diff --git "a/data/benchmarks.json" "b/data/benchmarks.json" --- "a/data/benchmarks.json" +++ "b/data/benchmarks.json" @@ -19,8 +19,8 @@ "arena_rank": "arena", "arena_votes": "arena" }, - "arena_elo": 1288.33, - "arena_rank": 214, + "arena_elo": 1288.23, + "arena_rank": 216, "arena_votes": 8662 }, { @@ -43,8 +43,8 @@ "arena_rank": "arena", "arena_votes": "arena" }, - "arena_elo": 1238.49, - "arena_rank": 246, + "arena_elo": 1238.42, + "arena_rank": 248, "arena_votes": 8858 }, { @@ -158,9 +158,9 @@ "lb_language": 0.39707333333333333, "lb_if": 0.6187925, "lb_data_analysis": 0.5411900000000001, - "arena_elo": 1322.62, - "arena_rank": 180, - "arena_votes": 70241, + "arena_elo": 1322.52, + "arena_rank": 182, + "arena_votes": 70240, "aider_pass_rate": 0.617 }, { @@ -197,8 +197,8 @@ "lb_language": 0.56937, "lb_if": 0.7229999999999999, "lb_data_analysis": 0.5411, - "arena_elo": 1341.53, - "arena_rank": 157, + "arena_elo": 1341.4, + "arena_rank": 160, "arena_votes": 82419, "aider_pass_rate": 0.5710000000000001 }, @@ -239,9 +239,9 @@ "lb_language": 0.54477, "lb_if": 0.69296, "lb_data_analysis": 0.5618650000000001, - "arena_elo": 1371.58, - "arena_rank": 123, - "arena_votes": 88515, + "arena_elo": 1371.51, + "arena_rank": 125, + "arena_votes": 88518, "aider_pass_rate": 0.6920000000000001 }, { @@ -279,8 +279,8 @@ "lb_language": 0.30073333333333335, "lb_if": 0.6402924999999999, "lb_data_analysis": 0.3731, - "arena_elo": 1260.1, - "arena_rank": 238, + "arena_elo": 1259.95, + "arena_rank": 241, "arena_votes": 117701, "aider_pass_rate": 0.406 }, @@ -320,8 +320,8 @@ "lb_language": 0.53574, "lb_if": 0.6388750000000001, "lb_data_analysis": 0.5784, - "arena_elo": 1320.92, - "arena_rank": 183, + "arena_elo": 1320.76, + "arena_rank": 186, "arena_votes": 194909, "aider_pass_rate": 0.534 }, @@ -361,8 +361,8 @@ "lb_language": 0.38083333333333336, "lb_if": 0.6500425, "lb_data_analysis": 0.38839999999999997, - "arena_elo": 1280.04, - "arena_rank": 223, + "arena_elo": 1279.88, + "arena_rank": 225, "arena_votes": 109284, "aider_pass_rate": 0.436 }, @@ -394,8 +394,8 @@ "lb_language": 0.14644333333333334, "lb_if": 0.571625, "lb_data_analysis": 0.2354, - "arena_elo": 1225.94, - "arena_rank": 254, + "arena_elo": 1225.73, + "arena_rank": 256, "arena_votes": 54036 }, { @@ -430,8 +430,8 @@ "lb_language": 0.5477066666666667, "lb_if": 0.8050825, "lb_data_analysis": 0.69625, - "arena_elo": 1397.55, - "arena_rank": 95, + "arena_elo": 1397.5, + "arena_rank": 96, "arena_votes": 18524 }, { @@ -464,8 +464,8 @@ "lb_language": 0.3518266666666667, "lb_if": 0.6915024999999999, "lb_data_analysis": 0.4417, - "arena_elo": 1306.73, - "arena_rank": 201, + "arena_elo": 1306.63, + "arena_rank": 203, "arena_votes": 24572, "aider_pass_rate": 0.5489999999999999 }, @@ -499,8 +499,8 @@ "lb_language": 0.47484666666666664, "lb_if": 0.75246, "lb_data_analysis": 0.6241, - "arena_elo": 1358.25, - "arena_rank": 134, + "arena_elo": 1358.15, + "arena_rank": 136, "arena_votes": 21770 }, { @@ -659,8 +659,8 @@ "lb_language": 0.32621666666666665, "lb_if": 0.5810025000000001, "lb_data_analysis": 0.4481, - "arena_elo": 1287.66, - "arena_rank": 215, + "arena_elo": 1287.64, + "arena_rank": 217, "arena_votes": 75754 }, { @@ -703,8 +703,8 @@ "lb_language": 0.25531, "lb_if": 0.52621, "lb_data_analysis": 0.2959, - "arena_elo": 1265.13, - "arena_rank": 234, + "arena_elo": 1265.11, + "arena_rank": 236, "arena_votes": 54611 }, { @@ -775,8 +775,8 @@ "hf_math_lvl5": 0.3806646525679758, "hf_musr": 0.45806250000000004, "hf_avg": 43.409948245645786, - "arena_elo": 1292.9, - "arena_rank": 212, + "arena_elo": 1292.81, + "arena_rank": 214, "arena_votes": 55240, "aider_pass_rate": 0.436 }, @@ -824,8 +824,8 @@ "hf_math_lvl5": 0.1729607250755287, "hf_musr": 0.3845416666666666, "hf_avg": 28.01011138792457, - "arena_elo": 1211.13, - "arena_rank": 264, + "arena_elo": 1211.03, + "arena_rank": 266, "arena_votes": 49605, "aider_pass_rate": 0.263 }, @@ -884,8 +884,8 @@ "hf_math_lvl5": 0.17673716012084592, "hf_musr": 0.3528541666666667, "hf_avg": 24.204650807793456, - "arena_elo": 1165.84, - "arena_rank": 290, + "arena_elo": 1165.69, + "arena_rank": 292, "arena_votes": 7936 }, { @@ -940,9 +940,9 @@ "hf_math_lvl5": 0.48338368580060426, "hf_musr": 0.44612500000000005, "hf_avg": 44.84747145129876, - "arena_elo": 1318.16, - "arena_rank": 187, - "arena_votes": 54886, + "arena_elo": 1317.94, + "arena_rank": 190, + "arena_votes": 54888, "aider_pass_rate": 0.42100000000000004 }, { @@ -1065,8 +1065,8 @@ "lb_language": 0.29333666666666663, "lb_if": 0.5838349999999999, "lb_data_analysis": 0.4376, - "arena_elo": 1255.56, - "arena_rank": 241, + "arena_elo": 1255.46, + "arena_rank": 243, "arena_votes": 24126 }, { @@ -1241,8 +1241,8 @@ "lb_language": 0.31805, "lb_if": 0.6957099999999999, "lb_data_analysis": 0.33599999999999997, - "arena_elo": 1298.49, - "arena_rank": 210, + "arena_elo": 1298.46, + "arena_rank": 212, "arena_votes": 7140 }, { @@ -1277,8 +1277,8 @@ "lb_language": 0.2421633333333333, "lb_if": 0.604665, "lb_data_analysis": 0.3682, - "arena_elo": 1223.07, - "arena_rank": 256, + "arena_elo": 1222.91, + "arena_rank": 258, "arena_votes": 66207, "aider_pass_rate": 0.414 }, @@ -1315,8 +1315,8 @@ "lb_language": 0.4956833333333333, "lb_if": 0.717875, "lb_data_analysis": 0.39039999999999997, - "arena_elo": 1274.14, - "arena_rank": 228, + "arena_elo": 1273.97, + "arena_rank": 230, "arena_votes": 88723, "aider_pass_rate": 0.466 }, @@ -1350,8 +1350,8 @@ "lb_language": 0.45262, "lb_if": 0.713875, "lb_data_analysis": 0.4998, - "arena_elo": 1323.58, - "arena_rank": 177, + "arena_elo": 1323.44, + "arena_rank": 179, "arena_votes": 98114 }, { @@ -1386,8 +1386,8 @@ "lb_language": 0.5393533333333334, "lb_if": 0.7217100000000001, "lb_data_analysis": 0.4661, - "arena_elo": 1345.24, - "arena_rank": 154, + "arena_elo": 1345.13, + "arena_rank": 156, "arena_votes": 112881, "aider_pass_rate": 0.602 }, @@ -1420,8 +1420,8 @@ "lb_language": 0.4563466666666667, "lb_if": 0.6858299999999999, "lb_data_analysis": 0.6236999999999999, - "arena_elo": 1334.45, - "arena_rank": 165, + "arena_elo": 1334.34, + "arena_rank": 167, "arena_votes": 45499, "aider_pass_rate": 0.5710000000000001 }, @@ -1459,8 +1459,8 @@ "lb_language": 0.29879333333333336, "lb_if": 0.5679974999999999, "lb_data_analysis": 0.55099, - "arena_elo": 1317.32, - "arena_rank": 192, + "arena_elo": 1317.22, + "arena_rank": 194, "arena_votes": 68718, "aider_pass_rate": 0.406 }, @@ -1504,8 +1504,8 @@ "hf_math_lvl5": 0.37462235649546827, "hf_musr": 0.41384375, "hf_avg": 27.639223265636087, - "arena_elo": 1401.61, - "arena_rank": 90, + "arena_elo": 1401.5, + "arena_rank": 91, "arena_votes": 27807, "aider_pass_rate": 0.654 }, @@ -1528,8 +1528,8 @@ "arena_votes": "arena", "aider_pass_rate": "aider" }, - "arena_elo": 1336.66, - "arena_rank": 161, + "arena_elo": 1336.61, + "arena_rank": 163, "arena_votes": 51981, "aider_pass_rate": 0.5 }, @@ -1552,8 +1552,8 @@ "arena_votes": "arena", "aider_pass_rate": "aider" }, - "arena_elo": 1387.74, - "arena_rank": 106, + "arena_elo": 1387.68, + "arena_rank": 108, "arena_votes": 31122, "aider_pass_rate": 0.579 }, @@ -1583,9 +1583,9 @@ "arena_rank": "arena", "arena_votes": "arena" }, - "arena_elo": 1347.47, - "arena_rank": 146, - "arena_votes": 57581 + "arena_elo": 1347.43, + "arena_rank": 148, + "arena_votes": 57572 }, { "slug": "openai/o3", @@ -1712,8 +1712,8 @@ "lb_language": 0.38114999999999993, "lb_if": 0.7550025, "lb_data_analysis": 0.4718, - "arena_elo": 1302.44, - "arena_rank": 209, + "arena_elo": 1302.33, + "arena_rank": 211, "arena_votes": 39406 }, { @@ -1788,8 +1788,8 @@ "lb_language": 0.23245333333333332, "lb_if": 0.5869175, "lb_data_analysis": 0.48810000000000003, - "arena_elo": 1270.06, - "arena_rank": 232, + "arena_elo": 1269.93, + "arena_rank": 234, "arena_votes": 5432, "aider_pass_rate": 0.594 }, @@ -1873,8 +1873,8 @@ "lb_language": 0.29213666666666666, "lb_if": 0.68271, "lb_data_analysis": 0.1636, - "arena_elo": 1260.93, - "arena_rank": 237, + "arena_elo": 1260.75, + "arena_rank": 239, "arena_votes": 37325, "aider_pass_rate": 0.444 }, @@ -1971,8 +1971,8 @@ "lb_language": 0.21091000000000001, "lb_if": 0.35587499999999994, "lb_data_analysis": 0.25925, - "arena_elo": 1156.05, - "arena_rank": 292, + "arena_elo": 1155.82, + "arena_rank": 294, "arena_votes": 3231 }, { @@ -2151,8 +2151,8 @@ "hf_math_lvl5": 0.277190332326284, "hf_musr": 0.4281979166666667, "hf_avg": 33.35799367075618, - "arena_elo": 1212.58, - "arena_rank": 262, + "arena_elo": 1212.41, + "arena_rank": 264, "arena_votes": 24146 }, { @@ -2379,8 +2379,8 @@ "hf_math_lvl5": 0.06268882175226587, "hf_musr": 0.39784375, "hf_avg": 24.226662652803373, - "arena_elo": 1182.9, - "arena_rank": 276, + "arena_elo": 1182.73, + "arena_rank": 278, "arena_votes": 15483 }, { @@ -2901,8 +2901,8 @@ "hf_math_lvl5": 0.03851963746223565, "hf_musr": 0.47709375000000004, "hf_avg": 14.343669671742774, - "arena_elo": 1222.37, - "arena_rank": 257, + "arena_elo": 1222.25, + "arena_rank": 260, "arena_votes": 104642 }, { @@ -11089,8 +11089,8 @@ "lb_language": 0.07196666666666666, "lb_if": 0.5279175, "lb_data_analysis": 0.081, - "arena_elo": 1125.86, - "arena_rank": 313, + "arena_elo": 1125.65, + "arena_rank": 315, "arena_votes": 1785 }, { @@ -11125,8 +11125,8 @@ "lb_language": 0.042846666666666665, "lb_if": 0.48317, "lb_data_analysis": 0.0762, - "arena_elo": 1129.99, - "arena_rank": 309, + "arena_elo": 1129.78, + "arena_rank": 311, "arena_votes": 11118 }, { @@ -11177,8 +11177,8 @@ "hf_math_lvl5": 0.20468277945619334, "hf_musr": 0.4465208333333333, "hf_avg": 34.125963384670946, - "arena_elo": 1211.75, - "arena_rank": 263, + "arena_elo": 1211.56, + "arena_rank": 265, "arena_votes": 4652 }, { @@ -11361,8 +11361,8 @@ "hf_math_lvl5": 0.0581570996978852, "hf_musr": 0.342125, "hf_avg": 15.02227766709556, - "arena_elo": 1113.36, - "arena_rank": 318, + "arena_elo": 1113.18, + "arena_rank": 320, "arena_votes": 2199 }, { @@ -18389,8 +18389,8 @@ "hf_math_lvl5": 0.12235649546827794, "hf_musr": 0.4595416666666667, "hf_avg": 27.353190438571634, - "arena_elo": 1163.73, - "arena_rank": 291, + "arena_elo": 1163.53, + "arena_rank": 293, "arena_votes": 3777 }, { @@ -20307,9 +20307,9 @@ "lb_language": 0.5148133333333332, "lb_if": 0.81829, "lb_data_analysis": 0.69529, - "arena_elo": 1335.63, - "arena_rank": 163, - "arena_votes": 25526 + "arena_elo": 1335.65, + "arena_rank": 165, + "arena_votes": 25522 }, { "hf_id": "Qwen/Qwen1.5-0.5B", @@ -20466,8 +20466,8 @@ "lb_language": 0.13224333333333332, "lb_if": 0.5526275, "lb_data_analysis": 0.20179999999999998, - "arena_elo": 1233.18, - "arena_rank": 249, + "arena_elo": 1233.01, + "arena_rank": 251, "arena_votes": 26195, "aider_pass_rate": 0.308 }, @@ -20519,8 +20519,8 @@ "hf_math_lvl5": 0.15256797583081572, "hf_musr": 0.43997916666666664, "hf_avg": 23.566106475051374, - "arena_elo": 1189.97, - "arena_rank": 273, + "arena_elo": 1189.79, + "arena_rank": 275, "arena_votes": 17839 }, { @@ -20571,8 +20571,8 @@ "hf_math_lvl5": 0.19561933534743203, "hf_musr": 0.4159791666666666, "hf_avg": 29.25746822860332, - "arena_elo": 1202.86, - "arena_rank": 266, + "arena_elo": 1202.67, + "arena_rank": 268, "arena_votes": 21741 }, { @@ -20629,8 +20629,8 @@ "lb_language": 0.05798333333333333, "lb_if": 0.27749999999999997, "lb_data_analysis": 0.0469, - "arena_elo": 1089.14, - "arena_rank": 323, + "arena_elo": 1088.95, + "arena_rank": 325, "arena_votes": 7597 }, { @@ -20687,8 +20687,8 @@ "lb_language": 0.061816666666666666, "lb_if": 0.4411675, "lb_data_analysis": 0.0435, - "arena_elo": 1142.81, - "arena_rank": 301, + "arena_elo": 1142.64, + "arena_rank": 303, "arena_votes": 4737 }, { @@ -30289,8 +30289,8 @@ "hf_math_lvl5": 0.4501510574018127, "hf_musr": 0.4948333333333334, "hf_avg": 42.33178738532094, - "arena_elo": 1285.95, - "arena_rank": 219, + "arena_elo": 1285.81, + "arena_rank": 221, "arena_votes": 2846 }, { @@ -30385,8 +30385,8 @@ "hf_math_lvl5": 0.19637462235649547, "hf_musr": 0.41746875, "hf_avg": 26.034998081672143, - "arena_elo": 1220.48, - "arena_rank": 261, + "arena_elo": 1220.35, + "arena_rank": 263, "arena_votes": 2896 }, { @@ -33947,8 +33947,8 @@ "hf_math_lvl5": 0.08383685800604229, "hf_musr": 0.41201041666666666, "hf_avg": 20.83936104726783, - "arena_elo": 1166.52, - "arena_rank": 289, + "arena_elo": 1166.32, + "arena_rank": 291, "arena_votes": 10224 }, { @@ -35729,8 +35729,8 @@ "hf_math_lvl5": 0.013595166163141994, "hf_musr": 0.37390625000000005, "hf_avg": 6.3704357034963754, - "arena_elo": 979.06, - "arena_rank": 335, + "arena_elo": 978.92, + "arena_rank": 337, "arena_votes": 3412 }, { @@ -35995,8 +35995,8 @@ "hf_math_lvl5": 0.09290030211480363, "hf_musr": 0.5058645833333334, "hf_avg": 27.310631874736753, - "arena_elo": 1183.38, - "arena_rank": 275, + "arena_elo": 1183.18, + "arena_rank": 277, "arena_votes": 4932 }, { @@ -38707,8 +38707,8 @@ "hf_math_lvl5": 0.01812688821752266, "hf_musr": 0.33939583333333334, "hf_avg": 8.053373854341979, - "arena_elo": 1113.59, - "arena_rank": 317, + "arena_elo": 1113.58, + "arena_rank": 318, "arena_votes": 10854 }, { @@ -38743,8 +38743,8 @@ "lb_language": 0.10647333333333332, "lb_if": 0.443375, "lb_data_analysis": 0.0726, - "arena_elo": 1179.72, - "arena_rank": 280, + "arena_elo": 1179.71, + "arena_rank": 282, "arena_votes": 23893 }, { @@ -38817,8 +38817,8 @@ "hf_math_lvl5": 0.0007552870090634441, "hf_musr": 0.39288541666666665, "hf_avg": 17.046939294966545, - "arena_elo": 1198.58, - "arena_rank": 268, + "arena_elo": 1198.6, + "arena_rank": 270, "arena_votes": 46616 }, { @@ -38913,8 +38913,8 @@ "hf_math_lvl5": 0.02039274924471299, "hf_musr": 0.334125, "hf_avg": 7.485804130315127, - "arena_elo": 1091, - "arena_rank": 322, + "arena_elo": 1090.95, + "arena_rank": 324, "arena_votes": 4780 }, { @@ -38965,8 +38965,8 @@ "hf_math_lvl5": 0.02945619335347432, "hf_musr": 0.42742708333333335, "hf_avg": 13.067087110466217, - "arena_elo": 1135.41, - "arena_rank": 308, + "arena_elo": 1135.36, + "arena_rank": 309, "arena_votes": 8925 }, { @@ -40809,8 +40809,8 @@ "hf_math_lvl5": 0.02039274924471299, "hf_musr": 0.34621875, "hf_avg": 9.39218439885523, - "arena_elo": 971.17, - "arena_rank": 336, + "arena_elo": 971.065, + "arena_rank": 338, "arena_votes": 2391 }, { @@ -41389,8 +41389,8 @@ "hf_math_lvl5": 0.09214501510574018, "hf_musr": 0.35148958333333336, "hf_avg": 18.396095114284222, - "arena_elo": 1155.08, - "arena_rank": 293, + "arena_elo": 1154.91, + "arena_rank": 295, "arena_votes": 6837 }, { @@ -41485,8 +41485,8 @@ "hf_math_lvl5": 0.1419939577039275, "hf_musr": 0.3900625, "hf_avg": 24.027678753483297, - "arena_elo": 1181.1, - "arena_rank": 279, + "arena_elo": 1180.95, + "arena_rank": 281, "arena_votes": 6638 }, { @@ -41581,8 +41581,8 @@ "hf_math_lvl5": 0.15256797583081572, "hf_musr": 0.3605416666666667, "hf_avg": 21.712212822028288, - "arena_elo": 1178.07, - "arena_rank": 282, + "arena_elo": 1177.91, + "arena_rank": 284, "arena_votes": 3188 }, { @@ -41677,8 +41677,8 @@ "hf_math_lvl5": 0.21978851963746224, "hf_musr": 0.47070833333333334, "hf_avg": 30.6030430081627, - "arena_elo": 1207.52, - "arena_rank": 265, + "arena_elo": 1207.34, + "arena_rank": 267, "arena_votes": 3090 }, { @@ -42539,8 +42539,8 @@ "hf_math_lvl5": 0.4078549848942598, "hf_musr": 0.4558229166666667, "hf_avg": 38.87959582082076, - "arena_elo": 1190.58, - "arena_rank": 272, + "arena_elo": 1190.43, + "arena_rank": 274, "arena_votes": 9901 }, { @@ -46597,8 +46597,8 @@ "hf_math_lvl5": 0.0702416918429003, "hf_musr": 0.3328541666666667, "hf_avg": 14.443126333711135, - "arena_elo": 1110.39, - "arena_rank": 319, + "arena_elo": 1110.22, + "arena_rank": 321, "arena_votes": 8045 }, { @@ -46897,8 +46897,8 @@ "lb_language": 0.13909000000000002, "lb_if": 0.5330400000000001, "lb_data_analysis": 0.2044, - "arena_elo": 1196.99, - "arena_rank": 269, + "arena_elo": 1196.8, + "arena_rank": 271, "arena_votes": 25055 }, { @@ -46933,8 +46933,8 @@ "lb_language": 0.09153666666666667, "lb_if": 0.39083500000000004, "lb_data_analysis": 0.26030000000000003, - "arena_elo": 1128.21, - "arena_rank": 310, + "arena_elo": 1128.03, + "arena_rank": 312, "arena_votes": 20685 }, { @@ -46969,8 +46969,8 @@ "lb_language": 0.08559, "lb_if": 0.363625, "lb_data_analysis": 0.2232, - "arena_elo": 1127.42, - "arena_rank": 311, + "arena_elo": 1127.22, + "arena_rank": 313, "arena_votes": 20118 }, { @@ -47061,8 +47061,8 @@ "lb_language": 0.12944, "lb_if": 0.472, "lb_data_analysis": 0.2343, - "arena_elo": 1170.13, - "arena_rank": 287, + "arena_elo": 1169.94, + "arena_rank": 289, "arena_votes": 17766 }, { @@ -47513,8 +47513,8 @@ "lb_language": 0.09055, "lb_if": 0.5165025, "lb_data_analysis": 0.059300000000000005, - "arena_elo": 1148.57, - "arena_rank": 298, + "arena_elo": 1148.37, + "arena_rank": 300, "arena_votes": 19402 }, { @@ -47731,8 +47731,8 @@ "lb_language": 0.26477666666666666, "lb_if": 0.63167, "lb_data_analysis": 0.255, - "arena_elo": 1228.45, - "arena_rank": 253, + "arena_elo": 1228.25, + "arena_rank": 255, "arena_votes": 51416 }, { @@ -47789,8 +47789,8 @@ "lb_language": 0.13761333333333334, "lb_if": 0.4480825, "lb_data_analysis": 0.1619, - "arena_elo": 1196.14, - "arena_rank": 270, + "arena_elo": 1195.93, + "arena_rank": 272, "arena_votes": 73503 }, { @@ -52059,8 +52059,8 @@ "hf_math_lvl5": 0.07628398791540786, "hf_musr": 0.42543749999999997, "hf_avg": 22.70925524673515, - "arena_elo": 1181.25, - "arena_rank": 277, + "arena_elo": 1181.06, + "arena_rank": 279, "arena_votes": 12637 }, { @@ -52133,8 +52133,8 @@ "hf_math_lvl5": 0.07250755287009064, "hf_musr": 0.4228645833333333, "hf_avg": 21.635827111564595, - "arena_elo": 1181.19, - "arena_rank": 278, + "arena_elo": 1181.01, + "arena_rank": 280, "arena_votes": 7968 }, { @@ -54251,8 +54251,8 @@ "hf_math_lvl5": 0.07099697885196375, "hf_musr": 0.41232291666666665, "hf_avg": 22.3449346084354, - "arena_elo": 1278.92, - "arena_rank": 224, + "arena_elo": 1278.88, + "arena_rank": 226, "arena_votes": 10072 }, { @@ -60655,8 +60655,8 @@ "lb_language": 0.11368333333333334, "lb_if": 0.52779, "lb_data_analysis": 0.1738, - "arena_elo": 1174.16, - "arena_rank": 284, + "arena_elo": 1173.98, + "arena_rank": 286, "arena_votes": 5006 }, { @@ -62583,8 +62583,8 @@ "hf_math_lvl5": 0.05664652567975831, "hf_musr": 0.3899375, "hf_avg": 20.57236409322395, - "arena_elo": 1151.32, - "arena_rank": 295, + "arena_elo": 1151.11, + "arena_rank": 297, "arena_votes": 4155 }, { @@ -65183,8 +65183,8 @@ "arena_rank": "arena", "arena_votes": "arena" }, - "arena_elo": 1249.27, - "arena_rank": 243, + "arena_elo": 1249.1, + "arena_rank": 245, "arena_votes": 10140 }, { @@ -65211,8 +65211,8 @@ "arena_votes": "arena", "aider_pass_rate": "aider" }, - "arena_elo": 1260.96, - "arena_rank": 236, + "arena_elo": 1260.76, + "arena_rank": 238, "arena_votes": 77554, "aider_pass_rate": 0.218 }, @@ -65241,8 +65241,8 @@ "arena_rank": "arena", "arena_votes": "arena" }, - "arena_elo": 1275.67, - "arena_rank": 226, + "arena_elo": 1275.51, + "arena_rank": 228, "arena_votes": 9866 }, { @@ -65268,8 +65268,8 @@ "arena_rank": "arena", "arena_votes": "arena" }, - "arena_elo": 1263.56, - "arena_rank": 235, + "arena_elo": 1263.45, + "arena_rank": 237, "arena_votes": 15147 }, { @@ -65473,8 +65473,8 @@ "arena_votes": "arena", "aider_pass_rate": "aider" }, - "arena_elo": 1312.51, - "arena_rank": 196, + "arena_elo": 1312.35, + "arena_rank": 198, "arena_votes": 93439, "aider_pass_rate": 0.556 }, @@ -65577,8 +65577,8 @@ "arena_rank": "arena", "arena_votes": "arena" }, - "arena_elo": 1241.41, - "arena_rank": 244, + "arena_elo": 1241.21, + "arena_rank": 246, "arena_votes": 62436 }, { @@ -65604,8 +65604,8 @@ "arena_rank": "arena", "arena_votes": "arena" }, - "arena_elo": 1313.48, - "arena_rank": 195, + "arena_elo": 1313.36, + "arena_rank": 197, "arena_votes": 45459 }, { @@ -65669,8 +65669,8 @@ "arena_rank": "arena", "arena_votes": "arena" }, - "arena_elo": 1232.23, - "arena_rank": 252, + "arena_elo": 1232.06, + "arena_rank": 254, "arena_votes": 39302 }, { @@ -65715,8 +65715,8 @@ "arena_rank": "arena", "arena_votes": "arena" }, - "arena_elo": 1170.66, - "arena_rank": 286, + "arena_elo": 1170.47, + "arena_rank": 288, "arena_votes": 16056 }, { @@ -65824,8 +65824,8 @@ "arena_rank": "arena", "arena_votes": "arena" }, - "arena_elo": 1309.19, - "arena_rank": 199, + "arena_elo": 1309.09, + "arena_rank": 201, "arena_votes": 34902 }, { @@ -65852,8 +65852,8 @@ "arena_votes": "arena", "aider_pass_rate": "aider" }, - "arena_elo": 1350.73, - "arena_rank": 143, + "arena_elo": 1350.65, + "arena_rank": 144, "arena_votes": 55606, "aider_pass_rate": 0.496 }, @@ -66149,8 +66149,8 @@ "arena_rank": "arena", "arena_votes": "arena" }, - "arena_elo": 1352.83, - "arena_rank": 141, + "arena_elo": 1352.8, + "arena_rank": 143, "arena_votes": 24955 }, { @@ -66316,8 +66316,8 @@ "arena_votes": "arena", "aider_pass_rate": "aider" }, - "arena_elo": 1304.78, - "arena_rank": 205, + "arena_elo": 1304.68, + "arena_rank": 207, "arena_votes": 28073, "aider_pass_rate": 0.466 }, @@ -66519,9 +66519,9 @@ "arena_rank": "arena", "arena_votes": "arena" }, - "arena_elo": 1374.26, - "arena_rank": 120, - "arena_votes": 32707 + "arena_elo": 1374.13, + "arena_rank": 123, + "arena_votes": 32710 }, { "name": "gpt-4.5-preview", @@ -66608,8 +66608,8 @@ "arena_votes": "arena" }, "arena_elo": 1365.11, - "arena_rank": 128, - "arena_votes": 47855 + "arena_rank": 130, + "arena_votes": 47852 }, { "name": "gemini-2.5-pro-exp-03-25", @@ -66655,9 +66655,9 @@ "arena_rank": "arena", "arena_votes": "arena" }, - "arena_elo": 1394.63, - "arena_rank": 99, - "arena_votes": 45802 + "arena_elo": 1394.59, + "arena_rank": 101, + "arena_votes": 45800 }, { "name": "chatgpt-4o-latest-2025-03-27", @@ -66745,9 +66745,9 @@ "arena_rank": "arena", "arena_votes": "arena" }, - "arena_elo": 1370.52, - "arena_rank": 124, - "arena_votes": 43398 + "arena_elo": 1370.36, + "arena_rank": 126, + "arena_votes": 43399 }, { "name": "command-a-03-2025", @@ -66774,9 +66774,9 @@ "arena_rank": "arena", "arena_votes": "arena" }, - "arena_elo": 1353.48, - "arena_rank": 139, - "arena_votes": 56677 + "arena_elo": 1353.31, + "arena_rank": 141, + "arena_votes": 56670 }, { "name": "gemini-1.5-flash-8b-001", @@ -66801,8 +66801,8 @@ "arena_rank": "arena", "arena_votes": "arena" }, - "arena_elo": 1258.23, - "arena_rank": 240, + "arena_elo": 1258.15, + "arena_rank": 242, "arena_votes": 35558 }, { @@ -66828,9 +66828,9 @@ "arena_rank": "arena", "arena_votes": "arena" }, - "arena_elo": 1359.9, - "arena_rank": 133, - "arena_votes": 43918 + "arena_elo": 1359.92, + "arena_rank": 135, + "arena_votes": 43913 }, { "name": "gemini-2.0-flash-lite-001", @@ -66876,8 +66876,8 @@ "arena_rank": "arena", "arena_votes": "arena" }, - "arena_elo": 1341.43, - "arena_rank": 158, + "arena_elo": 1341.41, + "arena_rank": 159, "arena_votes": 3829 }, { @@ -66903,8 +66903,8 @@ "arena_rank": "arena", "arena_votes": "arena" }, - "arena_elo": 1302.81, - "arena_rank": 208, + "arena_elo": 1302.8, + "arena_rank": 209, "arena_votes": 4171 }, { @@ -66932,8 +66932,8 @@ "arena_rank": "arena", "arena_votes": "arena" }, - "arena_elo": 1444.26, - "arena_rank": 35, + "arena_elo": 1444.16, + "arena_rank": 37, "arena_votes": 14547 }, { @@ -66959,9 +66959,9 @@ "arena_rank": "arena", "arena_votes": "arena" }, - "arena_elo": 1326.79, - "arena_rank": 174, - "arena_votes": 40211 + "arena_elo": 1326.67, + "arena_rank": 177, + "arena_votes": 40222 }, { "name": "grok-3-beta", @@ -67030,9 +67030,9 @@ "arena_rank": "arena", "arena_votes": "arena" }, - "arena_elo": 1413.13, - "arena_rank": 73, - "arena_votes": 51424 + "arena_elo": 1413.05, + "arena_rank": 75, + "arena_votes": 51411 }, { "name": "gpt-4.1-mini-2025-04-14", @@ -67059,9 +67059,9 @@ "arena_rank": "arena", "arena_votes": "arena" }, - "arena_elo": 1382.22, - "arena_rank": 115, - "arena_votes": 39550 + "arena_elo": 1382.1, + "arena_rank": 117, + "arena_votes": 39553 }, { "name": "gpt-4.1-nano-2025-04-14", @@ -67088,8 +67088,8 @@ "arena_rank": "arena", "arena_votes": "arena" }, - "arena_elo": 1321.53, - "arena_rank": 182, + "arena_elo": 1321.44, + "arena_rank": 184, "arena_votes": 6103 }, { @@ -67264,9 +67264,9 @@ "arena_rank": "arena", "arena_votes": "arena" }, - "arena_elo": 1421.72, - "arena_rank": 60, - "arena_votes": 18593 + "arena_elo": 1421.62, + "arena_rank": 62, + "arena_votes": 18595 }, { "name": "gemini-2.5-flash-preview-05-20", @@ -67398,9 +67398,9 @@ "arena_rank": "arena", "arena_votes": "arena" }, - "arena_elo": 1386.46, - "arena_rank": 111, - "arena_votes": 33444 + "arena_elo": 1386.25, + "arena_rank": 113, + "arena_votes": 33445 }, { "name": "phi-4-reasoning-plus", @@ -67469,9 +67469,9 @@ "arena_rank": "arena", "arena_votes": "arena" }, - "arena_elo": 1374.37, - "arena_rank": 119, - "arena_votes": 26431 + "arena_elo": 1374.43, + "arena_rank": 120, + "arena_votes": 26425 }, { "name": "qwen3-30b-a3b", @@ -67498,9 +67498,9 @@ "arena_rank": "arena", "arena_votes": "arena" }, - "arena_elo": 1327.6, - "arena_rank": 172, - "arena_votes": 26653 + "arena_elo": 1327.33, + "arena_rank": 175, + "arena_votes": 26648 }, { "name": "qwen3-32b", @@ -67527,8 +67527,8 @@ "arena_rank": "arena", "arena_votes": "arena" }, - "arena_elo": 1347.07, - "arena_rank": 148, + "arena_elo": 1347, + "arena_rank": 150, "arena_votes": 3926 }, { @@ -67577,9 +67577,9 @@ "arena_rank": "arena", "arena_votes": "arena" }, - "arena_elo": 1452.67, - "arena_rank": 25, - "arena_votes": 56199 + "arena_elo": 1451.28, + "arena_rank": 28, + "arena_votes": 58292 }, { "name": "deepseek-v3.1-terminus", @@ -67606,8 +67606,8 @@ "arena_rank": "arena", "arena_votes": "arena" }, - "arena_elo": 1415.82, - "arena_rank": 70, + "arena_elo": 1415.87, + "arena_rank": 71, "arena_votes": 3724 }, { @@ -67698,9 +67698,9 @@ "arena_rank": "arena", "arena_votes": "arena" }, - "arena_elo": 1405.12, - "arena_rank": 82, - "arena_votes": 33165 + "arena_elo": 1405, + "arena_rank": 83, + "arena_votes": 33139 }, { "name": "gemini-2.5-pro-06-05", @@ -67748,9 +67748,9 @@ "arena_rank": "arena", "arena_votes": "arena" }, - "arena_elo": 1411.13, - "arena_rank": 76, - "arena_votes": 24513 + "arena_elo": 1410.84, + "arena_rank": 79, + "arena_votes": 24514 }, { "name": "glm-4.5-air", @@ -67777,9 +67777,9 @@ "arena_rank": "arena", "arena_votes": "arena" }, - "arena_elo": 1372.78, - "arena_rank": 122, - "arena_votes": 31390 + "arena_elo": 1372.76, + "arena_rank": 124, + "arena_votes": 31387 }, { "name": "glm-4.6", @@ -67806,9 +67806,9 @@ "arena_rank": "arena", "arena_votes": "arena" }, - "arena_elo": 1425.94, - "arena_rank": 52, - "arena_votes": 35979 + "arena_elo": 1425.74, + "arena_rank": 54, + "arena_votes": 35917 }, { "name": "gpt-5", @@ -67877,9 +67877,9 @@ "arena_rank": "arena", "arena_votes": "arena" }, - "arena_elo": 1433.56, - "arena_rank": 45, - "arena_votes": 32246 + "arena_elo": 1433.35, + "arena_rank": 47, + "arena_votes": 32259 }, { "name": "gpt-5-low", @@ -67948,9 +67948,9 @@ "arena_rank": "arena", "arena_votes": "arena" }, - "arena_elo": 1389.6, - "arena_rank": 104, - "arena_votes": 27266 + "arena_elo": 1389.45, + "arena_rank": 106, + "arena_votes": 27256 }, { "name": "gpt-5-mini-low", @@ -68061,9 +68061,9 @@ "arena_rank": "arena", "arena_votes": "arena" }, - "arena_elo": 1336.54, - "arena_rank": 162, - "arena_votes": 8319 + "arena_elo": 1336.6, + "arena_rank": 164, + "arena_votes": 8320 }, { "name": "gpt-5-nano-low", @@ -68132,9 +68132,9 @@ "arena_rank": "arena", "arena_votes": "arena" }, - "arena_elo": 1426.16, - "arena_rank": 51, - "arena_votes": 31860 + "arena_elo": 1426.06, + "arena_rank": 53, + "arena_votes": 31851 }, { "name": "gpt-oss-120b", @@ -68161,9 +68161,9 @@ "arena_rank": "arena", "arena_votes": "arena" }, - "arena_elo": 1353.86, - "arena_rank": 138, - "arena_votes": 30920 + "arena_elo": 1353.77, + "arena_rank": 140, + "arena_votes": 30903 }, { "name": "grok-4-0709", @@ -68190,9 +68190,9 @@ "arena_rank": "arena", "arena_votes": "arena" }, - "arena_elo": 1410.27, - "arena_rank": 78, - "arena_votes": 41766 + "arena_elo": 1410.08, + "arena_rank": 80, + "arena_votes": 41742 }, { "name": "grok-code-fast-1-0825", @@ -68261,9 +68261,9 @@ "arena_rank": "arena", "arena_votes": "arena" }, - "arena_elo": 1422.26, + "arena_elo": 1422.95, "arena_rank": 59, - "arena_votes": 79772 + "arena_votes": 82043 }, { "name": "qwen3-235b-a22b-thinking-2507", @@ -68290,9 +68290,9 @@ "arena_rank": "arena", "arena_votes": "arena" }, - "arena_elo": 1399.73, - "arena_rank": 93, - "arena_votes": 9059 + "arena_elo": 1399.67, + "arena_rank": 94, + "arena_votes": 9061 }, { "name": "qwen3-coder-480b-a35b-instruct", @@ -68319,9 +68319,9 @@ "arena_rank": "arena", "arena_votes": "arena" }, - "arena_elo": 1387.24, + "arena_elo": 1387.36, "arena_rank": 109, - "arena_votes": 25975 + "arena_votes": 25962 }, { "name": "qwen3-max-2025-09-23", @@ -68348,9 +68348,9 @@ "arena_rank": "arena", "arena_votes": "arena" }, - "arena_elo": 1424.61, - "arena_rank": 54, - "arena_votes": 9239 + "arena_elo": 1424.31, + "arena_rank": 56, + "arena_votes": 9242 }, { "name": "qwen3-next-80b-a3b-instruct", @@ -68377,9 +68377,9 @@ "arena_rank": "arena", "arena_votes": "arena" }, - "arena_elo": 1401.72, - "arena_rank": 89, - "arena_votes": 23103 + "arena_elo": 1401.53, + "arena_rank": 90, + "arena_votes": 23076 }, { "name": "qwen3-next-80b-a3b", @@ -68406,9 +68406,9 @@ "arena_rank": "arena", "arena_votes": "arena" }, - "arena_elo": 1368.94, - "arena_rank": 125, - "arena_votes": 13836 + "arena_elo": 1369.03, + "arena_rank": 127, + "arena_votes": 13837 }, { "name": "claude-haiku-4-5-20251001", @@ -68435,9 +68435,9 @@ "arena_rank": "arena", "arena_votes": "arena" }, - "arena_elo": 1407.38, - "arena_rank": 80, - "arena_votes": 56977 + "arena_elo": 1407.68, + "arena_rank": 82, + "arena_votes": 59484 }, { "name": "deepseek-v3.2-exp", @@ -68464,9 +68464,9 @@ "arena_rank": "arena", "arena_votes": "arena" }, - "arena_elo": 1422.91, - "arena_rank": 57, - "arena_votes": 12028 + "arena_elo": 1422.77, + "arena_rank": 60, + "arena_votes": 12019 }, { "name": "minimax-m2", @@ -68493,9 +68493,9 @@ "arena_rank": "arena", "arena_votes": "arena" }, - "arena_elo": 1346.6, - "arena_rank": 151, - "arena_votes": 6920 + "arena_elo": 1346.39, + "arena_rank": 153, + "arena_votes": 6919 }, { "name": "kimi-k2", @@ -68732,9 +68732,9 @@ "arena_rank": "arena", "arena_votes": "arena" }, - "arena_elo": 1431.31, - "arena_rank": 47, - "arena_votes": 40189 + "arena_elo": 1431.68, + "arena_rank": 49, + "arena_votes": 42592 }, { "name": "claude-opus-4-5-20251101", @@ -68761,9 +68761,9 @@ "arena_rank": "arena", "arena_votes": "arena" }, - "arena_elo": 1468.26, - "arena_rank": 13, - "arena_votes": 44715 + "arena_elo": 1467.86, + "arena_rank": 15, + "arena_votes": 47320 }, { "name": "deepseek-v3.2", @@ -68790,9 +68790,9 @@ "arena_rank": "arena", "arena_votes": "arena" }, - "arena_elo": 1424.13, - "arena_rank": 55, - "arena_votes": 38958 + "arena_elo": 1423.8, + "arena_rank": 57, + "arena_votes": 41182 }, { "name": "deepseek-v3.2-speciale", @@ -68903,9 +68903,9 @@ "arena_rank": "arena", "arena_votes": "arena" }, - "arena_elo": 1378.02, - "arena_rank": 117, - "arena_votes": 2823 + "arena_elo": 1377.71, + "arena_rank": 119, + "arena_votes": 2816 }, { "name": "gpt-5.1-2025-11-13-low", @@ -69121,9 +69121,9 @@ "arena_rank": "arena", "arena_votes": "arena" }, - "arena_elo": 1443.02, - "arena_rank": 38, - "arena_votes": 12201 + "arena_elo": 1442.61, + "arena_rank": 39, + "arena_votes": 12180 }, { "name": "arcee-trinity-large-preview", @@ -69171,9 +69171,9 @@ "arena_rank": "arena", "arena_votes": "arena" }, - "arena_elo": 1498.99, + "arena_elo": 1495.6, "arena_rank": 2, - "arena_votes": 14934 + "arena_votes": 17416 }, { "name": "claude-sonnet-4-6", @@ -69200,9 +69200,9 @@ "arena_rank": "arena", "arena_votes": "arena" }, - "arena_elo": 1462.41, - "arena_rank": 18, - "arena_votes": 11082 + "arena_elo": 1461.73, + "arena_rank": 19, + "arena_votes": 10940 }, { "name": "gemini-3.1-pro-preview-high", @@ -69292,9 +69292,9 @@ "arena_rank": "arena", "arena_votes": "arena" }, - "arena_elo": 1455.9, - "arena_rank": 21, - "arena_votes": 12177 + "arena_elo": 1455.5, + "arena_rank": 24, + "arena_votes": 14093 }, { "name": "glm-5v-turbo", @@ -69317,6 +69317,35 @@ "lb_data_analysis": "livebench" } }, + { + "name": "glm-5.1", + "lb_name": "glm-5.1", + "lb_global": 0.7061917391304348, + "lb_reasoning": 0.72524, + "lb_coding": 0.63147, + "lb_math": 0.8489424999999999, + "lb_language": 0.7177899999999999, + "lb_if": 0.6845424999999999, + "lb_data_analysis": 0.6322633333333334, + "sources": { + "lb_name": "livebench", + "lb_global": "livebench", + "lb_reasoning": "livebench", + "lb_coding": "livebench", + "lb_math": "livebench", + "lb_language": "livebench", + "lb_if": "livebench", + "lb_data_analysis": "livebench", + "arena_name": "arena", + "arena_org": "arena", + "arena_elo": "arena", + "arena_rank": "arena", + "arena_votes": "arena" + }, + "arena_elo": 1470.88, + "arena_rank": 13, + "arena_votes": 5326 + }, { "name": "gpt-5.2-codex", "lb_name": "gpt-5.2-codex", @@ -69426,9 +69455,9 @@ "arena_rank": "arena", "arena_votes": "arena" }, - "arena_elo": 1484.42, - "arena_rank": 6, - "arena_votes": 7160 + "arena_elo": 1483.88, + "arena_rank": 7, + "arena_votes": 9681 }, { "name": "gpt-5.4-xhigh", @@ -69497,9 +69526,9 @@ "arena_rank": "arena", "arena_votes": "arena" }, - "arena_elo": 1455.46, + "arena_elo": 1458.77, "arena_rank": 22, - "arena_votes": 4514 + "arena_votes": 7169 }, { "name": "gpt-5.4-mini-low", @@ -69610,9 +69639,9 @@ "arena_rank": "arena", "arena_votes": "arena" }, - "arena_elo": 1404.12, - "arena_rank": 85, - "arena_votes": 3905 + "arena_elo": 1401.72, + "arena_rank": 89, + "arena_votes": 6553 }, { "name": "gpt-5.4-nano-low", @@ -69723,9 +69752,9 @@ "arena_rank": "arena", "arena_votes": "arena" }, - "arena_elo": 1481.2, - "arena_rank": 7, - "arena_votes": 7344 + "arena_elo": 1478.33, + "arena_rank": 8, + "arena_votes": 9781 }, { "name": "kimi-k2.5", @@ -69752,9 +69781,9 @@ "arena_rank": "arena", "arena_votes": "arena" }, - "arena_elo": 1452.98, - "arena_rank": 24, - "arena_votes": 17818 + "arena_elo": 1451.7, + "arena_rank": 27, + "arena_votes": 17735 }, { "name": "minimax-m2.5", @@ -69781,9 +69810,9 @@ "arena_rank": "arena", "arena_votes": "arena" }, - "arena_elo": 1406.48, - "arena_rank": 81, - "arena_votes": 14615 + "arena_elo": 1403.38, + "arena_rank": 86, + "arena_votes": 17217 }, { "name": "mimo-v2-pro", @@ -69810,9 +69839,9 @@ "arena_rank": "arena", "arena_votes": "arena" }, - "arena_elo": 1444.23, + "arena_elo": 1446.43, "arena_rank": 36, - "arena_votes": 6342 + "arena_votes": 8397 }, { "name": "minimax-m2.7", @@ -69839,17 +69868,59 @@ "arena_rank": "arena", "arena_votes": "arena" }, - "arena_elo": 1403.18, - "arena_rank": 86, - "arena_votes": 4666 + "arena_elo": 1404.38, + "arena_rank": 85, + "arena_votes": 6784 + }, + { + "name": "nemotron-3-super-120b-a12b", + "lb_name": "nemotron-3-super-120b-a12b", + "lb_global": 0.32021600000000006, + "lb_reasoning": 0.34389000000000003, + "lb_coding": 0.38536, + "lb_math": 0.3642875, + "lb_language": 0.300415, + "lb_if": 0.2840775, + "lb_data_analysis": 0.21230666666666667, + "sources": { + "lb_name": "livebench", + "lb_global": "livebench", + "lb_reasoning": "livebench", + "lb_coding": "livebench", + "lb_math": "livebench", + "lb_language": "livebench", + "lb_if": "livebench", + "lb_data_analysis": "livebench" + } + }, + { + "name": "qwen3.6-plus", + "lb_name": "qwen3.6-plus", + "lb_global": 0.7076726086956523, + "lb_reasoning": 0.75827, + "lb_coding": 0.642738, + "lb_math": 0.8372475, + "lb_language": 0.7498933333333334, + "lb_if": 0.5834199999999999, + "lb_data_analysis": 0.6991166666666667, + "sources": { + "lb_name": "livebench", + "lb_global": "livebench", + "lb_reasoning": "livebench", + "lb_coding": "livebench", + "lb_math": "livebench", + "lb_language": "livebench", + "lb_if": "livebench", + "lb_data_analysis": "livebench" + } }, { "name": "claude-opus-4-6-thinking", "arena_name": "claude-opus-4-6-thinking", "arena_org": "Anthropic", - "arena_elo": 1503.81, + "arena_elo": 1503.85, "arena_rank": 1, - "arena_votes": 13979, + "arena_votes": 16278, "sources": { "arena_name": "arena", "arena_org": "arena", @@ -69859,12 +69930,12 @@ } }, { - "name": "gemini-3.1-pro-preview", - "arena_name": "gemini-3.1-pro-preview", - "arena_org": "Google", - "arena_elo": 1494.17, + "name": "muse-spark", + "arena_name": "muse-spark", + "arena_org": "Meta", + "arena_elo": 1492.8, "arena_rank": 3, - "arena_votes": 17559, + "arena_votes": 3268, "sources": { "arena_name": "arena", "arena_org": "arena", @@ -69874,12 +69945,12 @@ } }, { - "name": "grok-4.20-beta1", - "arena_name": "grok-4.20-beta1", - "arena_org": "xAI", - "arena_elo": 1491.07, + "name": "gemini-3.1-pro-preview", + "arena_name": "gemini-3.1-pro-preview", + "arena_org": "Google", + "arena_elo": 1491.82, "arena_rank": 4, - "arena_votes": 7380, + "arena_votes": 20531, "sources": { "arena_name": "arena", "arena_org": "arena", @@ -69892,9 +69963,9 @@ "name": "gemini-3-pro", "arena_name": "gemini-3-pro", "arena_org": "Google", - "arena_elo": 1486.36, + "arena_elo": 1485.98, "arena_rank": 5, - "arena_votes": 41632, + "arena_votes": 41585, "sources": { "arena_name": "arena", "arena_org": "arena", @@ -69904,12 +69975,12 @@ } }, { - "name": "gpt-5.2-chat-latest-20260210", - "arena_name": "gpt-5.2-chat-latest-20260210", - "arena_org": "OpenAI", - "arena_elo": 1478.45, - "arena_rank": 8, - "arena_votes": 13083, + "name": "grok-4.20-beta1", + "arena_name": "grok-4.20-beta1", + "arena_org": "xAI", + "arena_elo": 1485.61, + "arena_rank": 6, + "arena_votes": 9689, "sources": { "arena_name": "arena", "arena_org": "arena", @@ -69919,12 +69990,12 @@ } }, { - "name": "gemini-3-flash", - "arena_name": "gemini-3-flash", - "arena_org": "Google", - "arena_elo": 1474.41, + "name": "gpt-5.2-chat-latest-20260210", + "arena_name": "gpt-5.2-chat-latest-20260210", + "arena_org": "OpenAI", + "arena_elo": 1476.53, "arena_rank": 9, - "arena_votes": 30966, + "arena_votes": 15704, "sources": { "arena_name": "arena", "arena_org": "arena", @@ -69937,9 +70008,9 @@ "name": "grok-4.20-multi-agent-beta-0309", "arena_name": "grok-4.20-multi-agent-beta-0309", "arena_org": "xAI", - "arena_elo": 1474.07, + "arena_elo": 1476.08, "arena_rank": 10, - "arena_votes": 7815, + "arena_votes": 10112, "sources": { "arena_name": "arena", "arena_org": "arena", @@ -69949,12 +70020,12 @@ } }, { - "name": "claude-opus-4-5-20251101-thinking-32k", - "arena_name": "claude-opus-4-5-20251101-thinking-32k", - "arena_org": "Anthropic", - "arena_elo": 1473.64, + "name": "gemini-3-flash", + "arena_name": "gemini-3-flash", + "arena_org": "Google", + "arena_elo": 1473.74, "arena_rank": 11, - "arena_votes": 37467, + "arena_votes": 30918, "sources": { "arena_name": "arena", "arena_org": "arena", @@ -69964,12 +70035,12 @@ } }, { - "name": "grok-4.1-thinking", - "arena_name": "grok-4.1-thinking", - "arena_org": "xAI", - "arena_elo": 1471.06, + "name": "claude-opus-4-5-20251101-thinking-32k", + "arena_name": "claude-opus-4-5-20251101-thinking-32k", + "arena_org": "Anthropic", + "arena_elo": 1473.05, "arena_rank": 12, - "arena_votes": 45399, + "arena_votes": 37307, "sources": { "arena_name": "arena", "arena_org": "arena", @@ -69979,12 +70050,12 @@ } }, { - "name": "qwen3.5-max-preview", - "arena_name": "qwen3.5-max-preview", - "arena_org": "Alibaba", - "arena_elo": 1466.93, + "name": "grok-4.1-thinking", + "arena_name": "grok-4.1-thinking", + "arena_org": "xAI", + "arena_elo": 1470.72, "arena_rank": 14, - "arena_votes": 5899, + "arena_votes": 47508, "sources": { "arena_name": "arena", "arena_org": "arena", @@ -69994,12 +70065,12 @@ } }, { - "name": "dola-seed-2.0-pro", - "arena_name": "dola-seed-2.0-pro", - "arena_org": "Bytedance", - "arena_elo": 1465.07, - "arena_rank": 15, - "arena_votes": 2986, + "name": "qwen3.5-max-preview", + "arena_name": "qwen3.5-max-preview", + "arena_org": "Alibaba", + "arena_elo": 1466.49, + "arena_rank": 16, + "arena_votes": 7952, "sources": { "arena_name": "arena", "arena_org": "arena", @@ -70012,9 +70083,9 @@ "name": "gpt-5.4", "arena_name": "gpt-5.4", "arena_org": "OpenAI", - "arena_elo": 1464.14, - "arena_rank": 16, - "arena_votes": 7261, + "arena_elo": 1465.63, + "arena_rank": 17, + "arena_votes": 9977, "sources": { "arena_name": "arena", "arena_org": "arena", @@ -70027,9 +70098,24 @@ "name": "gemini-3-flash (thinking-minimal)", "arena_name": "gemini-3-flash (thinking-minimal)", "arena_org": "Google", - "arena_elo": 1463.33, - "arena_rank": 17, - "arena_votes": 30448, + "arena_elo": 1462.89, + "arena_rank": 18, + "arena_votes": 33555, + "sources": { + "arena_name": "arena", + "arena_org": "arena", + "arena_elo": "arena", + "arena_rank": "arena", + "arena_votes": "arena" + } + }, + { + "name": "dola-seed-2.0-pro", + "arena_name": "dola-seed-2.0-pro", + "arena_org": "Bytedance", + "arena_elo": 1460.95, + "arena_rank": 20, + "arena_votes": 18882, "sources": { "arena_name": "arena", "arena_org": "arena", @@ -70042,9 +70128,9 @@ "name": "grok-4.1", "arena_name": "grok-4.1", "arena_org": "xAI", - "arena_elo": 1461.49, - "arena_rank": 19, - "arena_votes": 49287, + "arena_elo": 1460.38, + "arena_rank": 21, + "arena_votes": 51452, "sources": { "arena_name": "arena", "arena_org": "arena", @@ -70057,9 +70143,9 @@ "name": "gpt-5.3-chat-latest", "arena_name": "gpt-5.3-chat-latest", "arena_org": "OpenAI", - "arena_elo": 1460.5, - "arena_rank": 20, - "arena_votes": 11781, + "arena_elo": 1455.83, + "arena_rank": 23, + "arena_votes": 14444, "sources": { "arena_name": "arena", "arena_org": "arena", @@ -70072,9 +70158,9 @@ "name": "gpt-5.1-high", "arena_name": "gpt-5.1-high", "arena_org": "OpenAI", - "arena_elo": 1454.83, - "arena_rank": 23, - "arena_votes": 41170, + "arena_elo": 1454.42, + "arena_rank": 25, + "arena_votes": 41042, "sources": { "arena_name": "arena", "arena_org": "arena", @@ -70087,9 +70173,9 @@ "name": "claude-sonnet-4-5-20250929-thinking-32k", "arena_name": "claude-sonnet-4-5-20250929-thinking-32k", "arena_org": "Anthropic", - "arena_elo": 1452.47, + "arena_elo": 1451.72, "arena_rank": 26, - "arena_votes": 58247, + "arena_votes": 60401, "sources": { "arena_name": "arena", "arena_org": "arena", @@ -70102,9 +70188,9 @@ "name": "gemma-4-31b", "arena_name": "gemma-4-31b", "arena_org": "Google", - "arena_elo": 1452.08, - "arena_rank": 27, - "arena_votes": 4679, + "arena_elo": 1450.51, + "arena_rank": 29, + "arena_votes": 5957, "sources": { "arena_name": "arena", "arena_org": "arena", @@ -70117,9 +70203,9 @@ "name": "ernie-5.0-0110", "arena_name": "ernie-5.0-0110", "arena_org": "Baidu", - "arena_elo": 1450.31, - "arena_rank": 28, - "arena_votes": 20836, + "arena_elo": 1450.03, + "arena_rank": 30, + "arena_votes": 22778, "sources": { "arena_name": "arena", "arena_org": "arena", @@ -70132,24 +70218,9 @@ "name": "ernie-5.0-preview-1203", "arena_name": "ernie-5.0-preview-1203", "arena_org": "Baidu", - "arena_elo": 1449.68, - "arena_rank": 29, - "arena_votes": 9824, - "sources": { - "arena_name": "arena", - "arena_org": "arena", - "arena_elo": "arena", - "arena_rank": "arena", - "arena_votes": "arena" - } - }, - { - "name": "qwen3.5-397b-a17b", - "arena_name": "qwen3.5-397b-a17b", - "arena_org": "Alibaba", - "arena_elo": 1449.45, - "arena_rank": 30, - "arena_votes": 12994, + "arena_elo": 1449.43, + "arena_rank": 31, + "arena_votes": 9810, "sources": { "arena_name": "arena", "arena_org": "arena", @@ -70162,9 +70233,9 @@ "name": "claude-opus-4-1-20250805-thinking-16k", "arena_name": "claude-opus-4-1-20250805-thinking-16k", "arena_org": "Anthropic", - "arena_elo": 1448.62, - "arena_rank": 31, - "arena_votes": 50174, + "arena_elo": 1448.46, + "arena_rank": 32, + "arena_votes": 50152, "sources": { "arena_name": "arena", "arena_org": "arena", @@ -70177,9 +70248,9 @@ "name": "gemini-2.5-pro", "arena_name": "gemini-2.5-pro", "arena_org": "Google", - "arena_elo": 1448.05, - "arena_rank": 32, - "arena_votes": 105423, + "arena_elo": 1448.09, + "arena_rank": 33, + "arena_votes": 107824, "sources": { "arena_name": "arena", "arena_org": "arena", @@ -70189,12 +70260,12 @@ } }, { - "name": "claude-opus-4-1-20250805", - "arena_name": "claude-opus-4-1-20250805", - "arena_org": "Anthropic", - "arena_elo": 1446.86, - "arena_rank": 33, - "arena_votes": 77943, + "name": "qwen3.5-397b-a17b", + "arena_name": "qwen3.5-397b-a17b", + "arena_org": "Alibaba", + "arena_elo": 1446.75, + "arena_rank": 34, + "arena_votes": 15408, "sources": { "arena_name": "arena", "arena_org": "arena", @@ -70204,12 +70275,12 @@ } }, { - "name": "longcat-flash-chat-2602-exp", - "arena_name": "longcat-flash-chat-2602-exp", - "arena_org": "Meituan", - "arena_elo": 1444.92, - "arena_rank": 34, - "arena_votes": 3897, + "name": "claude-opus-4-1-20250805", + "arena_name": "claude-opus-4-1-20250805", + "arena_org": "Anthropic", + "arena_elo": 1446.58, + "arena_rank": 35, + "arena_votes": 77864, "sources": { "arena_name": "arena", "arena_org": "arena", @@ -70222,9 +70293,9 @@ "name": "chatgpt-4o-latest-20250326", "arena_name": "chatgpt-4o-latest-20250326", "arena_org": "OpenAI", - "arena_elo": 1443.1, - "arena_rank": 37, - "arena_votes": 83051, + "arena_elo": 1442.91, + "arena_rank": 38, + "arena_votes": 82998, "sources": { "arena_name": "arena", "arena_org": "arena", @@ -70237,9 +70308,9 @@ "name": "gpt-5.2-high", "arena_name": "gpt-5.2-high", "arena_org": "OpenAI", - "arena_elo": 1441.51, - "arena_rank": 39, - "arena_votes": 28004, + "arena_elo": 1441.93, + "arena_rank": 40, + "arena_votes": 30488, "sources": { "arena_name": "arena", "arena_org": "arena", @@ -70249,12 +70320,12 @@ } }, { - "name": "gemma-4-26b-a4b", - "arena_name": "gemma-4-26b-a4b", - "arena_org": "Google", - "arena_elo": 1440.64, - "arena_rank": 40, - "arena_votes": 4548, + "name": "longcat-flash-chat-2602-exp", + "arena_name": "longcat-flash-chat-2602-exp", + "arena_org": "Meituan", + "arena_elo": 1439.96, + "arena_rank": 41, + "arena_votes": 5790, "sources": { "arena_name": "arena", "arena_org": "arena", @@ -70267,9 +70338,9 @@ "name": "gpt-5.2", "arena_name": "gpt-5.2", "arena_org": "OpenAI", - "arena_elo": 1440.27, - "arena_rank": 41, - "arena_votes": 24946, + "arena_elo": 1439.49, + "arena_rank": 42, + "arena_votes": 27564, "sources": { "arena_name": "arena", "arena_org": "arena", @@ -70282,9 +70353,24 @@ "name": "gpt-5.1", "arena_name": "gpt-5.1", "arena_org": "OpenAI", - "arena_elo": 1438.55, - "arena_rank": 42, - "arena_votes": 43869, + "arena_elo": 1438.5, + "arena_rank": 43, + "arena_votes": 43708, + "sources": { + "arena_name": "arena", + "arena_org": "arena", + "arena_elo": "arena", + "arena_rank": "arena", + "arena_votes": "arena" + } + }, + { + "name": "gemma-4-26b-a4b", + "arena_name": "gemma-4-26b-a4b", + "arena_org": "Google", + "arena_elo": 1438.47, + "arena_rank": 44, + "arena_votes": 5927, "sources": { "arena_name": "arena", "arena_org": "arena", @@ -70297,9 +70383,9 @@ "name": "gemini-3.1-flash-lite-preview", "arena_name": "gemini-3.1-flash-lite-preview", "arena_org": "Google", - "arena_elo": 1438, - "arena_rank": 43, - "arena_votes": 13569, + "arena_elo": 1435.04, + "arena_rank": 45, + "arena_votes": 15996, "sources": { "arena_name": "arena", "arena_org": "arena", @@ -70312,9 +70398,9 @@ "name": "qwen3-max-preview", "arena_name": "qwen3-max-preview", "arena_org": "Alibaba", - "arena_elo": 1435.05, - "arena_rank": 44, - "arena_votes": 27955, + "arena_elo": 1434.78, + "arena_rank": 46, + "arena_votes": 27940, "sources": { "arena_name": "arena", "arena_org": "arena", @@ -70327,9 +70413,9 @@ "name": "kimi-k2.5-instant", "arena_name": "kimi-k2.5-instant", "arena_org": "Moonshot", - "arena_elo": 1433.17, - "arena_rank": 46, - "arena_votes": 8232, + "arena_elo": 1432.5, + "arena_rank": 48, + "arena_votes": 8241, "sources": { "arena_name": "arena", "arena_org": "arena", @@ -70342,9 +70428,9 @@ "name": "o3-2025-04-16", "arena_name": "o3-2025-04-16", "arena_org": "OpenAI", - "arena_elo": 1431.29, - "arena_rank": 48, - "arena_votes": 60179, + "arena_elo": 1431.15, + "arena_rank": 50, + "arena_votes": 60172, "sources": { "arena_name": "arena", "arena_org": "arena", @@ -70357,9 +70443,9 @@ "name": "kimi-k2-thinking-turbo", "arena_name": "kimi-k2-thinking-turbo", "arena_org": "Moonshot", - "arena_elo": 1429.83, - "arena_rank": 49, - "arena_votes": 43994, + "arena_elo": 1430.28, + "arena_rank": 51, + "arena_votes": 46203, "sources": { "arena_name": "arena", "arena_org": "arena", @@ -70372,9 +70458,9 @@ "name": "amazon-nova-experimental-chat-26-02-10", "arena_name": "amazon-nova-experimental-chat-26-02-10", "arena_org": "Amazon", - "arena_elo": 1428.58, - "arena_rank": 50, - "arena_votes": 3461, + "arena_elo": 1427.89, + "arena_rank": 52, + "arena_votes": 3452, "sources": { "arena_name": "arena", "arena_org": "arena", @@ -70387,9 +70473,9 @@ "name": "deepseek-v3.2-exp-thinking", "arena_name": "deepseek-v3.2-exp-thinking", "arena_org": "DeepSeek", - "arena_elo": 1424.89, - "arena_rank": 53, - "arena_votes": 9147, + "arena_elo": 1424.73, + "arena_rank": 55, + "arena_votes": 9146, "sources": { "arena_name": "arena", "arena_org": "arena", @@ -70402,9 +70488,9 @@ "name": "claude-opus-4-20250514-thinking-16k", "arena_name": "claude-opus-4-20250514-thinking-16k", "arena_org": "Anthropic", - "arena_elo": 1423.91, - "arena_rank": 56, - "arena_votes": 37192, + "arena_elo": 1423.77, + "arena_rank": 58, + "arena_votes": 37191, "sources": { "arena_name": "arena", "arena_org": "arena", @@ -70417,9 +70503,9 @@ "name": "deepseek-v3.2-thinking", "arena_name": "deepseek-v3.2-thinking", "arena_org": "DeepSeek", - "arena_elo": 1422.66, - "arena_rank": 58, - "arena_votes": 33449, + "arena_elo": 1422.63, + "arena_rank": 61, + "arena_votes": 35638, "sources": { "arena_name": "arena", "arena_org": "arena", @@ -70432,9 +70518,9 @@ "name": "grok-4-fast-chat", "arena_name": "grok-4-fast-chat", "arena_org": "xAI", - "arena_elo": 1420.81, - "arena_rank": 61, - "arena_votes": 6870, + "arena_elo": 1420.73, + "arena_rank": 63, + "arena_votes": 6872, "sources": { "arena_name": "arena", "arena_org": "arena", @@ -70447,9 +70533,9 @@ "name": "ernie-5.0-preview-1022", "arena_name": "ernie-5.0-preview-1022", "arena_org": "Baidu", - "arena_elo": 1419.07, - "arena_rank": 62, - "arena_votes": 4765, + "arena_elo": 1418.8, + "arena_rank": 64, + "arena_votes": 4758, "sources": { "arena_name": "arena", "arena_org": "arena", @@ -70462,9 +70548,9 @@ "name": "deepseek-v3.1", "arena_name": "deepseek-v3.1", "arena_org": "DeepSeek", - "arena_elo": 1418.02, - "arena_rank": 63, - "arena_votes": 15082, + "arena_elo": 1417.79, + "arena_rank": 65, + "arena_votes": 15074, "sources": { "arena_name": "arena", "arena_org": "arena", @@ -70477,9 +70563,9 @@ "name": "kimi-k2-0905-preview", "arena_name": "kimi-k2-0905-preview", "arena_org": "Moonshot", - "arena_elo": 1417.75, - "arena_rank": 64, - "arena_votes": 11867, + "arena_elo": 1417.73, + "arena_rank": 66, + "arena_votes": 11870, "sources": { "arena_name": "arena", "arena_org": "arena", @@ -70489,12 +70575,12 @@ } }, { - "name": "kimi-k2-0711-preview", - "arena_name": "kimi-k2-0711-preview", - "arena_org": "Moonshot", - "arena_elo": 1417.12, - "arena_rank": 65, - "arena_votes": 27875, + "name": "qwen3.5-122b-a10b", + "arena_name": "qwen3.5-122b-a10b", + "arena_org": "Alibaba", + "arena_elo": 1417.71, + "arena_rank": 67, + "arena_votes": 12139, "sources": { "arena_name": "arena", "arena_org": "arena", @@ -70504,12 +70590,12 @@ } }, { - "name": "deepseek-v3.1-thinking", - "arena_name": "deepseek-v3.1-thinking", - "arena_org": "DeepSeek", - "arena_elo": 1417.02, - "arena_rank": 66, - "arena_votes": 11822, + "name": "kimi-k2-0711-preview", + "arena_name": "kimi-k2-0711-preview", + "arena_org": "Moonshot", + "arena_elo": 1416.92, + "arena_rank": 68, + "arena_votes": 27869, "sources": { "arena_name": "arena", "arena_org": "arena", @@ -70519,12 +70605,12 @@ } }, { - "name": "deepseek-v3.1-terminus-thinking", - "arena_name": "deepseek-v3.1-terminus-thinking", + "name": "deepseek-v3.1-thinking", + "arena_name": "deepseek-v3.1-thinking", "arena_org": "DeepSeek", - "arena_elo": 1416.42, - "arena_rank": 67, - "arena_votes": 3487, + "arena_elo": 1416.79, + "arena_rank": 69, + "arena_votes": 11824, "sources": { "arena_name": "arena", "arena_org": "arena", @@ -70534,12 +70620,12 @@ } }, { - "name": "qwen3.5-122b-a10b", - "arena_name": "qwen3.5-122b-a10b", - "arena_org": "Alibaba", - "arena_elo": 1416.03, - "arena_rank": 68, - "arena_votes": 9686, + "name": "deepseek-v3.1-terminus-thinking", + "arena_name": "deepseek-v3.1-terminus-thinking", + "arena_org": "DeepSeek", + "arena_elo": 1416.46, + "arena_rank": 70, + "arena_votes": 3491, "sources": { "arena_name": "arena", "arena_org": "arena", @@ -70552,9 +70638,9 @@ "name": "qwen3-vl-235b-a22b-instruct", "arena_name": "qwen3-vl-235b-a22b-instruct", "arena_org": "Alibaba", - "arena_elo": 1415.86, - "arena_rank": 69, - "arena_votes": 11611, + "arena_elo": 1415.62, + "arena_rank": 72, + "arena_votes": 11610, "sources": { "arena_name": "arena", "arena_org": "arena", @@ -70564,12 +70650,12 @@ } }, { - "name": "mistral-large-3", - "arena_name": "mistral-large-3", - "arena_org": "Mistral", - "arena_elo": 1415.64, - "arena_rank": 71, - "arena_votes": 35825, + "name": "amazon-nova-experimental-chat-26-01-10", + "arena_name": "amazon-nova-experimental-chat-26-01-10", + "arena_org": "Amazon", + "arena_elo": 1414.95, + "arena_rank": 73, + "arena_votes": 3436, "sources": { "arena_name": "arena", "arena_org": "arena", @@ -70579,12 +70665,12 @@ } }, { - "name": "amazon-nova-experimental-chat-26-01-10", - "arena_name": "amazon-nova-experimental-chat-26-01-10", - "arena_org": "Amazon", - "arena_elo": 1415.04, - "arena_rank": 72, - "arena_votes": 3442, + "name": "mistral-large-3", + "arena_name": "mistral-large-3", + "arena_org": "Mistral", + "arena_elo": 1414.52, + "arena_rank": 74, + "arena_votes": 38277, "sources": { "arena_name": "arena", "arena_org": "arena", @@ -70597,9 +70683,9 @@ "name": "claude-opus-4-20250514", "arena_name": "claude-opus-4-20250514", "arena_org": "Anthropic", - "arena_elo": 1412.26, - "arena_rank": 74, - "arena_votes": 44565, + "arena_elo": 1412.11, + "arena_rank": 76, + "arena_votes": 44557, "sources": { "arena_name": "arena", "arena_org": "arena", @@ -70612,9 +70698,9 @@ "name": "grok-3-preview-02-24", "arena_name": "grok-3-preview-02-24", "arena_org": "xAI", - "arena_elo": 1411.74, - "arena_rank": 75, - "arena_votes": 33052, + "arena_elo": 1411.64, + "arena_rank": 77, + "arena_votes": 33053, "sources": { "arena_name": "arena", "arena_org": "arena", @@ -70627,9 +70713,9 @@ "name": "gemini-2.5-flash", "arena_name": "gemini-2.5-flash", "arena_org": "Google", - "arena_elo": 1410.89, - "arena_rank": 77, - "arena_votes": 104876, + "arena_elo": 1411.09, + "arena_rank": 78, + "arena_votes": 107221, "sources": { "arena_name": "arena", "arena_org": "arena", @@ -70642,9 +70728,9 @@ "name": "mistral-medium-2508", "arena_name": "mistral-medium-2508", "arena_org": "Mistral", - "arena_elo": 1410.23, - "arena_rank": 79, - "arena_votes": 74890, + "arena_elo": 1409.82, + "arena_rank": 81, + "arena_votes": 77340, "sources": { "arena_name": "arena", "arena_org": "arena", @@ -70657,24 +70743,9 @@ "name": "grok-4-fast-reasoning", "arena_name": "grok-4-fast-reasoning", "arena_org": "xAI", - "arena_elo": 1404.72, - "arena_rank": 83, - "arena_votes": 18898, - "sources": { - "arena_name": "arena", - "arena_org": "arena", - "arena_elo": "arena", - "arena_rank": "arena", - "arena_votes": "arena" - } - }, - { - "name": "qwen3.5-27b", - "arena_name": "qwen3.5-27b", - "arena_org": "Alibaba", - "arena_elo": 1404.35, + "arena_elo": 1404.43, "arena_rank": 84, - "arena_votes": 9564, + "arena_votes": 18883, "sources": { "arena_name": "arena", "arena_org": "arena", @@ -70687,9 +70758,9 @@ "name": "qwen3-235b-a22b-no-thinking", "arena_name": "qwen3-235b-a22b-no-thinking", "arena_org": "Alibaba", - "arena_elo": 1402.75, + "arena_elo": 1402.62, "arena_rank": 87, - "arena_votes": 38471, + "arena_votes": 38476, "sources": { "arena_name": "arena", "arena_org": "arena", @@ -70699,12 +70770,12 @@ } }, { - "name": "qwen3.5-flash", - "arena_name": "qwen3.5-flash", + "name": "qwen3.5-27b", + "arena_name": "qwen3.5-27b", "arena_org": "Alibaba", - "arena_elo": 1401.86, + "arena_elo": 1402.09, "arena_rank": 88, - "arena_votes": 10307, + "arena_votes": 11893, "sources": { "arena_name": "arena", "arena_org": "arena", @@ -70717,9 +70788,9 @@ "name": "longcat-flash-chat", "arena_name": "longcat-flash-chat", "arena_org": "Meituan", - "arena_elo": 1401.06, - "arena_rank": 91, - "arena_votes": 11478, + "arena_elo": 1400.96, + "arena_rank": 92, + "arena_votes": 11481, "sources": { "arena_name": "arena", "arena_org": "arena", @@ -70729,12 +70800,12 @@ } }, { - "name": "qwen3.5-35b-a3b", - "arena_name": "qwen3.5-35b-a3b", + "name": "qwen3.5-flash", + "arena_name": "qwen3.5-flash", "arena_org": "Alibaba", - "arena_elo": 1400.03, - "arena_rank": 92, - "arena_votes": 9959, + "arena_elo": 1399.94, + "arena_rank": 93, + "arena_votes": 12690, "sources": { "arena_name": "arena", "arena_org": "arena", @@ -70748,8 +70819,8 @@ "arena_name": "claude-sonnet-4-20250514-thinking-32k", "arena_org": "Anthropic", "arena_elo": 1398.54, - "arena_rank": 94, - "arena_votes": 35423, + "arena_rank": 95, + "arena_votes": 35434, "sources": { "arena_name": "arena", "arena_org": "arena", @@ -70762,9 +70833,9 @@ "name": "hunyuan-vision-1.5-thinking", "arena_name": "hunyuan-vision-1.5-thinking", "arena_org": "Tencent", - "arena_elo": 1396.6, - "arena_rank": 96, - "arena_votes": 2228, + "arena_elo": 1396.7, + "arena_rank": 97, + "arena_votes": 2227, "sources": { "arena_name": "arena", "arena_org": "arena", @@ -70774,12 +70845,12 @@ } }, { - "name": "amazon-nova-experimental-chat-12-10", - "arena_name": "amazon-nova-experimental-chat-12-10", - "arena_org": "Amazon", - "arena_elo": 1395.88, - "arena_rank": 97, - "arena_votes": 3706, + "name": "qwen3.5-35b-a3b", + "arena_name": "qwen3.5-35b-a3b", + "arena_org": "Alibaba", + "arena_elo": 1395.54, + "arena_rank": 98, + "arena_votes": 12328, "sources": { "arena_name": "arena", "arena_org": "arena", @@ -70792,9 +70863,24 @@ "name": "qwen3-vl-235b-a22b-thinking", "arena_name": "qwen3-vl-235b-a22b-thinking", "arena_org": "Alibaba", - "arena_elo": 1395.58, - "arena_rank": 98, - "arena_votes": 8021, + "arena_elo": 1395.36, + "arena_rank": 99, + "arena_votes": 8024, + "sources": { + "arena_name": "arena", + "arena_org": "arena", + "arena_elo": "arena", + "arena_rank": "arena", + "arena_votes": "arena" + } + }, + { + "name": "amazon-nova-experimental-chat-12-10", + "arena_name": "amazon-nova-experimental-chat-12-10", + "arena_org": "Amazon", + "arena_elo": 1395.2, + "arena_rank": 100, + "arena_votes": 3704, "sources": { "arena_name": "arena", "arena_org": "arena", @@ -70807,9 +70893,9 @@ "name": "mai-1-preview", "arena_name": "mai-1-preview", "arena_org": "Microsoft AI", - "arena_elo": 1392.77, - "arena_rank": 100, - "arena_votes": 18020, + "arena_elo": 1392.65, + "arena_rank": 102, + "arena_votes": 18023, "sources": { "arena_name": "arena", "arena_org": "arena", @@ -70822,9 +70908,9 @@ "name": "mimo-v2-flash (non-thinking)", "arena_name": "mimo-v2-flash (non-thinking)", "arena_org": "Xiaomi", - "arena_elo": 1392.69, - "arena_rank": 101, - "arena_votes": 27959, + "arena_elo": 1392.1, + "arena_rank": 103, + "arena_votes": 30218, "sources": { "arena_name": "arena", "arena_org": "arena", @@ -70837,9 +70923,9 @@ "name": "step-3.5-flash", "arena_name": "step-3.5-flash", "arena_org": "StepFun", - "arena_elo": 1392.29, - "arena_rank": 102, - "arena_votes": 16327, + "arena_elo": 1391.58, + "arena_rank": 104, + "arena_votes": 18567, "sources": { "arena_name": "arena", "arena_org": "arena", @@ -70852,9 +70938,9 @@ "name": "o4-mini-2025-04-16", "arena_name": "o4-mini-2025-04-16", "arena_org": "OpenAI", - "arena_elo": 1389.98, - "arena_rank": 103, - "arena_votes": 45771, + "arena_elo": 1389.69, + "arena_rank": 105, + "arena_votes": 45744, "sources": { "arena_name": "arena", "arena_org": "arena", @@ -70867,9 +70953,9 @@ "name": "claude-sonnet-4-20250514", "arena_name": "claude-sonnet-4-20250514", "arena_org": "Anthropic", - "arena_elo": 1388.73, - "arena_rank": 105, - "arena_votes": 40664, + "arena_elo": 1388.62, + "arena_rank": 107, + "arena_votes": 40662, "sources": { "arena_name": "arena", "arena_org": "arena", @@ -70879,12 +70965,12 @@ } }, { - "name": "mimo-v2-flash (thinking)", - "arena_name": "mimo-v2-flash (thinking)", - "arena_org": "Xiaomi", - "arena_elo": 1387.36, - "arena_rank": 107, - "arena_votes": 11014, + "name": "hunyuan-t1-20250711", + "arena_name": "hunyuan-t1-20250711", + "arena_org": "Tencent", + "arena_elo": 1387.09, + "arena_rank": 110, + "arena_votes": 4736, "sources": { "arena_name": "arena", "arena_org": "arena", @@ -70894,12 +70980,12 @@ } }, { - "name": "hunyuan-t1-20250711", - "arena_name": "hunyuan-t1-20250711", - "arena_org": "Tencent", - "arena_elo": 1387.24, - "arena_rank": 108, - "arena_votes": 4720, + "name": "mimo-v2-flash (thinking)", + "arena_name": "mimo-v2-flash (thinking)", + "arena_org": "Xiaomi", + "arena_elo": 1387.08, + "arena_rank": 111, + "arena_votes": 11018, "sources": { "arena_name": "arena", "arena_org": "arena", @@ -70912,9 +70998,9 @@ "name": "claude-3-7-sonnet-20250219-thinking-32k", "arena_name": "claude-3-7-sonnet-20250219-thinking-32k", "arena_org": "Anthropic", - "arena_elo": 1386.47, - "arena_rank": 110, - "arena_votes": 38993, + "arena_elo": 1386.37, + "arena_rank": 112, + "arena_votes": 39003, "sources": { "arena_name": "arena", "arena_org": "arena", @@ -70927,9 +71013,9 @@ "name": "minimax-m2.1-preview", "arena_name": "minimax-m2.1-preview", "arena_org": "MiniMax", - "arena_elo": 1386.26, - "arena_rank": 112, - "arena_votes": 17225, + "arena_elo": 1385.59, + "arena_rank": 114, + "arena_votes": 17231, "sources": { "arena_name": "arena", "arena_org": "arena", @@ -70942,9 +71028,9 @@ "name": "qwen3-30b-a3b-instruct-2507", "arena_name": "qwen3-30b-a3b-instruct-2507", "arena_org": "Alibaba", - "arena_elo": 1383.11, - "arena_rank": 113, - "arena_votes": 23947, + "arena_elo": 1383.04, + "arena_rank": 115, + "arena_votes": 23941, "sources": { "arena_name": "arena", "arena_org": "arena", @@ -70957,9 +71043,9 @@ "name": "hunyuan-turbos-20250416", "arena_name": "hunyuan-turbos-20250416", "arena_org": "Tencent", - "arena_elo": 1382.88, - "arena_rank": 114, - "arena_votes": 10774, + "arena_elo": 1382.67, + "arena_rank": 116, + "arena_votes": 10777, "sources": { "arena_name": "arena", "arena_org": "arena", @@ -70972,9 +71058,9 @@ "name": "gemini-2.5-flash-lite-preview-09-2025-no-thinking", "arena_name": "gemini-2.5-flash-lite-preview-09-2025-no-thinking", "arena_org": "Google", - "arena_elo": 1380, - "arena_rank": 116, - "arena_votes": 47594, + "arena_elo": 1379.96, + "arena_rank": 118, + "arena_votes": 47540, "sources": { "arena_name": "arena", "arena_org": "arena", @@ -70984,12 +71070,12 @@ } }, { - "name": "trinity-large", - "arena_name": "trinity-large", - "arena_org": "Arcee AI", - "arena_elo": 1375.26, - "arena_rank": 118, - "arena_votes": 11005, + "name": "gemini-2.5-flash-lite-preview-06-17-thinking", + "arena_name": "gemini-2.5-flash-lite-preview-06-17-thinking", + "arena_org": "Google", + "arena_elo": 1374.32, + "arena_rank": 121, + "arena_votes": 33175, "sources": { "arena_name": "arena", "arena_org": "arena", @@ -70999,12 +71085,12 @@ } }, { - "name": "gemini-2.5-flash-lite-preview-06-17-thinking", - "arena_name": "gemini-2.5-flash-lite-preview-06-17-thinking", - "arena_org": "Google", - "arena_elo": 1374.26, - "arena_rank": 121, - "arena_votes": 33181, + "name": "trinity-large-preview", + "arena_name": "trinity-large-preview", + "arena_org": "Arcee AI", + "arena_elo": 1374.31, + "arena_rank": 122, + "arena_votes": 13315, "sources": { "arena_name": "arena", "arena_org": "arena", @@ -71017,9 +71103,9 @@ "name": "glm-4.7-flash", "arena_name": "glm-4.7-flash", "arena_org": "Z.ai", - "arena_elo": 1368.59, - "arena_rank": 126, - "arena_votes": 11830, + "arena_elo": 1368.16, + "arena_rank": 128, + "arena_votes": 11829, "sources": { "arena_name": "arena", "arena_org": "arena", @@ -71032,9 +71118,9 @@ "name": "amazon-nova-experimental-chat-11-10", "arena_name": "amazon-nova-experimental-chat-11-10", "arena_org": "Amazon", - "arena_elo": 1367.87, - "arena_rank": 127, - "arena_votes": 25671, + "arena_elo": 1367.45, + "arena_rank": 129, + "arena_votes": 25550, "sources": { "arena_name": "arena", "arena_org": "arena", @@ -71044,12 +71130,12 @@ } }, { - "name": "nvidia-nemotron-3-super-120b-a12b", - "arena_name": "nvidia-nemotron-3-super-120b-a12b", - "arena_org": "Nvidia", - "arena_elo": 1364.61, - "arena_rank": 129, - "arena_votes": 3624, + "name": "minimax-m1", + "arena_name": "minimax-m1", + "arena_org": "MiniMax", + "arena_elo": 1363.35, + "arena_rank": 131, + "arena_votes": 35518, "sources": { "arena_name": "arena", "arena_org": "arena", @@ -71062,8 +71148,8 @@ "name": "o3-mini-high", "arena_name": "o3-mini-high", "arena_org": "OpenAI", - "arena_elo": 1363.28, - "arena_rank": 130, + "arena_elo": 1363.17, + "arena_rank": 132, "arena_votes": 18589, "sources": { "arena_name": "arena", @@ -71074,12 +71160,12 @@ } }, { - "name": "minimax-m1", - "arena_name": "minimax-m1", - "arena_org": "MiniMax", - "arena_elo": 1363.22, - "arena_rank": 131, - "arena_votes": 35520, + "name": "grok-3-mini-high", + "arena_name": "grok-3-mini-high", + "arena_org": "xAI", + "arena_elo": 1362.52, + "arena_rank": 133, + "arena_votes": 17084, "sources": { "arena_name": "arena", "arena_org": "arena", @@ -71089,12 +71175,12 @@ } }, { - "name": "grok-3-mini-high", - "arena_name": "grok-3-mini-high", - "arena_org": "xAI", - "arena_elo": 1362.88, - "arena_rank": 132, - "arena_votes": 17076, + "name": "nvidia-nemotron-3-super-120b-a12b", + "arena_name": "nvidia-nemotron-3-super-120b-a12b", + "arena_org": "Nvidia", + "arena_elo": 1361.07, + "arena_rank": 134, + "arena_votes": 7449, "sources": { "arena_name": "arena", "arena_org": "arena", @@ -71107,9 +71193,9 @@ "name": "grok-3-mini-beta", "arena_name": "grok-3-mini-beta", "arena_org": "xAI", - "arena_elo": 1357.5, - "arena_rank": 135, - "arena_votes": 22878, + "arena_elo": 1357.36, + "arena_rank": 137, + "arena_votes": 22881, "sources": { "arena_name": "arena", "arena_org": "arena", @@ -71122,9 +71208,9 @@ "name": "mistral-small-2506", "arena_name": "mistral-small-2506", "arena_org": "Mistral", - "arena_elo": 1357.01, - "arena_rank": 136, - "arena_votes": 17848, + "arena_elo": 1356.93, + "arena_rank": 138, + "arena_votes": 17843, "sources": { "arena_name": "arena", "arena_org": "arena", @@ -71137,9 +71223,9 @@ "name": "intellect-3", "arena_name": "intellect-3", "arena_org": "Prime Intellect", - "arena_elo": 1356.4, - "arena_rank": 137, - "arena_votes": 5363, + "arena_elo": 1356.3, + "arena_rank": 139, + "arena_votes": 5356, "sources": { "arena_name": "arena", "arena_org": "arena", @@ -71152,9 +71238,9 @@ "name": "glm-4.5v", "arena_name": "glm-4.5v", "arena_org": "Z.ai", - "arena_elo": 1353.43, - "arena_rank": 140, - "arena_votes": 4976, + "arena_elo": 1353.08, + "arena_rank": 142, + "arena_votes": 4980, "sources": { "arena_name": "arena", "arena_org": "arena", @@ -71167,9 +71253,9 @@ "name": "amazon-nova-experimental-chat-10-20", "arena_name": "amazon-nova-experimental-chat-10-20", "arena_org": "Amazon", - "arena_elo": 1350.9, - "arena_rank": 142, - "arena_votes": 11544, + "arena_elo": 1350.28, + "arena_rank": 145, + "arena_votes": 11535, "sources": { "arena_name": "arena", "arena_org": "arena", @@ -71182,8 +71268,8 @@ "name": "hunyuan-turbos-20250226", "arena_name": "hunyuan-turbos-20250226", "arena_org": "Tencent", - "arena_elo": 1348.54, - "arena_rank": 144, + "arena_elo": 1348.45, + "arena_rank": 146, "arena_votes": 2220, "sources": { "arena_name": "arena", @@ -71197,9 +71283,9 @@ "name": "step-3", "arena_name": "step-3", "arena_org": "StepFun", - "arena_elo": 1347.56, - "arena_rank": 145, - "arena_votes": 6582, + "arena_elo": 1347.59, + "arena_rank": 147, + "arena_votes": 6587, "sources": { "arena_name": "arena", "arena_org": "arena", @@ -71212,9 +71298,9 @@ "name": "amazon-nova-experimental-chat-10-09", "arena_name": "amazon-nova-experimental-chat-10-09", "arena_org": "Amazon", - "arena_elo": 1347.14, - "arena_rank": 147, - "arena_votes": 2859, + "arena_elo": 1347.01, + "arena_rank": 149, + "arena_votes": 2858, "sources": { "arena_name": "arena", "arena_org": "arena", @@ -71227,9 +71313,9 @@ "name": "mercury-2", "arena_name": "mercury-2", "arena_org": "Inception AI", - "arena_elo": 1347.05, - "arena_rank": 149, - "arena_votes": 3136, + "arena_elo": 1346.84, + "arena_rank": 151, + "arena_votes": 3130, "sources": { "arena_name": "arena", "arena_org": "arena", @@ -71242,8 +71328,8 @@ "name": "llama-3.1-nemotron-ultra-253b-v1", "arena_name": "llama-3.1-nemotron-ultra-253b-v1", "arena_org": "Nvidia", - "arena_elo": 1346.89, - "arena_rank": 150, + "arena_elo": 1346.83, + "arena_rank": 152, "arena_votes": 2549, "sources": { "arena_name": "arena", @@ -71257,9 +71343,9 @@ "name": "ling-flash-2.0", "arena_name": "ling-flash-2.0", "arena_org": "Ant Group", - "arena_elo": 1346.26, - "arena_rank": 152, - "arena_votes": 7085, + "arena_elo": 1346.2, + "arena_rank": 154, + "arena_votes": 7081, "sources": { "arena_name": "arena", "arena_org": "arena", @@ -71272,8 +71358,8 @@ "name": "qwen-plus-0125", "arena_name": "qwen-plus-0125", "arena_org": "Alibaba", - "arena_elo": 1346, - "arena_rank": 153, + "arena_elo": 1345.89, + "arena_rank": 155, "arena_votes": 5819, "sources": { "arena_name": "arena", @@ -71287,9 +71373,9 @@ "name": "nvidia-llama-3.3-nemotron-super-49b-v1.5", "arena_name": "nvidia-llama-3.3-nemotron-super-49b-v1.5", "arena_org": "Nvidia", - "arena_elo": 1342.78, - "arena_rank": 155, - "arena_votes": 3368, + "arena_elo": 1342.82, + "arena_rank": 157, + "arena_votes": 3366, "sources": { "arena_name": "arena", "arena_org": "arena", @@ -71302,8 +71388,8 @@ "name": "glm-4-plus-0111", "arena_name": "glm-4-plus-0111", "arena_org": "Zhipu", - "arena_elo": 1342.55, - "arena_rank": 156, + "arena_elo": 1342.51, + "arena_rank": 158, "arena_votes": 5760, "sources": { "arena_name": "arena", @@ -71317,8 +71403,8 @@ "name": "hunyuan-turbo-0110", "arena_name": "hunyuan-turbo-0110", "arena_org": "Tencent", - "arena_elo": 1340.3, - "arena_rank": 159, + "arena_elo": 1340.22, + "arena_rank": 161, "arena_votes": 2290, "sources": { "arena_name": "arena", @@ -71332,9 +71418,9 @@ "name": "nova-2-lite", "arena_name": "nova-2-lite", "arena_org": "Amazon", - "arena_elo": 1337.9, - "arena_rank": 160, - "arena_votes": 12312, + "arena_elo": 1337.37, + "arena_rank": 162, + "arena_votes": 12288, "sources": { "arena_name": "arena", "arena_org": "arena", @@ -71347,8 +71433,8 @@ "name": "grok-2-2024-08-13", "arena_name": "grok-2-2024-08-13", "arena_org": "xAI", - "arena_elo": 1334.85, - "arena_rank": 164, + "arena_elo": 1334.82, + "arena_rank": 166, "arena_votes": 63498, "sources": { "arena_name": "arena", @@ -71362,8 +71448,8 @@ "name": "llama-3.1-405b-instruct-bf16", "arena_name": "llama-3.1-405b-instruct-bf16", "arena_org": "Meta", - "arena_elo": 1334.4, - "arena_rank": 166, + "arena_elo": 1334.25, + "arena_rank": 168, "arena_votes": 41375, "sources": { "arena_name": "arena", @@ -71377,8 +71463,8 @@ "name": "gemini-advanced-0514", "arena_name": "gemini-advanced-0514", "arena_org": "Google", - "arena_elo": 1334.28, - "arena_rank": 167, + "arena_elo": 1334.23, + "arena_rank": 169, "arena_votes": 50148, "sources": { "arena_name": "arena", @@ -71392,8 +71478,8 @@ "name": "step-2-16k-exp-202412", "arena_name": "step-2-16k-exp-202412", "arena_org": "StepFun", - "arena_elo": 1333.95, - "arena_rank": 168, + "arena_elo": 1333.84, + "arena_rank": 170, "arena_votes": 4833, "sources": { "arena_name": "arena", @@ -71407,8 +71493,8 @@ "name": "llama-3.1-405b-instruct-fp8", "arena_name": "llama-3.1-405b-instruct-fp8", "arena_org": "Meta", - "arena_elo": 1332.6, - "arena_rank": 169, + "arena_elo": 1332.45, + "arena_rank": 171, "arena_votes": 59656, "sources": { "arena_name": "arena", @@ -71423,8 +71509,8 @@ "arena_name": "olmo-3.1-32b-instruct", "arena_org": "Ai2", "arena_elo": 1330.9, - "arena_rank": 170, - "arena_votes": 12282, + "arena_rank": 172, + "arena_votes": 12291, "sources": { "arena_name": "arena", "arena_org": "arena", @@ -71437,8 +71523,8 @@ "name": "yi-lightning", "arena_name": "yi-lightning", "arena_org": "01 AI", - "arena_elo": 1328.21, - "arena_rank": 171, + "arena_elo": 1328.09, + "arena_rank": 173, "arena_votes": 27332, "sources": { "arena_name": "arena", @@ -71454,8 +71540,8 @@ "name": "llama-3.3-nemotron-49b-super-v1", "arena_name": "llama-3.3-nemotron-49b-super-v1", "arena_org": "Nvidia", - "arena_elo": 1327.41, - "arena_rank": 173, + "arena_elo": 1327.38, + "arena_rank": 174, "arena_votes": 2218, "sources": { "arena_name": "arena", @@ -71469,9 +71555,9 @@ "name": "molmo-2-8b", "arena_name": "molmo-2-8b", "arena_org": "Ai2", - "arena_elo": 1326.75, - "arena_rank": 175, - "arena_votes": 805, + "arena_elo": 1326.95, + "arena_rank": 176, + "arena_votes": 806, "sources": { "arena_name": "arena", "arena_org": "arena", @@ -71484,8 +71570,8 @@ "name": "hunyuan-large-2025-02-10", "arena_name": "hunyuan-large-2025-02-10", "arena_org": "Tencent", - "arena_elo": 1325.78, - "arena_rank": 176, + "arena_elo": 1325.67, + "arena_rank": 178, "arena_votes": 3738, "sources": { "arena_name": "arena", @@ -71499,8 +71585,8 @@ "name": "deepseek-v2.5-1210", "arena_name": "deepseek-v2.5-1210", "arena_org": "DeepSeek", - "arena_elo": 1323.18, - "arena_rank": 178, + "arena_elo": 1323.07, + "arena_rank": 180, "arena_votes": 6795, "sources": { "arena_name": "arena", @@ -71516,8 +71602,8 @@ "name": "gemini-1.5-pro-001", "arena_name": "gemini-1.5-pro-001", "arena_org": "Google", - "arena_elo": 1322.63, - "arena_rank": 179, + "arena_elo": 1322.59, + "arena_rank": 181, "arena_votes": 79138, "sources": { "arena_name": "arena", @@ -71534,8 +71620,8 @@ "arena_name": "llama-4-scout-17b-16e-instruct", "arena_org": "Meta", "arena_elo": 1322.03, - "arena_rank": 181, - "arena_votes": 30505, + "arena_rank": 183, + "arena_votes": 30494, "sources": { "arena_name": "arena", "arena_org": "arena", @@ -71548,9 +71634,9 @@ "name": "ring-flash-2.0", "arena_name": "ring-flash-2.0", "arena_org": "Ant Group", - "arena_elo": 1320.92, - "arena_rank": 184, - "arena_votes": 7223, + "arena_elo": 1320.78, + "arena_rank": 185, + "arena_votes": 7221, "sources": { "arena_name": "arena", "arena_org": "arena", @@ -71563,8 +71649,8 @@ "name": "step-1o-turbo-202506", "arena_name": "step-1o-turbo-202506", "arena_org": "StepFun", - "arena_elo": 1320.44, - "arena_rank": 185, + "arena_elo": 1320.48, + "arena_rank": 187, "arena_votes": 9110, "sources": { "arena_name": "arena", @@ -71578,8 +71664,8 @@ "name": "glm-4-plus", "arena_name": "glm-4-plus", "arena_org": "Zhipu AI", - "arena_elo": 1319.01, - "arena_rank": 186, + "arena_elo": 1318.92, + "arena_rank": 188, "arena_votes": 26126, "sources": { "arena_name": "arena", @@ -71590,12 +71676,12 @@ } }, { - "name": "gpt-oss-20b", - "arena_name": "gpt-oss-20b", - "arena_org": "OpenAI", - "arena_elo": 1318.16, - "arena_rank": 188, - "arena_votes": 10704, + "name": "gemma-3n-e4b-it", + "arena_name": "gemma-3n-e4b-it", + "arena_org": "Google", + "arena_elo": 1318.03, + "arena_rank": 189, + "arena_votes": 22723, "sources": { "arena_name": "arena", "arena_org": "arena", @@ -71605,12 +71691,12 @@ } }, { - "name": "gemma-3n-e4b-it", - "arena_name": "gemma-3n-e4b-it", - "arena_org": "Google", - "arena_elo": 1318.07, - "arena_rank": 189, - "arena_votes": 22728, + "name": "gpt-oss-20b", + "arena_name": "gpt-oss-20b", + "arena_org": "OpenAI", + "arena_elo": 1317.71, + "arena_rank": 191, + "arena_votes": 10701, "sources": { "arena_name": "arena", "arena_org": "arena", @@ -71623,9 +71709,9 @@ "name": "nvidia-nemotron-3-nano-30b-a3b-bf16", "arena_name": "nvidia-nemotron-3-nano-30b-a3b-bf16", "arena_org": "Nvidia", - "arena_elo": 1317.92, - "arena_rank": 190, - "arena_votes": 15607, + "arena_elo": 1317.49, + "arena_rank": 192, + "arena_votes": 15589, "sources": { "arena_name": "arena", "arena_org": "arena", @@ -71638,8 +71724,8 @@ "name": "qwen-max-0919", "arena_name": "qwen-max-0919", "arena_org": "Alibaba", - "arena_elo": 1317.59, - "arena_rank": 191, + "arena_elo": 1317.48, + "arena_rank": 193, "arena_votes": 16478, "sources": { "arena_name": "arena", @@ -71653,8 +71739,8 @@ "name": "qwen2.5-plus-1127", "arena_name": "qwen2.5-plus-1127", "arena_org": "Alibaba", - "arena_elo": 1315.01, - "arena_rank": 193, + "arena_elo": 1314.87, + "arena_rank": 195, "arena_votes": 10187, "sources": { "arena_name": "arena", @@ -71668,8 +71754,8 @@ "name": "athene-v2-chat", "arena_name": "athene-v2-chat", "arena_org": "NexusFlow", - "arena_elo": 1314.17, - "arena_rank": 194, + "arena_elo": 1314.06, + "arena_rank": 196, "arena_votes": 24739, "sources": { "arena_name": "arena", @@ -71683,8 +71769,8 @@ "name": "gpt-4-1106-preview", "arena_name": "gpt-4-1106-preview", "arena_org": "OpenAI", - "arena_elo": 1312.18, - "arena_rank": 197, + "arena_elo": 1312, + "arena_rank": 199, "arena_votes": 100105, "sources": { "arena_name": "arena", @@ -71700,8 +71786,8 @@ "name": "hunyuan-standard-2025-02-10", "arena_name": "hunyuan-standard-2025-02-10", "arena_org": "Tencent", - "arena_elo": 1310.79, - "arena_rank": 198, + "arena_elo": 1310.68, + "arena_rank": 200, "arena_votes": 3904, "sources": { "arena_name": "arena", @@ -71715,8 +71801,8 @@ "name": "grok-2-mini-2024-08-13", "arena_name": "grok-2-mini-2024-08-13", "arena_org": "xAI", - "arena_elo": 1307.76, - "arena_rank": 200, + "arena_elo": 1307.72, + "arena_rank": 202, "arena_votes": 52567, "sources": { "arena_name": "arena", @@ -71730,9 +71816,9 @@ "name": "mercury", "arena_name": "mercury", "arena_org": "Inception AI", - "arena_elo": 1306.25, - "arena_rank": 202, - "arena_votes": 1982, + "arena_elo": 1306.26, + "arena_rank": 204, + "arena_votes": 1979, "sources": { "arena_name": "arena", "arena_org": "arena", @@ -71745,8 +71831,8 @@ "name": "athene-70b-0725", "arena_name": "athene-70b-0725", "arena_org": "NexusFlow", - "arena_elo": 1305.56, - "arena_rank": 203, + "arena_elo": 1305.52, + "arena_rank": 205, "arena_votes": 19621, "sources": { "arena_name": "arena", @@ -71760,9 +71846,9 @@ "name": "olmo-3-32b-think", "arena_name": "olmo-3-32b-think", "arena_org": "Ai2", - "arena_elo": 1305.54, - "arena_rank": 204, - "arena_votes": 5995, + "arena_elo": 1305.35, + "arena_rank": 206, + "arena_votes": 5987, "sources": { "arena_name": "arena", "arena_org": "arena", @@ -71775,9 +71861,9 @@ "name": "magistral-medium-2506", "arena_name": "magistral-medium-2506", "arena_org": "Mistral", - "arena_elo": 1303.18, - "arena_rank": 206, - "arena_votes": 11723, + "arena_elo": 1303.12, + "arena_rank": 208, + "arena_votes": 11725, "sources": { "arena_name": "arena", "arena_org": "arena", @@ -71790,8 +71876,8 @@ "name": "mistral-small-3.1-24b-instruct-2503", "arena_name": "mistral-small-3.1-24b-instruct-2503", "arena_org": "Mistral", - "arena_elo": 1302.85, - "arena_rank": 207, + "arena_elo": 1302.77, + "arena_rank": 210, "arena_votes": 33474, "sources": { "arena_name": "arena", @@ -71805,9 +71891,9 @@ "name": "hunyuan-large-vision", "arena_name": "hunyuan-large-vision", "arena_org": "Tencent", - "arena_elo": 1293.83, - "arena_rank": 211, - "arena_votes": 5399, + "arena_elo": 1293.91, + "arena_rank": 213, + "arena_votes": 5404, "sources": { "arena_name": "arena", "arena_org": "arena", @@ -71820,8 +71906,8 @@ "name": "amazon-nova-pro-v1.0", "arena_name": "amazon-nova-pro-v1.0", "arena_org": "Amazon", - "arena_elo": 1289.69, - "arena_rank": 213, + "arena_elo": 1289.58, + "arena_rank": 215, "arena_votes": 24745, "sources": { "arena_name": "arena", @@ -71835,8 +71921,8 @@ "name": "reka-core-20240904", "arena_name": "reka-core-20240904", "arena_org": "Reka AI", - "arena_elo": 1287.33, - "arena_rank": 216, + "arena_elo": 1287.22, + "arena_rank": 218, "arena_votes": 7312, "sources": { "arena_name": "arena", @@ -71850,9 +71936,9 @@ "name": "ibm-granite-h-small", "arena_name": "ibm-granite-h-small", "arena_org": "IBM", - "arena_elo": 1286.93, - "arena_rank": 217, - "arena_votes": 5747, + "arena_elo": 1287.03, + "arena_rank": 219, + "arena_votes": 5743, "sources": { "arena_name": "arena", "arena_org": "arena", @@ -71865,8 +71951,8 @@ "name": "gpt-4-0314", "arena_name": "gpt-4-0314", "arena_org": "OpenAI", - "arena_elo": 1286, - "arena_rank": 218, + "arena_elo": 1285.82, + "arena_rank": 220, "arena_votes": 54173, "sources": { "arena_name": "arena", @@ -71882,9 +71968,9 @@ "name": "olmo-3.1-32b-think", "arena_name": "olmo-3.1-32b-think", "arena_org": "Ai2", - "arena_elo": 1285.68, - "arena_rank": 220, - "arena_votes": 8550, + "arena_elo": 1285.44, + "arena_rank": 222, + "arena_votes": 8544, "sources": { "arena_name": "arena", "arena_org": "arena", @@ -71897,8 +71983,8 @@ "name": "llama-3.1-nemotron-51b-instruct", "arena_name": "llama-3.1-nemotron-51b-instruct", "arena_org": "Nvidia", - "arena_elo": 1285.46, - "arena_rank": 221, + "arena_elo": 1285.32, + "arena_rank": 223, "arena_votes": 3749, "sources": { "arena_name": "arena", @@ -71912,8 +71998,8 @@ "name": "gemini-1.5-flash-001", "arena_name": "gemini-1.5-flash-001", "arena_org": "Google", - "arena_elo": 1285.21, - "arena_rank": 222, + "arena_elo": 1285.18, + "arena_rank": 224, "arena_votes": 62833, "sources": { "arena_name": "arena", @@ -71927,8 +72013,8 @@ "name": "nemotron-4-340b-instruct", "arena_name": "nemotron-4-340b-instruct", "arena_org": "Nvidia", - "arena_elo": 1276.43, - "arena_rank": 225, + "arena_elo": 1276.24, + "arena_rank": 227, "arena_votes": 19659, "sources": { "arena_name": "arena", @@ -71942,8 +72028,8 @@ "name": "llama-3-70b-instruct", "arena_name": "llama-3-70b-instruct", "arena_org": "Meta", - "arena_elo": 1275.29, - "arena_rank": 227, + "arena_elo": 1275.19, + "arena_rank": 229, "arena_votes": 156876, "sources": { "arena_name": "arena", @@ -71957,8 +72043,8 @@ "name": "mistral-small-24b-instruct-2501", "arena_name": "mistral-small-24b-instruct-2501", "arena_org": "Mistral", - "arena_elo": 1273.57, - "arena_rank": 229, + "arena_elo": 1273.47, + "arena_rank": 231, "arena_votes": 14681, "sources": { "arena_name": "arena", @@ -71972,8 +72058,8 @@ "name": "glm-4-0520", "arena_name": "glm-4-0520", "arena_org": "Zhipu AI", - "arena_elo": 1272.67, - "arena_rank": 230, + "arena_elo": 1272.53, + "arena_rank": 232, "arena_votes": 9788, "sources": { "arena_name": "arena", @@ -71987,8 +72073,8 @@ "name": "reka-flash-20240904", "arena_name": "reka-flash-20240904", "arena_org": "Reka AI", - "arena_elo": 1271.29, - "arena_rank": 231, + "arena_elo": 1271.16, + "arena_rank": 233, "arena_votes": 7536, "sources": { "arena_name": "arena", @@ -72002,8 +72088,8 @@ "name": "c4ai-aya-expanse-32b", "arena_name": "c4ai-aya-expanse-32b", "arena_org": "Cohere", - "arena_elo": 1266.39, - "arena_rank": 233, + "arena_elo": 1266.3, + "arena_rank": 235, "arena_votes": 27124, "sources": { "arena_name": "arena", @@ -72017,8 +72103,8 @@ "name": "amazon-nova-lite-v1.0", "arena_name": "amazon-nova-lite-v1.0", "arena_org": "Amazon", - "arena_elo": 1260.08, - "arena_rank": 239, + "arena_elo": 1259.97, + "arena_rank": 240, "arena_votes": 19372, "sources": { "arena_name": "arena", @@ -72032,8 +72118,8 @@ "name": "olmo-2-0325-32b-instruct", "arena_name": "olmo-2-0325-32b-instruct", "arena_org": "Ai2", - "arena_elo": 1251.32, - "arena_rank": 242, + "arena_elo": 1251.17, + "arena_rank": 244, "arena_votes": 3334, "sources": { "arena_name": "arena", @@ -72047,8 +72133,8 @@ "name": "amazon-nova-micro-v1.0", "arena_name": "amazon-nova-micro-v1.0", "arena_org": "Amazon", - "arena_elo": 1240.38, - "arena_rank": 245, + "arena_elo": 1240.26, + "arena_rank": 247, "arena_votes": 19364, "sources": { "arena_name": "arena", @@ -72062,8 +72148,8 @@ "name": "ministral-8b-2410", "arena_name": "ministral-8b-2410", "arena_org": "Mistral", - "arena_elo": 1236.71, - "arena_rank": 247, + "arena_elo": 1236.61, + "arena_rank": 249, "arena_votes": 4781, "sources": { "arena_name": "arena", @@ -72077,8 +72163,8 @@ "name": "gemini-pro-dev-api", "arena_name": "gemini-pro-dev-api", "arena_org": "Google", - "arena_elo": 1234.3, - "arena_rank": 248, + "arena_elo": 1234.23, + "arena_rank": 250, "arena_votes": 18354, "sources": { "arena_name": "arena", @@ -72092,8 +72178,8 @@ "name": "hunyuan-standard-256k", "arena_name": "hunyuan-standard-256k", "arena_org": "Tencent", - "arena_elo": 1233.09, - "arena_rank": 250, + "arena_elo": 1232.96, + "arena_rank": 252, "arena_votes": 2728, "sources": { "arena_name": "arena", @@ -72107,8 +72193,8 @@ "name": "reka-flash-21b-20240226-online", "arena_name": "reka-flash-21b-20240226-online", "arena_org": "Reka AI", - "arena_elo": 1232.32, - "arena_rank": 251, + "arena_elo": 1232.16, + "arena_rank": 253, "arena_votes": 15450, "sources": { "arena_name": "arena", @@ -72122,8 +72208,8 @@ "name": "reka-flash-21b-20240226", "arena_name": "reka-flash-21b-20240226", "arena_org": "Reka AI", - "arena_elo": 1225.57, - "arena_rank": 255, + "arena_elo": 1225.41, + "arena_rank": 257, "arena_votes": 24806, "sources": { "arena_name": "arena", @@ -72137,8 +72223,8 @@ "name": "c4ai-aya-expanse-8b", "arena_name": "c4ai-aya-expanse-8b", "arena_org": "Cohere", - "arena_elo": 1222.35, - "arena_rank": 258, + "arena_elo": 1222.26, + "arena_rank": 259, "arena_votes": 9818, "sources": { "arena_name": "arena", @@ -72152,8 +72238,8 @@ "name": "mistral-medium", "arena_name": "mistral-medium", "arena_org": "Mistral", - "arena_elo": 1221.99, - "arena_rank": 259, + "arena_elo": 1221.77, + "arena_rank": 261, "arena_votes": 34550, "sources": { "arena_name": "arena", @@ -72167,8 +72253,8 @@ "name": "gemini-pro", "arena_name": "gemini-pro", "arena_org": "Google", - "arena_elo": 1220.99, - "arena_rank": 260, + "arena_elo": 1220.9, + "arena_rank": 262, "arena_votes": 6390, "sources": { "arena_name": "arena", @@ -72182,8 +72268,8 @@ "name": "gpt-3.5-turbo-1106", "arena_name": "gpt-3.5-turbo-1106", "arena_org": "OpenAI", - "arena_elo": 1201.47, - "arena_rank": 267, + "arena_elo": 1201.31, + "arena_rank": 269, "arena_votes": 16619, "sources": { "arena_name": "arena", @@ -72199,8 +72285,8 @@ "name": "dbrx-instruct-preview", "arena_name": "dbrx-instruct-preview", "arena_org": "Databricks", - "arena_elo": 1194.06, - "arena_rank": 271, + "arena_elo": 1193.86, + "arena_rank": 273, "arena_votes": 32191, "sources": { "arena_name": "arena", @@ -72214,8 +72300,8 @@ "name": "wizardlm-70b", "arena_name": "wizardlm-70b", "arena_org": "Microsoft", - "arena_elo": 1183.65, - "arena_rank": 274, + "arena_elo": 1183.46, + "arena_rank": 276, "arena_votes": 8214, "sources": { "arena_name": "arena", @@ -72229,8 +72315,8 @@ "name": "snowflake-arctic-instruct", "arena_name": "snowflake-arctic-instruct", "arena_org": "Snowflake", - "arena_elo": 1178.47, - "arena_rank": 281, + "arena_elo": 1178.28, + "arena_rank": 283, "arena_votes": 32832, "sources": { "arena_name": "arena", @@ -72244,8 +72330,8 @@ "name": "tulu-2-dpo-70b", "arena_name": "tulu-2-dpo-70b", "arena_org": "AllenAI/UW", - "arena_elo": 1177, - "arena_rank": 283, + "arena_elo": 1176.78, + "arena_rank": 285, "arena_votes": 6535, "sources": { "arena_name": "arena", @@ -72259,8 +72345,8 @@ "name": "vicuna-33b", "arena_name": "vicuna-33b", "arena_org": "LMSYS", - "arena_elo": 1171.75, - "arena_rank": 285, + "arena_elo": 1171.56, + "arena_rank": 287, "arena_votes": 22479, "sources": { "arena_name": "arena", @@ -72274,8 +72360,8 @@ "name": "llama-2-70b-chat", "arena_name": "llama-2-70b-chat", "arena_org": "Meta", - "arena_elo": 1169.79, - "arena_rank": 288, + "arena_elo": 1169.61, + "arena_rank": 290, "arena_votes": 38492, "sources": { "arena_name": "arena", @@ -72289,8 +72375,8 @@ "name": "llama2-70b-steerlm-chat", "arena_name": "llama2-70b-steerlm-chat", "arena_org": "Nvidia", - "arena_elo": 1154.28, - "arena_rank": 294, + "arena_elo": 1154.04, + "arena_rank": 296, "arena_votes": 3585, "sources": { "arena_name": "arena", @@ -72304,8 +72390,8 @@ "name": "dolphin-2.2.1-mistral-7b", "arena_name": "dolphin-2.2.1-mistral-7b", "arena_org": "Cognitive Computations", - "arena_elo": 1150.97, - "arena_rank": 296, + "arena_elo": 1150.78, + "arena_rank": 298, "arena_votes": 1679, "sources": { "arena_name": "arena", @@ -72319,8 +72405,8 @@ "name": "mpt-30b-chat", "arena_name": "mpt-30b-chat", "arena_org": "MosaicML", - "arena_elo": 1149.06, - "arena_rank": 297, + "arena_elo": 1148.88, + "arena_rank": 299, "arena_votes": 2572, "sources": { "arena_name": "arena", @@ -72334,8 +72420,8 @@ "name": "wizardlm-13b", "arena_name": "wizardlm-13b", "arena_org": "Microsoft", - "arena_elo": 1148.17, - "arena_rank": 299, + "arena_elo": 1147.98, + "arena_rank": 301, "arena_votes": 7044, "sources": { "arena_name": "arena", @@ -72349,8 +72435,8 @@ "name": "falcon-180b-chat", "arena_name": "falcon-180b-chat", "arena_org": "TII", - "arena_elo": 1146.01, - "arena_rank": 300, + "arena_elo": 1145.83, + "arena_rank": 302, "arena_votes": 1295, "sources": { "arena_name": "arena", @@ -72364,8 +72450,8 @@ "name": "phi-3-mini-4k-instruct-june-2024", "arena_name": "phi-3-mini-4k-instruct-june-2024", "arena_org": "Microsoft", - "arena_elo": 1142.12, - "arena_rank": 302, + "arena_elo": 1141.93, + "arena_rank": 304, "arena_votes": 12297, "sources": { "arena_name": "arena", @@ -72379,8 +72465,8 @@ "name": "llama-2-13b-chat", "arena_name": "llama-2-13b-chat", "arena_org": "Meta", - "arena_elo": 1140.5, - "arena_rank": 303, + "arena_elo": 1140.32, + "arena_rank": 305, "arena_votes": 19174, "sources": { "arena_name": "arena", @@ -72394,8 +72480,8 @@ "name": "vicuna-13b", "arena_name": "vicuna-13b", "arena_org": "LMSYS", - "arena_elo": 1139.88, - "arena_rank": 304, + "arena_elo": 1139.69, + "arena_rank": 306, "arena_votes": 19367, "sources": { "arena_name": "arena", @@ -72409,8 +72495,8 @@ "name": "qwen-14b-chat", "arena_name": "qwen-14b-chat", "arena_org": "Alibaba", - "arena_elo": 1137.54, - "arena_rank": 305, + "arena_elo": 1137.35, + "arena_rank": 307, "arena_votes": 4964, "sources": { "arena_name": "arena", @@ -72424,8 +72510,8 @@ "name": "palm-2", "arena_name": "palm-2", "arena_org": "Google", - "arena_elo": 1136.28, - "arena_rank": 306, + "arena_elo": 1136.13, + "arena_rank": 308, "arena_votes": 8554, "sources": { "arena_name": "arena", @@ -72439,8 +72525,8 @@ "name": "codellama-34b-instruct", "arena_name": "codellama-34b-instruct", "arena_org": "Meta", - "arena_elo": 1135.53, - "arena_rank": 307, + "arena_elo": 1135.35, + "arena_rank": 310, "arena_votes": 7366, "sources": { "arena_name": "arena", @@ -72454,8 +72540,8 @@ "name": "guanaco-33b", "arena_name": "guanaco-33b", "arena_org": "UW", - "arena_elo": 1126.26, - "arena_rank": 312, + "arena_elo": 1126.06, + "arena_rank": 314, "arena_votes": 2921, "sources": { "arena_name": "arena", @@ -72469,8 +72555,8 @@ "name": "stripedhyena-nous-7b", "arena_name": "stripedhyena-nous-7b", "arena_org": "Together AI", - "arena_elo": 1119.94, - "arena_rank": 314, + "arena_elo": 1119.75, + "arena_rank": 316, "arena_votes": 5182, "sources": { "arena_name": "arena", @@ -72484,8 +72570,8 @@ "name": "codellama-70b-instruct", "arena_name": "codellama-70b-instruct", "arena_org": "Meta", - "arena_elo": 1118.09, - "arena_rank": 315, + "arena_elo": 1117.93, + "arena_rank": 317, "arena_votes": 1143, "sources": { "arena_name": "arena", @@ -72499,8 +72585,8 @@ "name": "vicuna-7b", "arena_name": "vicuna-7b", "arena_org": "LMSYS", - "arena_elo": 1113.59, - "arena_rank": 316, + "arena_elo": 1113.41, + "arena_rank": 319, "arena_votes": 6923, "sources": { "arena_name": "arena", @@ -72514,8 +72600,8 @@ "name": "mistral-7b-instruct", "arena_name": "mistral-7b-instruct", "arena_org": "Mistral", - "arena_elo": 1108.57, - "arena_rank": 320, + "arena_elo": 1108.38, + "arena_rank": 322, "arena_votes": 8977, "sources": { "arena_name": "arena", @@ -72529,8 +72615,8 @@ "name": "llama-2-7b-chat", "arena_name": "llama-2-7b-chat", "arena_org": "Meta", - "arena_elo": 1107.13, - "arena_rank": 321, + "arena_elo": 1106.94, + "arena_rank": 323, "arena_votes": 14148, "sources": { "arena_name": "arena", @@ -72544,8 +72630,8 @@ "name": "olmo-7b-instruct", "arena_name": "olmo-7b-instruct", "arena_org": "Ai2", - "arena_elo": 1073.53, - "arena_rank": 324, + "arena_elo": 1073.31, + "arena_rank": 326, "arena_votes": 6328, "sources": { "arena_name": "arena", @@ -72559,8 +72645,8 @@ "name": "koala-13b", "arena_name": "koala-13b", "arena_org": "UC Berkeley", - "arena_elo": 1069.36, - "arena_rank": 325, + "arena_elo": 1069.17, + "arena_rank": 327, "arena_votes": 6965, "sources": { "arena_name": "arena", @@ -72574,8 +72660,8 @@ "name": "alpaca-13b", "arena_name": "alpaca-13b", "arena_org": "Stanford", - "arena_elo": 1066.43, - "arena_rank": 326, + "arena_elo": 1066.3, + "arena_rank": 328, "arena_votes": 5745, "sources": { "arena_name": "arena", @@ -72589,8 +72675,8 @@ "name": "gpt4all-13b-snoozy", "arena_name": "gpt4all-13b-snoozy", "arena_org": "Nomic AI", - "arena_elo": 1064.94, - "arena_rank": 327, + "arena_elo": 1064.78, + "arena_rank": 329, "arena_votes": 1743, "sources": { "arena_name": "arena", @@ -72604,8 +72690,8 @@ "name": "mpt-7b-chat", "arena_name": "mpt-7b-chat", "arena_org": "MosaicML", - "arena_elo": 1060.78, - "arena_rank": 328, + "arena_elo": 1060.62, + "arena_rank": 330, "arena_votes": 3924, "sources": { "arena_name": "arena", @@ -72619,8 +72705,8 @@ "name": "chatglm3-6b", "arena_name": "chatglm3-6b", "arena_org": "Tsinghua", - "arena_elo": 1054.98, - "arena_rank": 329, + "arena_elo": 1054.78, + "arena_rank": 331, "arena_votes": 4658, "sources": { "arena_name": "arena", @@ -72634,8 +72720,8 @@ "name": "RWKV-4-Raven-14B", "arena_name": "RWKV-4-Raven-14B", "arena_org": "RWKV", - "arena_elo": 1040.25, - "arena_rank": 330, + "arena_elo": 1040.08, + "arena_rank": 332, "arena_votes": 4845, "sources": { "arena_name": "arena", @@ -72649,8 +72735,8 @@ "name": "chatglm2-6b", "arena_name": "chatglm2-6b", "arena_org": "Tsinghua", - "arena_elo": 1023.09, - "arena_rank": 331, + "arena_elo": 1022.9, + "arena_rank": 333, "arena_votes": 2658, "sources": { "arena_name": "arena", @@ -72664,8 +72750,8 @@ "name": "oasst-pythia-12b", "arena_name": "oasst-pythia-12b", "arena_org": "OpenAssistant", - "arena_elo": 1021.01, - "arena_rank": 332, + "arena_elo": 1020.84, + "arena_rank": 334, "arena_votes": 6310, "sources": { "arena_name": "arena", @@ -72679,8 +72765,8 @@ "name": "chatglm-6b", "arena_name": "chatglm-6b", "arena_org": "Tsinghua", - "arena_elo": 994.492, - "arena_rank": 333, + "arena_elo": 994.294, + "arena_rank": 335, "arena_votes": 4914, "sources": { "arena_name": "arena", @@ -72694,8 +72780,8 @@ "name": "fastchat-t5-3b", "arena_name": "fastchat-t5-3b", "arena_org": "LMSYS", - "arena_elo": 990.269, - "arena_rank": 334, + "arena_elo": 990.113, + "arena_rank": 336, "arena_votes": 4203, "sources": { "arena_name": "arena", @@ -72709,8 +72795,8 @@ "name": "stablelm-tuned-alpha-7b", "arena_name": "stablelm-tuned-alpha-7b", "arena_org": "Stability AI", - "arena_elo": 951.532, - "arena_rank": 337, + "arena_elo": 951.347, + "arena_rank": 339, "arena_votes": 3287, "sources": { "arena_name": "arena",