1162,23273,95,59.3]}},"gpt-4o-mini":{"bs":{"gpqa":[0.3772,20.9,168,205],"arc_agi_2":[0,0,82,82],"simpleqa":[0.083,0,71,72],"simplebench":[0.107,0,82,82],"chess":[0,0,138,138],"aime":[0.0694,4.7,147,186],"math_l5":[0.5263,12.5,47,90],"aider":[3.6,0,56,56],"livebench":[41.26,0,39,48],"balrog":[0.174,0,22,32],"weirdml":[0.1176,0,120,128],"video_mme":[0.648,5.4,19,48],"vpct":[0.34,4,25,27],"geobench":[3401,49.4,19,28],"lech_writing":[6.72,23.1,38,45]},"ar":{"text_style_control":[1318,68697,251,61],"vision_style_control":[1098,17341,122,40.2]}}}