github-actions[bot] commited on
Commit
ca5f4c2
·
1 Parent(s): 4472bda

chore: update benchmark data [skip ci]

Browse files
Files changed (1) hide show
  1. data/benchmarks.json +1068 -915
data/benchmarks.json CHANGED
@@ -7,8 +7,8 @@
7
  "gpqa": 0.369,
8
  "arc": 0.93,
9
  "gsm8k": 0.87,
10
- "arena_elo": 1289.12,
11
- "arena_rank": 201,
12
  "arena_votes": 8662
13
  },
14
  {
@@ -19,8 +19,8 @@
19
  "gpqa": 0.323,
20
  "arc": 0.857,
21
  "gsm8k": 0.758,
22
- "arena_elo": 1239.3,
23
- "arena_rank": 233,
24
  "arena_votes": 8858
25
  },
26
  {
@@ -82,9 +82,9 @@
82
  "lb_language": 0.39707333333333333,
83
  "lb_if": 0.6187925,
84
  "lb_data_analysis": 0.5411900000000001,
85
- "arena_elo": 1323.7,
86
- "arena_rank": 166,
87
- "arena_votes": 70889,
88
  "aider_pass_rate": 0.617
89
  },
90
  {
@@ -106,8 +106,8 @@
106
  "lb_language": 0.56937,
107
  "lb_if": 0.7229999999999999,
108
  "lb_data_analysis": 0.5411,
109
- "arena_elo": 1342.62,
110
- "arena_rank": 143,
111
  "arena_votes": 82419,
112
  "aider_pass_rate": 0.5710000000000001
113
  },
@@ -132,9 +132,9 @@
132
  "lb_language": 0.54477,
133
  "lb_if": 0.69296,
134
  "lb_data_analysis": 0.5618650000000001,
135
- "arena_elo": 1372.48,
136
- "arena_rank": 110,
137
- "arena_votes": 89218,
138
  "aider_pass_rate": 0.6920000000000001
139
  },
140
  {
@@ -157,8 +157,8 @@
157
  "lb_language": 0.30073333333333335,
158
  "lb_if": 0.6402924999999999,
159
  "lb_data_analysis": 0.3731,
160
- "arena_elo": 1261.21,
161
- "arena_rank": 225,
162
  "arena_votes": 117701,
163
  "aider_pass_rate": 0.406
164
  },
@@ -183,8 +183,8 @@
183
  "lb_language": 0.53574,
184
  "lb_if": 0.6388750000000001,
185
  "lb_data_analysis": 0.5784,
186
- "arena_elo": 1322.06,
187
- "arena_rank": 170,
188
  "arena_votes": 194909,
189
  "aider_pass_rate": 0.534
190
  },
@@ -209,8 +209,8 @@
209
  "lb_language": 0.38083333333333336,
210
  "lb_if": 0.6500425,
211
  "lb_data_analysis": 0.38839999999999997,
212
- "arena_elo": 1281.17,
213
- "arena_rank": 210,
214
  "arena_votes": 109284,
215
  "aider_pass_rate": 0.436
216
  },
@@ -228,8 +228,8 @@
228
  "lb_language": 0.14644333333333334,
229
  "lb_if": 0.571625,
230
  "lb_data_analysis": 0.2354,
231
- "arena_elo": 1227.12,
232
- "arena_rank": 241,
233
  "arena_votes": 54036
234
  },
235
  {
@@ -249,8 +249,8 @@
249
  "lb_language": 0.5477066666666667,
250
  "lb_if": 0.8050825,
251
  "lb_data_analysis": 0.69625,
252
- "arena_elo": 1398.17,
253
- "arena_rank": 82,
254
  "arena_votes": 18524
255
  },
256
  {
@@ -268,8 +268,8 @@
268
  "lb_language": 0.3518266666666667,
269
  "lb_if": 0.6915024999999999,
270
  "lb_data_analysis": 0.4417,
271
- "arena_elo": 1307.44,
272
- "arena_rank": 189,
273
  "arena_votes": 24572,
274
  "aider_pass_rate": 0.5489999999999999
275
  },
@@ -289,8 +289,8 @@
289
  "lb_language": 0.47484666666666664,
290
  "lb_if": 0.75246,
291
  "lb_data_analysis": 0.6241,
292
- "arena_elo": 1358.95,
293
- "arena_rank": 122,
294
  "arena_votes": 21770
295
  },
296
  {
@@ -385,8 +385,8 @@
385
  "lb_language": 0.32621666666666665,
386
  "lb_if": 0.5810025000000001,
387
  "lb_data_analysis": 0.4481,
388
- "arena_elo": 1288.44,
389
- "arena_rank": 202,
390
  "arena_votes": 75754
391
  },
392
  {
@@ -415,8 +415,8 @@
415
  "lb_language": 0.25531,
416
  "lb_if": 0.52621,
417
  "lb_data_analysis": 0.2959,
418
- "arena_elo": 1265.9,
419
- "arena_rank": 221,
420
  "arena_votes": 54611
421
  },
422
  {
@@ -452,8 +452,8 @@
452
  "hf_math_lvl5": 0.3806646525679758,
453
  "hf_musr": 0.45806250000000004,
454
  "hf_avg": 43.409948245645786,
455
- "arena_elo": 1293.79,
456
- "arena_rank": 199,
457
  "arena_votes": 55240,
458
  "aider_pass_rate": 0.436
459
  },
@@ -477,8 +477,8 @@
477
  "hf_math_lvl5": 0.1729607250755287,
478
  "hf_musr": 0.3845416666666666,
479
  "hf_avg": 28.01011138792457,
480
- "arena_elo": 1211.91,
481
- "arena_rank": 251,
482
  "arena_votes": 49605,
483
  "aider_pass_rate": 0.263
484
  },
@@ -509,8 +509,8 @@
509
  "hf_math_lvl5": 0.17673716012084592,
510
  "hf_musr": 0.3528541666666667,
511
  "hf_avg": 24.204650807793456,
512
- "arena_elo": 1166.89,
513
- "arena_rank": 277,
514
  "arena_votes": 7936
515
  },
516
  {
@@ -538,9 +538,9 @@
538
  "hf_math_lvl5": 0.48338368580060426,
539
  "hf_musr": 0.44612500000000005,
540
  "hf_avg": 44.84747145129876,
541
- "arena_elo": 1319.31,
542
- "arena_rank": 175,
543
- "arena_votes": 55372,
544
  "aider_pass_rate": 0.42100000000000004
545
  },
546
  {
@@ -628,8 +628,8 @@
628
  "lb_language": 0.29333666666666663,
629
  "lb_if": 0.5838349999999999,
630
  "lb_data_analysis": 0.4376,
631
- "arena_elo": 1256.41,
632
- "arena_rank": 228,
633
  "arena_votes": 24126
634
  },
635
  {
@@ -729,8 +729,8 @@
729
  "lb_language": 0.31805,
730
  "lb_if": 0.6957099999999999,
731
  "lb_data_analysis": 0.33599999999999997,
732
- "arena_elo": 1299.15,
733
- "arena_rank": 197,
734
  "arena_votes": 7140
735
  },
736
  {
@@ -750,8 +750,8 @@
750
  "lb_language": 0.2421633333333333,
751
  "lb_if": 0.604665,
752
  "lb_data_analysis": 0.3682,
753
- "arena_elo": 1224.17,
754
- "arena_rank": 243,
755
  "arena_votes": 66207,
756
  "aider_pass_rate": 0.414
757
  },
@@ -773,8 +773,8 @@
773
  "lb_language": 0.4956833333333333,
774
  "lb_if": 0.717875,
775
  "lb_data_analysis": 0.39039999999999997,
776
- "arena_elo": 1275.27,
777
- "arena_rank": 215,
778
  "arena_votes": 88723,
779
  "aider_pass_rate": 0.466
780
  },
@@ -794,8 +794,8 @@
794
  "lb_language": 0.45262,
795
  "lb_if": 0.713875,
796
  "lb_data_analysis": 0.4998,
797
- "arena_elo": 1324.49,
798
- "arena_rank": 164,
799
  "arena_votes": 98114
800
  },
801
  {
@@ -815,8 +815,8 @@
815
  "lb_language": 0.5393533333333334,
816
  "lb_if": 0.7217100000000001,
817
  "lb_data_analysis": 0.4661,
818
- "arena_elo": 1346.07,
819
- "arena_rank": 141,
820
  "arena_votes": 112881,
821
  "aider_pass_rate": 0.602
822
  },
@@ -834,8 +834,8 @@
834
  "lb_language": 0.4563466666666667,
835
  "lb_if": 0.6858299999999999,
836
  "lb_data_analysis": 0.6236999999999999,
837
- "arena_elo": 1335.3,
838
- "arena_rank": 153,
839
  "arena_votes": 45499,
840
  "aider_pass_rate": 0.5710000000000001
841
  },
@@ -857,9 +857,9 @@
857
  "lb_language": 0.29879333333333336,
858
  "lb_if": 0.5679974999999999,
859
  "lb_data_analysis": 0.55099,
860
- "arena_elo": 1318.01,
861
- "arena_rank": 178,
862
- "arena_votes": 68794,
863
  "aider_pass_rate": 0.406
864
  },
865
  {
@@ -880,8 +880,8 @@
880
  "hf_math_lvl5": 0.37462235649546827,
881
  "hf_musr": 0.41384375,
882
  "hf_avg": 27.639223265636087,
883
- "arena_elo": 1402.43,
884
- "arena_rank": 76,
885
  "arena_votes": 27807,
886
  "aider_pass_rate": 0.654
887
  },
@@ -892,8 +892,8 @@
892
  "mmlu": 0.852,
893
  "gpqa": 0.6,
894
  "math": 0.9,
895
- "arena_elo": 1337.26,
896
- "arena_rank": 149,
897
  "arena_votes": 51981,
898
  "aider_pass_rate": 0.5
899
  },
@@ -904,8 +904,8 @@
904
  "mmlu": 0.908,
905
  "gpqa": 0.733,
906
  "mgsm": 0.908,
907
- "arena_elo": 1388.52,
908
- "arena_rank": 94,
909
  "arena_votes": 31122,
910
  "aider_pass_rate": 0.579
911
  },
@@ -921,9 +921,9 @@
921
  "mmlu": 0.869,
922
  "math": 0.979,
923
  "mgsm": 0.92,
924
- "arena_elo": 1348.64,
925
- "arena_rank": 133,
926
- "arena_votes": 58329
927
  },
928
  {
929
  "slug": "openai/o3",
@@ -997,8 +997,8 @@
997
  "lb_language": 0.38114999999999993,
998
  "lb_if": 0.7550025,
999
  "lb_data_analysis": 0.4718,
1000
- "arena_elo": 1303.15,
1001
- "arena_rank": 196,
1002
  "arena_votes": 39406
1003
  },
1004
  {
@@ -1044,8 +1044,8 @@
1044
  "lb_language": 0.23245333333333332,
1045
  "lb_if": 0.5869175,
1046
  "lb_data_analysis": 0.48810000000000003,
1047
- "arena_elo": 1270.89,
1048
- "arena_rank": 219,
1049
  "arena_votes": 5432,
1050
  "aider_pass_rate": 0.594
1051
  },
@@ -1096,8 +1096,8 @@
1096
  "lb_language": 0.29213666666666666,
1097
  "lb_if": 0.68271,
1098
  "lb_data_analysis": 0.1636,
1099
- "arena_elo": 1262.04,
1100
- "arena_rank": 224,
1101
  "arena_votes": 37325,
1102
  "aider_pass_rate": 0.444
1103
  },
@@ -1160,8 +1160,8 @@
1160
  "lb_language": 0.21091000000000001,
1161
  "lb_if": 0.35587499999999994,
1162
  "lb_data_analysis": 0.25925,
1163
- "arena_elo": 1157.2,
1164
- "arena_rank": 279,
1165
  "arena_votes": 3231
1166
  },
1167
  {
@@ -1263,8 +1263,8 @@
1263
  "hf_math_lvl5": 0.277190332326284,
1264
  "hf_musr": 0.4281979166666667,
1265
  "hf_avg": 33.35799367075618,
1266
- "arena_elo": 1213.65,
1267
- "arena_rank": 249,
1268
  "arena_votes": 24146
1269
  },
1270
  {
@@ -1386,8 +1386,8 @@
1386
  "hf_math_lvl5": 0.06268882175226587,
1387
  "hf_musr": 0.39784375,
1388
  "hf_avg": 24.226662652803373,
1389
- "arena_elo": 1184.01,
1390
- "arena_rank": 263,
1391
  "arena_votes": 15483
1392
  },
1393
  {
@@ -1673,8 +1673,8 @@
1673
  "hf_math_lvl5": 0.03851963746223565,
1674
  "hf_musr": 0.47709375000000004,
1675
  "hf_avg": 14.343669671742774,
1676
- "arena_elo": 1223.4,
1677
- "arena_rank": 244,
1678
  "arena_votes": 104642
1679
  },
1680
  {
@@ -6142,8 +6142,8 @@
6142
  "lb_language": 0.07196666666666666,
6143
  "lb_if": 0.5279175,
6144
  "lb_data_analysis": 0.081,
6145
- "arena_elo": 1127.04,
6146
- "arena_rank": 300,
6147
  "arena_votes": 1785
6148
  },
6149
  {
@@ -6164,8 +6164,8 @@
6164
  "lb_language": 0.042846666666666665,
6165
  "lb_if": 0.48317,
6166
  "lb_data_analysis": 0.0762,
6167
- "arena_elo": 1131.19,
6168
- "arena_rank": 296,
6169
  "arena_votes": 11118
6170
  },
6171
  {
@@ -6191,8 +6191,8 @@
6191
  "hf_math_lvl5": 0.20468277945619334,
6192
  "hf_musr": 0.4465208333333333,
6193
  "hf_avg": 34.125963384670946,
6194
- "arena_elo": 1212.91,
6195
- "arena_rank": 250,
6196
  "arena_votes": 4652
6197
  },
6198
  {
@@ -6290,8 +6290,8 @@
6290
  "hf_math_lvl5": 0.0581570996978852,
6291
  "hf_musr": 0.342125,
6292
  "hf_avg": 15.02227766709556,
6293
- "arena_elo": 1114.48,
6294
- "arena_rank": 304,
6295
  "arena_votes": 2199
6296
  },
6297
  {
@@ -10127,8 +10127,8 @@
10127
  "hf_math_lvl5": 0.12235649546827794,
10128
  "hf_musr": 0.4595416666666667,
10129
  "hf_avg": 27.353190438571634,
10130
- "arena_elo": 1164.89,
10131
- "arena_rank": 278,
10132
  "arena_votes": 3777
10133
  },
10134
  {
@@ -11176,9 +11176,9 @@
11176
  "lb_language": 0.5148133333333332,
11177
  "lb_if": 0.81829,
11178
  "lb_data_analysis": 0.69529,
11179
- "arena_elo": 1336.26,
11180
- "arena_rank": 150,
11181
- "arena_votes": 25934
11182
  },
11183
  {
11184
  "hf_id": "Qwen/Qwen1.5-0.5B",
@@ -11272,8 +11272,8 @@
11272
  "lb_language": 0.13224333333333332,
11273
  "lb_if": 0.5526275,
11274
  "lb_data_analysis": 0.20179999999999998,
11275
- "arena_elo": 1234.26,
11276
- "arena_rank": 236,
11277
  "arena_votes": 26195,
11278
  "aider_pass_rate": 0.308
11279
  },
@@ -11300,8 +11300,8 @@
11300
  "hf_math_lvl5": 0.15256797583081572,
11301
  "hf_musr": 0.43997916666666664,
11302
  "hf_avg": 23.566106475051374,
11303
- "arena_elo": 1191.11,
11304
- "arena_rank": 260,
11305
  "arena_votes": 17839
11306
  },
11307
  {
@@ -11327,8 +11327,8 @@
11327
  "hf_math_lvl5": 0.19561933534743203,
11328
  "hf_musr": 0.4159791666666666,
11329
  "hf_avg": 29.25746822860332,
11330
- "arena_elo": 1204.03,
11331
- "arena_rank": 253,
11332
  "arena_votes": 21741
11333
  },
11334
  {
@@ -11361,8 +11361,8 @@
11361
  "lb_language": 0.05798333333333333,
11362
  "lb_if": 0.27749999999999997,
11363
  "lb_data_analysis": 0.0469,
11364
- "arena_elo": 1090.29,
11365
- "arena_rank": 310,
11366
  "arena_votes": 7597
11367
  },
11368
  {
@@ -11395,8 +11395,8 @@
11395
  "lb_language": 0.061816666666666666,
11396
  "lb_if": 0.4411675,
11397
  "lb_data_analysis": 0.0435,
11398
- "arena_elo": 1143.95,
11399
- "arena_rank": 288,
11400
  "arena_votes": 4737
11401
  },
11402
  {
@@ -16644,8 +16644,8 @@
16644
  "hf_math_lvl5": 0.4501510574018127,
16645
  "hf_musr": 0.4948333333333334,
16646
  "hf_avg": 42.33178738532094,
16647
- "arena_elo": 1286.91,
16648
- "arena_rank": 206,
16649
  "arena_votes": 2846
16650
  },
16651
  {
@@ -16695,8 +16695,8 @@
16695
  "hf_math_lvl5": 0.19637462235649547,
16696
  "hf_musr": 0.41746875,
16697
  "hf_avg": 26.034998081672143,
16698
- "arena_elo": 1221.4,
16699
- "arena_rank": 248,
16700
  "arena_votes": 2896
16701
  },
16702
  {
@@ -18637,8 +18637,8 @@
18637
  "hf_math_lvl5": 0.08383685800604229,
18638
  "hf_musr": 0.41201041666666666,
18639
  "hf_avg": 20.83936104726783,
18640
- "arena_elo": 1167.69,
18641
- "arena_rank": 276,
18642
  "arena_votes": 10224
18643
  },
18644
  {
@@ -19608,8 +19608,8 @@
19608
  "hf_math_lvl5": 0.013595166163141994,
19609
  "hf_musr": 0.37390625000000005,
19610
  "hf_avg": 6.3704357034963754,
19611
- "arena_elo": 980.138,
19612
- "arena_rank": 322,
19613
  "arena_votes": 3412
19614
  },
19615
  {
@@ -19759,8 +19759,8 @@
19759
  "hf_math_lvl5": 0.09290030211480363,
19760
  "hf_musr": 0.5058645833333334,
19761
  "hf_avg": 27.310631874736753,
19762
- "arena_elo": 1184.54,
19763
- "arena_rank": 262,
19764
  "arena_votes": 4932
19765
  },
19766
  {
@@ -21237,8 +21237,8 @@
21237
  "hf_math_lvl5": 0.01812688821752266,
21238
  "hf_musr": 0.33939583333333334,
21239
  "hf_avg": 8.053373854341979,
21240
- "arena_elo": 1114.42,
21241
- "arena_rank": 305,
21242
  "arena_votes": 10854
21243
  },
21244
  {
@@ -21259,8 +21259,8 @@
21259
  "lb_language": 0.10647333333333332,
21260
  "lb_if": 0.443375,
21261
  "lb_data_analysis": 0.0726,
21262
- "arena_elo": 1180.52,
21263
- "arena_rank": 267,
21264
  "arena_votes": 23893
21265
  },
21266
  {
@@ -21298,8 +21298,8 @@
21298
  "hf_math_lvl5": 0.0007552870090634441,
21299
  "hf_musr": 0.39288541666666665,
21300
  "hf_avg": 17.046939294966545,
21301
- "arena_elo": 1199.3,
21302
- "arena_rank": 255,
21303
  "arena_votes": 46616
21304
  },
21305
  {
@@ -21349,8 +21349,8 @@
21349
  "hf_math_lvl5": 0.02039274924471299,
21350
  "hf_musr": 0.334125,
21351
  "hf_avg": 7.485804130315127,
21352
- "arena_elo": 1091.89,
21353
- "arena_rank": 309,
21354
  "arena_votes": 4780
21355
  },
21356
  {
@@ -21376,8 +21376,8 @@
21376
  "hf_math_lvl5": 0.02945619335347432,
21377
  "hf_musr": 0.42742708333333335,
21378
  "hf_avg": 13.067087110466217,
21379
- "arena_elo": 1136.28,
21380
- "arena_rank": 295,
21381
  "arena_votes": 8925
21382
  },
21383
  {
@@ -22381,8 +22381,8 @@
22381
  "hf_math_lvl5": 0.02039274924471299,
22382
  "hf_musr": 0.34621875,
22383
  "hf_avg": 9.39218439885523,
22384
- "arena_elo": 972.199,
22385
- "arena_rank": 323,
22386
  "arena_votes": 2391
22387
  },
22388
  {
@@ -22696,8 +22696,8 @@
22696
  "hf_math_lvl5": 0.09214501510574018,
22697
  "hf_musr": 0.35148958333333336,
22698
  "hf_avg": 18.396095114284222,
22699
- "arena_elo": 1156.2,
22700
- "arena_rank": 280,
22701
  "arena_votes": 6837
22702
  },
22703
  {
@@ -22747,8 +22747,8 @@
22747
  "hf_math_lvl5": 0.1419939577039275,
22748
  "hf_musr": 0.3900625,
22749
  "hf_avg": 24.027678753483297,
22750
- "arena_elo": 1182.2,
22751
- "arena_rank": 266,
22752
  "arena_votes": 6638
22753
  },
22754
  {
@@ -22798,8 +22798,8 @@
22798
  "hf_math_lvl5": 0.15256797583081572,
22799
  "hf_musr": 0.3605416666666667,
22800
  "hf_avg": 21.712212822028288,
22801
- "arena_elo": 1179.18,
22802
- "arena_rank": 269,
22803
  "arena_votes": 3188
22804
  },
22805
  {
@@ -22849,8 +22849,8 @@
22849
  "hf_math_lvl5": 0.21978851963746224,
22850
  "hf_musr": 0.47070833333333334,
22851
  "hf_avg": 30.6030430081627,
22852
- "arena_elo": 1208.66,
22853
- "arena_rank": 252,
22854
  "arena_votes": 3090
22855
  },
22856
  {
@@ -23318,8 +23318,8 @@
23318
  "hf_math_lvl5": 0.4078549848942598,
23319
  "hf_musr": 0.4558229166666667,
23320
  "hf_avg": 38.87959582082076,
23321
- "arena_elo": 1191.6,
23322
- "arena_rank": 259,
23323
  "arena_votes": 9901
23324
  },
23325
  {
@@ -25538,8 +25538,8 @@
25538
  "hf_math_lvl5": 0.0702416918429003,
25539
  "hf_musr": 0.3328541666666667,
25540
  "hf_avg": 14.443126333711135,
25541
- "arena_elo": 1111.46,
25542
- "arena_rank": 306,
25543
  "arena_votes": 8045
25544
  },
25545
  {
@@ -25719,8 +25719,8 @@
25719
  "lb_language": 0.13909000000000002,
25720
  "lb_if": 0.5330400000000001,
25721
  "lb_data_analysis": 0.2044,
25722
- "arena_elo": 1198.15,
25723
- "arena_rank": 256,
25724
  "arena_votes": 25055
25725
  },
25726
  {
@@ -25741,8 +25741,8 @@
25741
  "lb_language": 0.09153666666666667,
25742
  "lb_if": 0.39083500000000004,
25743
  "lb_data_analysis": 0.26030000000000003,
25744
- "arena_elo": 1129.35,
25745
- "arena_rank": 297,
25746
  "arena_votes": 20685
25747
  },
25748
  {
@@ -25763,8 +25763,8 @@
25763
  "lb_language": 0.08559,
25764
  "lb_if": 0.363625,
25765
  "lb_data_analysis": 0.2232,
25766
- "arena_elo": 1128.57,
25767
- "arena_rank": 298,
25768
  "arena_votes": 20118
25769
  },
25770
  {
@@ -25823,8 +25823,8 @@
25823
  "lb_language": 0.12944,
25824
  "lb_if": 0.472,
25825
  "lb_data_analysis": 0.2343,
25826
- "arena_elo": 1171.27,
25827
- "arena_rank": 274,
25828
  "arena_votes": 17766
25829
  },
25830
  {
@@ -26072,8 +26072,8 @@
26072
  "lb_language": 0.09055,
26073
  "lb_if": 0.5165025,
26074
  "lb_data_analysis": 0.059300000000000005,
26075
- "arena_elo": 1149.76,
26076
- "arena_rank": 285,
26077
  "arena_votes": 19402
26078
  },
26079
  {
@@ -26197,8 +26197,8 @@
26197
  "lb_language": 0.26477666666666666,
26198
  "lb_if": 0.63167,
26199
  "lb_data_analysis": 0.255,
26200
- "arena_elo": 1229.63,
26201
- "arena_rank": 240,
26202
  "arena_votes": 51416
26203
  },
26204
  {
@@ -26231,8 +26231,8 @@
26231
  "lb_language": 0.13761333333333334,
26232
  "lb_if": 0.4480825,
26233
  "lb_data_analysis": 0.1619,
26234
- "arena_elo": 1197.32,
26235
- "arena_rank": 257,
26236
  "arena_votes": 73503
26237
  },
26238
  {
@@ -28559,8 +28559,8 @@
28559
  "hf_math_lvl5": 0.07628398791540786,
28560
  "hf_musr": 0.42543749999999997,
28561
  "hf_avg": 22.70925524673515,
28562
- "arena_elo": 1182.41,
28563
- "arena_rank": 264,
28564
  "arena_votes": 12637
28565
  },
28566
  {
@@ -28598,8 +28598,8 @@
28598
  "hf_math_lvl5": 0.07250755287009064,
28599
  "hf_musr": 0.4228645833333333,
28600
  "hf_avg": 21.635827111564595,
28601
- "arena_elo": 1182.33,
28602
- "arena_rank": 265,
28603
  "arena_votes": 7968
28604
  },
28605
  {
@@ -29752,8 +29752,8 @@
29752
  "hf_math_lvl5": 0.07099697885196375,
29753
  "hf_musr": 0.41232291666666665,
29754
  "hf_avg": 22.3449346084354,
29755
- "arena_elo": 1279.71,
29756
- "arena_rank": 211,
29757
  "arena_votes": 10072
29758
  },
29759
  {
@@ -33248,8 +33248,8 @@
33248
  "lb_language": 0.11368333333333334,
33249
  "lb_if": 0.52779,
33250
  "lb_data_analysis": 0.1738,
33251
- "arena_elo": 1175.31,
33252
- "arena_rank": 271,
33253
  "arena_votes": 5006
33254
  },
33255
  {
@@ -34302,8 +34302,8 @@
34302
  "hf_math_lvl5": 0.05664652567975831,
34303
  "hf_musr": 0.3899375,
34304
  "hf_avg": 20.57236409322395,
34305
- "arena_elo": 1152.51,
34306
- "arena_rank": 282,
34307
  "arena_votes": 4155
34308
  },
34309
  {
@@ -35718,8 +35718,8 @@
35718
  "lb_language": 0.2793333333333334,
35719
  "lb_if": 0.5561674999999999,
35720
  "lb_data_analysis": 0.39766500000000005,
35721
- "arena_elo": 1250.38,
35722
- "arena_rank": 230,
35723
  "arena_votes": 10140
35724
  },
35725
  {
@@ -35731,8 +35731,8 @@
35731
  "lb_language": 0.23921666666666663,
35732
  "lb_if": 0.7150825,
35733
  "lb_data_analysis": 0.179,
35734
- "arena_elo": 1262.12,
35735
- "arena_rank": 223,
35736
  "arena_votes": 77554,
35737
  "aider_pass_rate": 0.218
35738
  },
@@ -35746,8 +35746,8 @@
35746
  "lb_language": 0.3086066666666667,
35747
  "lb_if": 0.5761225,
35748
  "lb_data_analysis": 0.492345,
35749
- "arena_elo": 1276.74,
35750
- "arena_rank": 213,
35751
  "arena_votes": 9866
35752
  },
35753
  {
@@ -35759,8 +35759,8 @@
35759
  "lb_language": 0.33044,
35760
  "lb_if": 0.6718325,
35761
  "lb_data_analysis": 0.3438,
35762
- "arena_elo": 1264.5,
35763
- "arena_rank": 222,
35764
  "arena_votes": 15147
35765
  },
35766
  {
@@ -35865,8 +35865,8 @@
35865
  "lb_language": 0.43553333333333333,
35866
  "lb_if": 0.6392074999999999,
35867
  "lb_data_analysis": 0.5308999999999999,
35868
- "arena_elo": 1313.49,
35869
- "arena_rank": 183,
35870
  "arena_votes": 93439,
35871
  "aider_pass_rate": 0.556
35872
  },
@@ -35919,8 +35919,8 @@
35919
  "lb_language": 0.28744,
35920
  "lb_if": 0.6819175000000001,
35921
  "lb_data_analysis": 0.3983,
35922
- "arena_elo": 1242.57,
35923
- "arena_rank": 231,
35924
  "arena_votes": 62436
35925
  },
35926
  {
@@ -35932,8 +35932,8 @@
35932
  "lb_language": 0.3979266666666667,
35933
  "lb_if": 0.7184575000000001,
35934
  "lb_data_analysis": 0.42910000000000004,
35935
- "arena_elo": 1314.35,
35936
- "arena_rank": 182,
35937
  "arena_votes": 45459
35938
  },
35939
  {
@@ -35965,8 +35965,8 @@
35965
  "lb_language": 0.11368333333333332,
35966
  "lb_if": 0.5824975,
35967
  "lb_data_analysis": 0.2347,
35968
- "arena_elo": 1233.36,
35969
- "arena_rank": 239,
35970
  "arena_votes": 39302
35971
  },
35972
  {
@@ -35988,8 +35988,8 @@
35988
  "lb_language": 0.07264333333333332,
35989
  "lb_if": 0.3832075,
35990
  "lb_data_analysis": 0.03,
35991
- "arena_elo": 1171.84,
35992
- "arena_rank": 273,
35993
  "arena_votes": 16056
35994
  },
35995
  {
@@ -36044,8 +36044,8 @@
36044
  "lb_language": 0.29534,
36045
  "lb_if": 0.8454575,
36046
  "lb_data_analysis": 0.39359999999999995,
36047
- "arena_elo": 1310.14,
36048
- "arena_rank": 186,
36049
  "arena_votes": 34902
36050
  },
36051
  {
@@ -36057,8 +36057,8 @@
36057
  "lb_language": 0.4740566666666666,
36058
  "lb_if": 0.7774575,
36059
  "lb_data_analysis": 0.5145,
36060
- "arena_elo": 1351.67,
36061
- "arena_rank": 130,
36062
  "arena_votes": 55606,
36063
  "aider_pass_rate": 0.496
36064
  },
@@ -36212,8 +36212,8 @@
36212
  "lb_language": 0.3427633333333333,
36213
  "lb_if": 0.782835,
36214
  "lb_data_analysis": 0.5621,
36215
- "arena_elo": 1353.63,
36216
- "arena_rank": 127,
36217
  "arena_votes": 24955
36218
  },
36219
  {
@@ -36298,8 +36298,8 @@
36298
  "lb_language": 0.40453333333333336,
36299
  "lb_if": 0.67929,
36300
  "lb_data_analysis": 0.541955,
36301
- "arena_elo": 1305.6,
36302
- "arena_rank": 192,
36303
  "arena_votes": 28073,
36304
  "aider_pass_rate": 0.466
36305
  },
@@ -36404,9 +36404,9 @@
36404
  "lb_language": 0.5836933333333333,
36405
  "lb_if": 0.7534574999999999,
36406
  "lb_data_analysis": 0.64271,
36407
- "arena_elo": 1374.92,
36408
- "arena_rank": 108,
36409
- "arena_votes": 33167
36410
  },
36411
  {
36412
  "name": "gpt-4.5-preview",
@@ -36449,9 +36449,9 @@
36449
  "lb_language": 0.41314333333333336,
36450
  "lb_if": 0.7490399999999999,
36451
  "lb_data_analysis": 0.387965,
36452
- "arena_elo": 1365.59,
36453
- "arena_rank": 117,
36454
- "arena_votes": 48382
36455
  },
36456
  {
36457
  "name": "gemini-2.5-pro-exp-03-25",
@@ -36473,9 +36473,9 @@
36473
  "lb_language": 0.4682266666666666,
36474
  "lb_if": 0.8147075,
36475
  "lb_data_analysis": 0.64019,
36476
- "arena_elo": 1394.86,
36477
- "arena_rank": 87,
36478
- "arena_votes": 46351
36479
  },
36480
  {
36481
  "name": "chatgpt-4o-latest-2025-03-27",
@@ -36519,9 +36519,9 @@
36519
  "lb_language": 0.6319400000000001,
36520
  "lb_if": 0.764915,
36521
  "lb_data_analysis": 0.599645,
36522
- "arena_elo": 1371.55,
36523
- "arena_rank": 112,
36524
- "arena_votes": 44145
36525
  },
36526
  {
36527
  "name": "command-a-03-2025",
@@ -36533,9 +36533,9 @@
36533
  "lb_language": 0.36696,
36534
  "lb_if": 0.82904,
36535
  "lb_data_analysis": 0.48457000000000006,
36536
- "arena_elo": 1353.63,
36537
- "arena_rank": 128,
36538
- "arena_votes": 56995
36539
  },
36540
  {
36541
  "name": "gemini-1.5-flash-8b-001",
@@ -36546,8 +36546,8 @@
36546
  "lb_language": 0.22867666666666667,
36547
  "lb_if": 0.6971649999999999,
36548
  "lb_data_analysis": 0.4241,
36549
- "arena_elo": 1259.14,
36550
- "arena_rank": 227,
36551
  "arena_votes": 35558
36552
  },
36553
  {
@@ -36559,9 +36559,9 @@
36559
  "lb_language": 0.42386999999999997,
36560
  "lb_if": 0.8578749999999999,
36561
  "lb_data_analysis": 0.7332000000000001,
36562
- "arena_elo": 1361.23,
36563
- "arena_rank": 121,
36564
- "arena_votes": 44611
36565
  },
36566
  {
36567
  "name": "gemini-2.0-flash-lite-001",
@@ -36583,8 +36583,8 @@
36583
  "lb_language": 0.3126966666666667,
36584
  "lb_if": 0.7382925,
36585
  "lb_data_analysis": 0.4284,
36586
- "arena_elo": 1342.15,
36587
- "arena_rank": 144,
36588
  "arena_votes": 3829
36589
  },
36590
  {
@@ -36596,8 +36596,8 @@
36596
  "lb_language": 0.15059333333333333,
36597
  "lb_if": 0.6358325,
36598
  "lb_data_analysis": 0.36950000000000005,
36599
- "arena_elo": 1303.57,
36600
- "arena_rank": 195,
36601
  "arena_votes": 4171
36602
  },
36603
  {
@@ -36610,8 +36610,8 @@
36610
  "lb_language": 0.6475866666666666,
36611
  "lb_if": 0.72325,
36612
  "lb_data_analysis": 0.600695,
36613
- "arena_elo": 1444.85,
36614
- "arena_rank": 28,
36615
  "arena_votes": 14547
36616
  },
36617
  {
@@ -36623,9 +36623,9 @@
36623
  "lb_language": 0.4964766666666667,
36624
  "lb_if": 0.7574575,
36625
  "lb_data_analysis": 0.6155,
36626
- "arena_elo": 1328.03,
36627
- "arena_rank": 161,
36628
- "arena_votes": 40876
36629
  },
36630
  {
36631
  "name": "grok-3-beta",
@@ -36659,9 +36659,9 @@
36659
  "lb_language": 0.54551,
36660
  "lb_if": 0.7704575,
36661
  "lb_data_analysis": 0.66404,
36662
- "arena_elo": 1413.88,
36663
- "arena_rank": 63,
36664
- "arena_votes": 51717
36665
  },
36666
  {
36667
  "name": "gpt-4.1-mini-2025-04-14",
@@ -36673,9 +36673,9 @@
36673
  "lb_language": 0.37996,
36674
  "lb_if": 0.7030825,
36675
  "lb_data_analysis": 0.6133799999999999,
36676
- "arena_elo": 1382.37,
36677
- "arena_rank": 103,
36678
- "arena_votes": 40190
36679
  },
36680
  {
36681
  "name": "gpt-4.1-nano-2025-04-14",
@@ -36687,8 +36687,8 @@
36687
  "lb_language": 0.30958,
36688
  "lb_if": 0.5753725,
36689
  "lb_data_analysis": 0.498195,
36690
- "arena_elo": 1322.14,
36691
- "arena_rank": 169,
36692
  "arena_votes": 6103
36693
  },
36694
  {
@@ -36778,9 +36778,9 @@
36778
  "lb_language": 0.6482266666666666,
36779
  "lb_if": 0.79954,
36780
  "lb_data_analysis": 0.7153849999999999,
36781
- "arena_elo": 1420.18,
36782
- "arena_rank": 51,
36783
- "arena_votes": 19106
36784
  },
36785
  {
36786
  "name": "gemini-2.5-flash-preview-05-20",
@@ -36847,9 +36847,9 @@
36847
  "lb_language": 0.44743666666666665,
36848
  "lb_if": 0.7139575,
36849
  "lb_data_analysis": 0.602025,
36850
- "arena_elo": 1385.92,
36851
- "arena_rank": 100,
36852
- "arena_votes": 34285
36853
  },
36854
  {
36855
  "name": "phi-4-reasoning-plus",
@@ -36883,9 +36883,9 @@
36883
  "lb_language": 0.60609,
36884
  "lb_if": 0.8772925,
36885
  "lb_data_analysis": 0.68308,
36886
- "arena_elo": 1375.14,
36887
- "arena_rank": 107,
36888
- "arena_votes": 26961
36889
  },
36890
  {
36891
  "name": "qwen3-30b-a3b",
@@ -36897,9 +36897,9 @@
36897
  "lb_language": 0.54465,
36898
  "lb_if": 0.21108249999999998,
36899
  "lb_data_analysis": 0.44922666666666666,
36900
- "arena_elo": 1328.65,
36901
- "arena_rank": 160,
36902
- "arena_votes": 27213
36903
  },
36904
  {
36905
  "name": "qwen3-32b",
@@ -36911,8 +36911,8 @@
36911
  "lb_language": 0.5554233333333333,
36912
  "lb_if": 0.1777075,
36913
  "lb_data_analysis": 0.4654,
36914
- "arena_elo": 1347.52,
36915
- "arena_rank": 138,
36916
  "arena_votes": 3926
36917
  },
36918
  {
@@ -36936,9 +36936,9 @@
36936
  "lb_language": 0.7599833333333333,
36937
  "lb_if": 0.2352075,
36938
  "lb_data_analysis": 0.47005,
36939
- "arena_elo": 1451.82,
36940
- "arena_rank": 21,
36941
- "arena_votes": 50036
36942
  },
36943
  {
36944
  "name": "deepseek-v3.1-terminus",
@@ -36950,9 +36950,9 @@
36950
  "lb_language": 0.63882,
36951
  "lb_if": 0.8189575,
36952
  "lb_data_analysis": 0.67298,
36953
- "arena_elo": 1416.54,
36954
- "arena_rank": 58,
36955
- "arena_votes": 3732
36956
  },
36957
  {
36958
  "name": "gemini-2.5-flash-06-05",
@@ -36997,9 +36997,9 @@
36997
  "lb_language": 0.6534300000000001,
36998
  "lb_if": 0.2767925,
36999
  "lb_data_analysis": 0.6098266666666666,
37000
- "arena_elo": 1405.05,
37001
- "arena_rank": 72,
37002
- "arena_votes": 32443
37003
  },
37004
  {
37005
  "name": "gemini-2.5-pro-06-05",
@@ -37022,9 +37022,9 @@
37022
  "lb_language": 0.6162266666666666,
37023
  "lb_if": 0.8157925,
37024
  "lb_data_analysis": 0.6628999999999999,
37025
- "arena_elo": 1410.51,
37026
- "arena_rank": 67,
37027
- "arena_votes": 24545
37028
  },
37029
  {
37030
  "name": "glm-4.5-air",
@@ -37036,9 +37036,9 @@
37036
  "lb_language": 0.44289666666666666,
37037
  "lb_if": 0.7883775000000001,
37038
  "lb_data_analysis": 0.65962,
37039
- "arena_elo": 1372.46,
37040
- "arena_rank": 111,
37041
- "arena_votes": 31058
37042
  },
37043
  {
37044
  "name": "glm-4.6",
@@ -37050,9 +37050,9 @@
37050
  "lb_language": 0.5898633333333333,
37051
  "lb_if": 0.26192,
37052
  "lb_data_analysis": 0.5194766666666667,
37053
- "arena_elo": 1425.94,
37054
- "arena_rank": 42,
37055
- "arena_votes": 35019
37056
  },
37057
  {
37058
  "name": "gpt-5",
@@ -37086,9 +37086,9 @@
37086
  "lb_language": 0.8082699999999999,
37087
  "lb_if": 0.8811249999999999,
37088
  "lb_data_analysis": 0.716345,
37089
- "arena_elo": 1434.65,
37090
- "arena_rank": 37,
37091
- "arena_votes": 32221
37092
  },
37093
  {
37094
  "name": "gpt-5-low",
@@ -37122,9 +37122,9 @@
37122
  "lb_language": 0.7552066666666667,
37123
  "lb_if": 0.65271,
37124
  "lb_data_analysis": 0.55195,
37125
- "arena_elo": 1390.56,
37126
- "arena_rank": 91,
37127
- "arena_votes": 26887
37128
  },
37129
  {
37130
  "name": "gpt-5-mini-low",
@@ -37180,9 +37180,9 @@
37180
  "lb_language": 0.46841666666666665,
37181
  "lb_if": 0.5569975,
37182
  "lb_data_analysis": 0.4340566666666667,
37183
- "arena_elo": 1338.18,
37184
- "arena_rank": 147,
37185
- "arena_votes": 8329
37186
  },
37187
  {
37188
  "name": "gpt-5-nano-low",
@@ -37216,9 +37216,9 @@
37216
  "lb_language": 0.62963,
37217
  "lb_if": 0.7300425,
37218
  "lb_data_analysis": 0.644815,
37219
- "arena_elo": 1426.54,
37220
- "arena_rank": 41,
37221
- "arena_votes": 31535
37222
  },
37223
  {
37224
  "name": "gpt-oss-120b",
@@ -37230,9 +37230,9 @@
37230
  "lb_language": 0.48590666666666665,
37231
  "lb_if": 0.5029175,
37232
  "lb_data_analysis": 0.38804999999999995,
37233
- "arena_elo": 1354.86,
37234
- "arena_rank": 126,
37235
- "arena_votes": 30658
37236
  },
37237
  {
37238
  "name": "grok-4-0709",
@@ -37244,9 +37244,9 @@
37244
  "lb_language": 0.76388,
37245
  "lb_if": 0.29075,
37246
  "lb_data_analysis": 0.6337666666666667,
37247
- "arena_elo": 1410.05,
37248
- "arena_rank": 69,
37249
- "arena_votes": 41655
37250
  },
37251
  {
37252
  "name": "grok-code-fast-1-0825",
@@ -37280,9 +37280,9 @@
37280
  "lb_language": 0.6606966666666668,
37281
  "lb_if": 0.2172075,
37282
  "lb_data_analysis": 0.4471566666666667,
37283
- "arena_elo": 1422.96,
37284
- "arena_rank": 48,
37285
- "arena_votes": 74402
37286
  },
37287
  {
37288
  "name": "qwen3-235b-a22b-thinking-2507",
@@ -37294,9 +37294,9 @@
37294
  "lb_language": 0.6952366666666666,
37295
  "lb_if": 0.40641999999999995,
37296
  "lb_data_analysis": 0.5218266666666667,
37297
- "arena_elo": 1399.54,
37298
- "arena_rank": 81,
37299
- "arena_votes": 9171
37300
  },
37301
  {
37302
  "name": "qwen3-coder-480b-a35b-instruct",
@@ -37308,9 +37308,9 @@
37308
  "lb_language": 0.6426233333333333,
37309
  "lb_if": 0.741625,
37310
  "lb_data_analysis": 0.64683,
37311
- "arena_elo": 1387.29,
37312
- "arena_rank": 96,
37313
- "arena_votes": 26338
37314
  },
37315
  {
37316
  "name": "qwen3-max-2025-09-23",
@@ -37322,9 +37322,9 @@
37322
  "lb_language": 0.7144733333333333,
37323
  "lb_if": 0.76546,
37324
  "lb_data_analysis": 0.6536649999999999,
37325
- "arena_elo": 1425.2,
37326
- "arena_rank": 43,
37327
- "arena_votes": 9131
37328
  },
37329
  {
37330
  "name": "qwen3-next-80b-a3b-instruct",
@@ -37336,9 +37336,9 @@
37336
  "lb_language": 0.6633766666666666,
37337
  "lb_if": 0.191875,
37338
  "lb_data_analysis": 0.49784,
37339
- "arena_elo": 1402.36,
37340
- "arena_rank": 77,
37341
- "arena_votes": 22600
37342
  },
37343
  {
37344
  "name": "qwen3-next-80b-a3b",
@@ -37350,9 +37350,9 @@
37350
  "lb_language": 0.5631166666666667,
37351
  "lb_if": 0.41541999999999996,
37352
  "lb_data_analysis": 0.5358333333333333,
37353
- "arena_elo": 1369.04,
37354
- "arena_rank": 113,
37355
- "arena_votes": 13704
37356
  },
37357
  {
37358
  "name": "claude-haiku-4-5-20251001",
@@ -37364,9 +37364,9 @@
37364
  "lb_language": 0.5704566666666667,
37365
  "lb_if": 0.17754250000000002,
37366
  "lb_data_analysis": 0.45124999999999993,
37367
- "arena_elo": 1406.41,
37368
- "arena_rank": 71,
37369
- "arena_votes": 50555
37370
  },
37371
  {
37372
  "name": "deepseek-v3.2-exp",
@@ -37378,9 +37378,9 @@
37378
  "lb_language": 0.65596,
37379
  "lb_if": 0.1932925,
37380
  "lb_data_analysis": 0.4425866666666667,
37381
- "arena_elo": 1423.96,
37382
- "arena_rank": 46,
37383
- "arena_votes": 11652
37384
  },
37385
  {
37386
  "name": "minimax-m2",
@@ -37392,9 +37392,9 @@
37392
  "lb_language": 0.47647666666666666,
37393
  "lb_if": 0.810165,
37394
  "lb_data_analysis": 0.6755800000000001,
37395
- "arena_elo": 1347.62,
37396
- "arena_rank": 137,
37397
- "arena_votes": 6661
37398
  },
37399
  {
37400
  "name": "kimi-k2",
@@ -37516,9 +37516,9 @@
37516
  "lb_language": 0.7432699999999999,
37517
  "lb_if": 0.28204,
37518
  "lb_data_analysis": 0.52238,
37519
- "arena_elo": 1430.98,
37520
- "arena_rank": 39,
37521
- "arena_votes": 34398
37522
  },
37523
  {
37524
  "name": "claude-opus-4-5-20251101",
@@ -37530,9 +37530,9 @@
37530
  "lb_language": 0.7709166666666668,
37531
  "lb_if": 0.26591750000000003,
37532
  "lb_data_analysis": 0.4561233333333334,
37533
- "arena_elo": 1467.25,
37534
- "arena_rank": 11,
37535
- "arena_votes": 38768
37536
  },
37537
  {
37538
  "name": "deepseek-v3.2",
@@ -37544,9 +37544,9 @@
37544
  "lb_language": 0.6423933333333333,
37545
  "lb_if": 0.230625,
37546
  "lb_data_analysis": 0.45034,
37547
- "arena_elo": 1423.23,
37548
- "arena_rank": 47,
37549
- "arena_votes": 33766
37550
  },
37551
  {
37552
  "name": "deepseek-v3.2-speciale",
@@ -37602,9 +37602,9 @@
37602
  "lb_language": 0.49737666666666663,
37603
  "lb_if": 0.1706225,
37604
  "lb_data_analysis": 0.46410666666666667,
37605
- "arena_elo": 1377.94,
37606
- "arena_rank": 105,
37607
- "arena_votes": 2773
37608
  },
37609
  {
37610
  "name": "gpt-5.1-2025-11-13-low",
@@ -37715,9 +37715,9 @@
37715
  "lb_language": 0.6522633333333333,
37716
  "lb_if": 0.3565825,
37717
  "lb_data_analysis": 0.5517133333333334,
37718
- "arena_elo": 1441.47,
37719
- "arena_rank": 31,
37720
- "arena_votes": 11896
37721
  },
37722
  {
37723
  "name": "arcee-trinity-large-preview",
@@ -37740,9 +37740,9 @@
37740
  "lb_language": 0.8326966666666666,
37741
  "lb_if": 0.633125,
37742
  "lb_data_analysis": 0.6989299999999999,
37743
- "arena_elo": 1503.39,
37744
- "arena_rank": 1,
37745
- "arena_votes": 10399
37746
  },
37747
  {
37748
  "name": "claude-sonnet-4-6",
@@ -37754,9 +37754,9 @@
37754
  "lb_language": 0.7769333333333334,
37755
  "lb_if": 0.639165,
37756
  "lb_data_analysis": 0.7605666666666667,
37757
- "arena_elo": 1460.39,
37758
- "arena_rank": 16,
37759
- "arena_votes": 6961
37760
  },
37761
  {
37762
  "name": "gemini-3.1-pro-preview-high",
@@ -37790,9 +37790,9 @@
37790
  "lb_language": 0.7752800000000001,
37791
  "lb_if": 0.5532900000000001,
37792
  "lb_data_analysis": 0.67896,
37793
- "arena_elo": 1453.95,
37794
- "arena_rank": 18,
37795
- "arena_votes": 9031
37796
  },
37797
  {
37798
  "name": "gpt-5.2-codex",
@@ -37848,9 +37848,9 @@
37848
  "lb_language": 0.8300899999999999,
37849
  "lb_if": 0.6495425,
37850
  "lb_data_analysis": 0.7704833333333333,
37851
- "arena_elo": 1484.63,
37852
  "arena_rank": 6,
37853
- "arena_votes": 3989
37854
  },
37855
  {
37856
  "name": "gpt-5.4-xhigh",
@@ -37863,6 +37863,116 @@
37863
  "lb_if": 0.7021674999999999,
37864
  "lb_data_analysis": 0.7931333333333334
37865
  },
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
37866
  {
37867
  "name": "grok-4.20-beta-0309",
37868
  "lb_name": "grok-4.20-beta-0309-non-reasoning",
@@ -37883,7 +37993,10 @@
37883
  "lb_math": 0.8705550000000001,
37884
  "lb_language": 0.7771733333333333,
37885
  "lb_if": 0.6338775,
37886
- "lb_data_analysis": 0.62857
 
 
 
37887
  },
37888
  {
37889
  "name": "kimi-k2.5",
@@ -37895,9 +38008,9 @@
37895
  "lb_language": 0.77666,
37896
  "lb_if": 0.574125,
37897
  "lb_data_analysis": 0.6135766666666667,
37898
- "arena_elo": 1451.99,
37899
- "arena_rank": 19,
37900
- "arena_votes": 13903
37901
  },
37902
  {
37903
  "name": "minimax-m2.5",
@@ -37909,833 +38022,873 @@
37909
  "lb_language": 0.5510100000000001,
37910
  "lb_if": 0.5723325,
37911
  "lb_data_analysis": 0.49605000000000005,
37912
- "arena_elo": 1403.5,
37913
- "arena_rank": 74,
37914
- "arena_votes": 9308
37915
  },
37916
  {
37917
  "name": "claude-opus-4-6-thinking",
37918
  "arena_name": "claude-opus-4-6-thinking",
37919
  "arena_org": "Anthropic",
37920
- "arena_elo": 1503.26,
37921
- "arena_rank": 2,
37922
- "arena_votes": 9543
37923
- },
37924
- {
37925
- "name": "grok-4.20-beta1",
37926
- "arena_name": "grok-4.20-beta1",
37927
- "arena_org": "xAI",
37928
- "arena_elo": 1495.99,
37929
- "arena_rank": 3,
37930
- "arena_votes": 6063
37931
  },
37932
  {
37933
  "name": "gemini-3.1-pro-preview",
37934
  "arena_name": "gemini-3.1-pro-preview",
37935
  "arena_org": "Google",
37936
- "arena_elo": 1492.35,
 
 
 
 
 
 
 
 
37937
  "arena_rank": 4,
37938
- "arena_votes": 10521
37939
  },
37940
  {
37941
  "name": "gemini-3-pro",
37942
  "arena_name": "gemini-3-pro",
37943
  "arena_org": "Google",
37944
- "arena_elo": 1485.56,
37945
  "arena_rank": 5,
37946
- "arena_votes": 40879
37947
  },
37948
  {
37949
  "name": "gpt-5.2-chat-latest-20260210",
37950
  "arena_name": "gpt-5.2-chat-latest-20260210",
37951
  "arena_org": "OpenAI",
37952
- "arena_elo": 1480.84,
37953
  "arena_rank": 7,
37954
- "arena_votes": 7208
37955
  },
37956
  {
37957
  "name": "gemini-3-flash",
37958
  "arena_name": "gemini-3-flash",
37959
  "arena_org": "Google",
37960
- "arena_elo": 1474.14,
37961
- "arena_rank": 8,
37962
- "arena_votes": 30514
37963
- },
37964
- {
37965
- "name": "grok-4.1-thinking",
37966
- "arena_name": "grok-4.1-thinking",
37967
- "arena_org": "xAI",
37968
- "arena_elo": 1472.84,
37969
  "arena_rank": 9,
37970
- "arena_votes": 40567
37971
  },
37972
  {
37973
  "name": "claude-opus-4-5-20251101-thinking-32k",
37974
  "arena_name": "claude-opus-4-5-20251101-thinking-32k",
37975
  "arena_org": "Anthropic",
37976
- "arena_elo": 1472.37,
37977
  "arena_rank": 10,
37978
- "arena_votes": 33905
37979
  },
37980
  {
37981
- "name": "dola-seed-2.0-preview",
37982
- "arena_name": "dola-seed-2.0-preview",
37983
- "arena_org": "Bytedance",
37984
- "arena_elo": 1465.28,
37985
- "arena_rank": 12,
37986
- "arena_votes": 8049
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
37987
  },
37988
  {
37989
  "name": "gemini-3-flash (thinking-minimal)",
37990
  "arena_name": "gemini-3-flash (thinking-minimal)",
37991
  "arena_org": "Google",
37992
- "arena_elo": 1462.81,
37993
- "arena_rank": 13,
37994
- "arena_votes": 24202
37995
  },
37996
  {
37997
  "name": "gpt-5.4",
37998
  "arena_name": "gpt-5.4",
37999
  "arena_org": "OpenAI",
38000
- "arena_elo": 1462.59,
38001
- "arena_rank": 14,
38002
- "arena_votes": 4055
 
 
 
 
 
 
 
 
38003
  },
38004
  {
38005
  "name": "grok-4.1",
38006
  "arena_name": "grok-4.1",
38007
  "arena_org": "xAI",
38008
- "arena_elo": 1462.24,
38009
- "arena_rank": 15,
38010
- "arena_votes": 44647
38011
  },
38012
  {
38013
  "name": "gpt-5.1-high",
38014
  "arena_name": "gpt-5.1-high",
38015
  "arena_org": "OpenAI",
38016
- "arena_elo": 1456.37,
38017
- "arena_rank": 17,
38018
- "arena_votes": 37407
38019
- },
38020
- {
38021
- "name": "ernie-5.0-0110",
38022
- "arena_name": "ernie-5.0-0110",
38023
- "arena_org": "Baidu",
38024
- "arena_elo": 1451.85,
38025
  "arena_rank": 20,
38026
- "arena_votes": 16403
38027
  },
38028
  {
38029
  "name": "claude-sonnet-4-5-20250929-thinking-32k",
38030
  "arena_name": "claude-sonnet-4-5-20250929-thinking-32k",
38031
  "arena_org": "Anthropic",
38032
- "arena_elo": 1451.11,
38033
- "arena_rank": 22,
38034
- "arena_votes": 52034
 
 
 
 
 
 
 
 
38035
  },
38036
  {
38037
  "name": "qwen3.5-397b-a17b",
38038
  "arena_name": "qwen3.5-397b-a17b",
38039
  "arena_org": "Alibaba",
38040
- "arena_elo": 1449.89,
38041
- "arena_rank": 23,
38042
- "arena_votes": 8090
38043
  },
38044
  {
38045
  "name": "ernie-5.0-preview-1203",
38046
  "arena_name": "ernie-5.0-preview-1203",
38047
  "arena_org": "Baidu",
38048
- "arena_elo": 1449.77,
38049
- "arena_rank": 24,
38050
- "arena_votes": 9657
38051
- },
38052
- {
38053
- "name": "gemini-2.5-pro",
38054
- "arena_name": "gemini-2.5-pro",
38055
- "arena_org": "Google",
38056
- "arena_elo": 1449.24,
38057
- "arena_rank": 25,
38058
- "arena_votes": 100138
38059
  },
38060
  {
38061
  "name": "claude-opus-4-1-20250805-thinking-16k",
38062
  "arena_name": "claude-opus-4-1-20250805-thinking-16k",
38063
  "arena_org": "Anthropic",
38064
- "arena_elo": 1448.78,
38065
- "arena_rank": 26,
38066
- "arena_votes": 49499
 
 
 
 
 
 
 
 
38067
  },
38068
  {
38069
  "name": "claude-opus-4-1-20250805",
38070
  "arena_name": "claude-opus-4-1-20250805",
38071
  "arena_org": "Anthropic",
38072
- "arena_elo": 1447.01,
38073
- "arena_rank": 27,
38074
- "arena_votes": 77032
38075
  },
38076
  {
38077
- "name": "gpt-5.2-high",
38078
- "arena_name": "gpt-5.2-high",
38079
- "arena_org": "OpenAI",
38080
- "arena_elo": 1443.44,
38081
- "arena_rank": 29,
38082
- "arena_votes": 22443
38083
  },
38084
  {
38085
  "name": "chatgpt-4o-latest-20250326",
38086
  "arena_name": "chatgpt-4o-latest-20250326",
38087
  "arena_org": "OpenAI",
38088
- "arena_elo": 1443.44,
38089
- "arena_rank": 30,
38090
- "arena_votes": 82750
 
 
 
 
 
 
 
 
38091
  },
38092
  {
38093
  "name": "gpt-5.2",
38094
  "arena_name": "gpt-5.2",
38095
  "arena_org": "OpenAI",
38096
- "arena_elo": 1441.04,
38097
- "arena_rank": 32,
38098
- "arena_votes": 19419
38099
  },
38100
  {
38101
  "name": "gpt-5.1",
38102
  "arena_name": "gpt-5.1",
38103
  "arena_org": "OpenAI",
38104
- "arena_elo": 1438.92,
38105
- "arena_rank": 33,
38106
- "arena_votes": 40089
38107
- },
38108
- {
38109
- "name": "kimi-k2.5-instant",
38110
- "arena_name": "kimi-k2.5-instant",
38111
- "arena_org": "Moonshot",
38112
- "arena_elo": 1438.1,
38113
- "arena_rank": 34,
38114
- "arena_votes": 10086
38115
  },
38116
  {
38117
  "name": "gemini-3.1-flash-lite-preview",
38118
  "arena_name": "gemini-3.1-flash-lite-preview",
38119
  "arena_org": "Google",
38120
- "arena_elo": 1437.17,
38121
- "arena_rank": 35,
38122
- "arena_votes": 3860
38123
  },
38124
  {
38125
  "name": "qwen3-max-preview",
38126
  "arena_name": "qwen3-max-preview",
38127
  "arena_org": "Alibaba",
38128
- "arena_elo": 1434.98,
38129
- "arena_rank": 36,
38130
- "arena_votes": 27579
 
 
 
 
 
 
 
 
38131
  },
38132
  {
38133
  "name": "o3-2025-04-16",
38134
  "arena_name": "o3-2025-04-16",
38135
  "arena_org": "OpenAI",
38136
- "arena_elo": 1432.88,
38137
- "arena_rank": 38,
38138
- "arena_votes": 60747
38139
  },
38140
  {
38141
  "name": "kimi-k2-thinking-turbo",
38142
  "arena_name": "kimi-k2-thinking-turbo",
38143
  "arena_org": "Moonshot",
38144
- "arena_elo": 1429.62,
38145
- "arena_rank": 40,
38146
- "arena_votes": 38973
38147
  },
38148
  {
38149
- "name": "claude-opus-4-20250514-thinking-16k",
38150
- "arena_name": "claude-opus-4-20250514-thinking-16k",
38151
- "arena_org": "Anthropic",
38152
- "arena_elo": 1424.3,
38153
- "arena_rank": 44,
38154
- "arena_votes": 37611
38155
  },
38156
  {
38157
  "name": "deepseek-v3.2-exp-thinking",
38158
  "arena_name": "deepseek-v3.2-exp-thinking",
38159
  "arena_org": "DeepSeek",
38160
- "arena_elo": 1424.22,
38161
- "arena_rank": 45,
38162
- "arena_votes": 8922
38163
  },
38164
  {
38165
- "name": "grok-4-fast-chat",
38166
- "arena_name": "grok-4-fast-chat",
38167
- "arena_org": "xAI",
38168
- "arena_elo": 1421.55,
38169
- "arena_rank": 49,
38170
- "arena_votes": 6951
38171
  },
38172
  {
38173
  "name": "deepseek-v3.2-thinking",
38174
  "arena_name": "deepseek-v3.2-thinking",
38175
  "arena_org": "DeepSeek",
38176
- "arena_elo": 1420.63,
38177
- "arena_rank": 50,
38178
- "arena_votes": 28519
 
 
 
 
 
 
 
 
38179
  },
38180
  {
38181
  "name": "ernie-5.0-preview-1022",
38182
  "arena_name": "ernie-5.0-preview-1022",
38183
  "arena_org": "Baidu",
38184
- "arena_elo": 1419.49,
38185
- "arena_rank": 52,
38186
- "arena_votes": 4535
38187
- },
38188
- {
38189
- "name": "qwen3.5-122b-a10b",
38190
- "arena_name": "qwen3.5-122b-a10b",
38191
- "arena_org": "Alibaba",
38192
- "arena_elo": 1418.95,
38193
- "arena_rank": 53,
38194
- "arena_votes": 4515
38195
  },
38196
  {
38197
  "name": "deepseek-v3.1",
38198
  "arena_name": "deepseek-v3.1",
38199
  "arena_org": "DeepSeek",
38200
- "arena_elo": 1418.7,
38201
- "arena_rank": 54,
38202
- "arena_votes": 15170
38203
  },
38204
  {
38205
  "name": "kimi-k2-0905-preview",
38206
  "arena_name": "kimi-k2-0905-preview",
38207
  "arena_org": "Moonshot",
38208
- "arena_elo": 1418.38,
38209
- "arena_rank": 55,
38210
- "arena_votes": 11874
38211
  },
38212
  {
38213
- "name": "deepseek-v3.1-thinking",
38214
- "arena_name": "deepseek-v3.1-thinking",
38215
- "arena_org": "DeepSeek",
38216
- "arena_elo": 1417.21,
38217
- "arena_rank": 56,
38218
- "arena_votes": 11913
38219
  },
38220
  {
38221
  "name": "kimi-k2-0711-preview",
38222
  "arena_name": "kimi-k2-0711-preview",
38223
  "arena_org": "Moonshot",
38224
- "arena_elo": 1417.15,
38225
- "arena_rank": 57,
38226
- "arena_votes": 28377
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
38227
  },
38228
  {
38229
  "name": "mistral-large-3",
38230
  "arena_name": "mistral-large-3",
38231
  "arena_org": "Mistral",
38232
- "arena_elo": 1416.34,
38233
- "arena_rank": 59,
38234
- "arena_votes": 30359
38235
  },
38236
  {
38237
  "name": "qwen3-vl-235b-a22b-instruct",
38238
  "arena_name": "qwen3-vl-235b-a22b-instruct",
38239
  "arena_org": "Alibaba",
38240
- "arena_elo": 1415.94,
38241
- "arena_rank": 60,
38242
- "arena_votes": 11555
38243
- },
38244
- {
38245
- "name": "deepseek-v3.1-terminus-thinking",
38246
- "arena_name": "deepseek-v3.1-terminus-thinking",
38247
- "arena_org": "DeepSeek",
38248
- "arena_elo": 1415.39,
38249
- "arena_rank": 61,
38250
- "arena_votes": 3508
38251
  },
38252
  {
38253
  "name": "amazon-nova-experimental-chat-26-01-10",
38254
  "arena_name": "amazon-nova-experimental-chat-26-01-10",
38255
  "arena_org": "Amazon",
38256
- "arena_elo": 1415.23,
38257
- "arena_rank": 62,
38258
- "arena_votes": 3386
38259
  },
38260
  {
38261
  "name": "claude-opus-4-20250514",
38262
  "arena_name": "claude-opus-4-20250514",
38263
  "arena_org": "Anthropic",
38264
- "arena_elo": 1413.21,
38265
- "arena_rank": 64,
38266
- "arena_votes": 45215
38267
  },
38268
  {
38269
  "name": "grok-3-preview-02-24",
38270
  "arena_name": "grok-3-preview-02-24",
38271
  "arena_org": "xAI",
38272
- "arena_elo": 1411.72,
38273
- "arena_rank": 65,
38274
- "arena_votes": 33796
38275
  },
38276
  {
38277
  "name": "gemini-2.5-flash",
38278
  "arena_name": "gemini-2.5-flash",
38279
  "arena_org": "Google",
38280
- "arena_elo": 1410.85,
38281
- "arena_rank": 66,
38282
- "arena_votes": 99458
38283
  },
38284
  {
38285
  "name": "mistral-medium-2508",
38286
  "arena_name": "mistral-medium-2508",
38287
  "arena_org": "Mistral",
38288
- "arena_elo": 1410.42,
38289
- "arena_rank": 68,
38290
- "arena_votes": 68770
 
 
 
 
 
 
 
 
38291
  },
38292
  {
38293
  "name": "qwen3.5-27b",
38294
  "arena_name": "qwen3.5-27b",
38295
  "arena_org": "Alibaba",
38296
- "arena_elo": 1409.64,
38297
- "arena_rank": 70,
38298
- "arena_votes": 4671
38299
  },
38300
  {
38301
  "name": "grok-4-fast-reasoning",
38302
  "arena_name": "grok-4-fast-reasoning",
38303
  "arena_org": "xAI",
38304
- "arena_elo": 1404.43,
38305
- "arena_rank": 73,
38306
- "arena_votes": 18353
38307
  },
38308
  {
38309
  "name": "qwen3-235b-a22b-no-thinking",
38310
  "arena_name": "qwen3-235b-a22b-no-thinking",
38311
  "arena_org": "Alibaba",
38312
- "arena_elo": 1402.65,
38313
- "arena_rank": 75,
38314
- "arena_votes": 39190
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
38315
  },
38316
  {
38317
  "name": "longcat-flash-chat",
38318
  "arena_name": "longcat-flash-chat",
38319
  "arena_org": "Meituan",
38320
- "arena_elo": 1400.96,
38321
- "arena_rank": 78,
38322
- "arena_votes": 11435
38323
  },
38324
  {
38325
  "name": "claude-sonnet-4-20250514-thinking-32k",
38326
  "arena_name": "claude-sonnet-4-20250514-thinking-32k",
38327
  "arena_org": "Anthropic",
38328
- "arena_elo": 1400.08,
38329
- "arena_rank": 79,
38330
- "arena_votes": 35873
38331
- },
38332
- {
38333
- "name": "qwen3.5-flash",
38334
- "arena_name": "qwen3.5-flash",
38335
- "arena_org": "Alibaba",
38336
- "arena_elo": 1399.95,
38337
- "arena_rank": 80,
38338
- "arena_votes": 5578
38339
  },
38340
  {
38341
- "name": "qwen3.5-35b-a3b",
38342
- "arena_name": "qwen3.5-35b-a3b",
38343
- "arena_org": "Alibaba",
38344
- "arena_elo": 1397.63,
38345
- "arena_rank": 83,
38346
- "arena_votes": 4726
38347
  },
38348
  {
38349
  "name": "qwen3-vl-235b-a22b-thinking",
38350
  "arena_name": "qwen3-vl-235b-a22b-thinking",
38351
  "arena_org": "Alibaba",
38352
- "arena_elo": 1396.2,
38353
- "arena_rank": 84,
38354
- "arena_votes": 7892
38355
  },
38356
  {
38357
  "name": "amazon-nova-experimental-chat-12-10",
38358
  "arena_name": "amazon-nova-experimental-chat-12-10",
38359
  "arena_org": "Amazon",
38360
- "arena_elo": 1395.64,
38361
- "arena_rank": 85,
38362
- "arena_votes": 3683
38363
  },
38364
  {
38365
- "name": "hunyuan-vision-1.5-thinking",
38366
- "arena_name": "hunyuan-vision-1.5-thinking",
38367
- "arena_org": "Tencent",
38368
- "arena_elo": 1395.51,
38369
- "arena_rank": 86,
38370
- "arena_votes": 2204
38371
  },
38372
  {
38373
  "name": "mimo-v2-flash (non-thinking)",
38374
  "arena_name": "mimo-v2-flash (non-thinking)",
38375
  "arena_org": "Xiaomi",
38376
- "arena_elo": 1392.89,
38377
- "arena_rank": 88,
38378
- "arena_votes": 22766
38379
- },
38380
- {
38381
- "name": "mai-1-preview",
38382
- "arena_name": "mai-1-preview",
38383
- "arena_org": "Microsoft AI",
38384
- "arena_elo": 1392.69,
38385
- "arena_rank": 89,
38386
- "arena_votes": 17964
38387
  },
38388
  {
38389
  "name": "o4-mini-2025-04-16",
38390
  "arena_name": "o4-mini-2025-04-16",
38391
  "arena_org": "OpenAI",
38392
- "arena_elo": 1391.14,
38393
- "arena_rank": 90,
38394
- "arena_votes": 46255
38395
  },
38396
  {
38397
  "name": "claude-sonnet-4-20250514",
38398
  "arena_name": "claude-sonnet-4-20250514",
38399
  "arena_org": "Anthropic",
38400
- "arena_elo": 1390.23,
38401
- "arena_rank": 92,
38402
- "arena_votes": 41232
38403
  },
38404
  {
38405
  "name": "step-3.5-flash",
38406
  "arena_name": "step-3.5-flash",
38407
  "arena_org": "StepFun",
38408
- "arena_elo": 1389.23,
38409
- "arena_rank": 93,
38410
- "arena_votes": 11573
38411
- },
38412
- {
38413
- "name": "claude-3-7-sonnet-20250219-thinking-32k",
38414
- "arena_name": "claude-3-7-sonnet-20250219-thinking-32k",
38415
- "arena_org": "Anthropic",
38416
- "arena_elo": 1388.26,
38417
- "arena_rank": 95,
38418
- "arena_votes": 39653
38419
  },
38420
  {
38421
  "name": "mimo-v2-flash (thinking)",
38422
  "arena_name": "mimo-v2-flash (thinking)",
38423
  "arena_org": "Xiaomi",
38424
- "arena_elo": 1387.15,
38425
- "arena_rank": 97,
38426
- "arena_votes": 10848
38427
  },
38428
  {
38429
  "name": "hunyuan-t1-20250711",
38430
  "arena_name": "hunyuan-t1-20250711",
38431
  "arena_org": "Tencent",
38432
- "arena_elo": 1387.09,
38433
- "arena_rank": 98,
38434
- "arena_votes": 4773
 
 
 
 
 
 
 
 
38435
  },
38436
  {
38437
  "name": "minimax-m2.1-preview",
38438
  "arena_name": "minimax-m2.1-preview",
38439
  "arena_org": "MiniMax",
38440
- "arena_elo": 1386.14,
38441
- "arena_rank": 99,
38442
- "arena_votes": 17019
38443
- },
38444
- {
38445
- "name": "qwen3-30b-a3b-instruct-2507",
38446
- "arena_name": "qwen3-30b-a3b-instruct-2507",
38447
- "arena_org": "Alibaba",
38448
- "arena_elo": 1384.04,
38449
- "arena_rank": 101,
38450
- "arena_votes": 23938
38451
  },
38452
  {
38453
  "name": "hunyuan-turbos-20250416",
38454
  "arena_name": "hunyuan-turbos-20250416",
38455
  "arena_org": "Tencent",
38456
- "arena_elo": 1383.24,
38457
- "arena_rank": 102,
38458
- "arena_votes": 10967
38459
  },
38460
  {
38461
- "name": "gemini-2.5-flash-lite-preview-09-2025-no-thinking",
38462
- "arena_name": "gemini-2.5-flash-lite-preview-09-2025-no-thinking",
38463
- "arena_org": "Google",
38464
- "arena_elo": 1380.29,
38465
- "arena_rank": 104,
38466
- "arena_votes": 46727
38467
  },
38468
  {
38469
- "name": "gemini-2.5-flash-lite-preview-06-17-thinking",
38470
- "arena_name": "gemini-2.5-flash-lite-preview-06-17-thinking",
38471
  "arena_org": "Google",
38472
- "arena_elo": 1375.2,
38473
- "arena_rank": 106,
38474
- "arena_votes": 33537
38475
  },
38476
  {
38477
  "name": "trinity-large",
38478
  "arena_name": "trinity-large",
38479
  "arena_org": "Arcee AI",
38480
- "arena_elo": 1374.74,
38481
- "arena_rank": 109,
38482
- "arena_votes": 5482
 
 
 
 
 
 
 
 
38483
  },
38484
  {
38485
  "name": "glm-4.7-flash",
38486
  "arena_name": "glm-4.7-flash",
38487
  "arena_org": "Z.ai",
38488
- "arena_elo": 1368.23,
38489
- "arena_rank": 114,
38490
- "arena_votes": 11744
38491
  },
38492
  {
38493
  "name": "amazon-nova-experimental-chat-11-10",
38494
  "arena_name": "amazon-nova-experimental-chat-11-10",
38495
  "arena_org": "Amazon",
38496
- "arena_elo": 1367.12,
38497
- "arena_rank": 115,
38498
- "arena_votes": 22111
38499
- },
38500
- {
38501
- "name": "minimax-m1",
38502
- "arena_name": "minimax-m1",
38503
- "arena_org": "MiniMax",
38504
- "arena_elo": 1367.02,
38505
- "arena_rank": 116,
38506
- "arena_votes": 36285
38507
  },
38508
  {
38509
  "name": "nvidia-nemotron-3-super-120b-a12b",
38510
  "arena_name": "nvidia-nemotron-3-super-120b-a12b",
38511
  "arena_org": "Nvidia",
38512
- "arena_elo": 1364.47,
38513
- "arena_rank": 118,
38514
- "arena_votes": 3556
 
 
 
 
 
 
 
 
38515
  },
38516
  {
38517
  "name": "o3-mini-high",
38518
  "arena_name": "o3-mini-high",
38519
  "arena_org": "OpenAI",
38520
- "arena_elo": 1364.08,
38521
- "arena_rank": 119,
38522
  "arena_votes": 18589
38523
  },
38524
  {
38525
  "name": "grok-3-mini-high",
38526
  "arena_name": "grok-3-mini-high",
38527
  "arena_org": "xAI",
38528
- "arena_elo": 1363.29,
38529
- "arena_rank": 120,
38530
- "arena_votes": 17381
38531
  },
38532
  {
38533
  "name": "grok-3-mini-beta",
38534
  "arena_name": "grok-3-mini-beta",
38535
  "arena_org": "xAI",
38536
- "arena_elo": 1357.83,
38537
- "arena_rank": 123,
38538
- "arena_votes": 23512
38539
  },
38540
  {
38541
  "name": "mistral-small-2506",
38542
  "arena_name": "mistral-small-2506",
38543
  "arena_org": "Mistral",
38544
- "arena_elo": 1356.9,
38545
- "arena_rank": 124,
38546
- "arena_votes": 18178
38547
  },
38548
  {
38549
  "name": "intellect-3",
38550
  "arena_name": "intellect-3",
38551
  "arena_org": "Prime Intellect",
38552
- "arena_elo": 1356.48,
38553
- "arena_rank": 125,
38554
- "arena_votes": 5274
38555
  },
38556
  {
38557
  "name": "glm-4.5v",
38558
  "arena_name": "glm-4.5v",
38559
  "arena_org": "Z.ai",
38560
- "arena_elo": 1353.45,
38561
- "arena_rank": 129,
38562
- "arena_votes": 4938
38563
  },
38564
  {
38565
  "name": "amazon-nova-experimental-chat-10-20",
38566
  "arena_name": "amazon-nova-experimental-chat-10-20",
38567
  "arena_org": "Amazon",
38568
- "arena_elo": 1351.27,
38569
- "arena_rank": 131,
38570
- "arena_votes": 11296
38571
  },
38572
  {
38573
  "name": "hunyuan-turbos-20250226",
38574
  "arena_name": "hunyuan-turbos-20250226",
38575
  "arena_org": "Tencent",
38576
- "arena_elo": 1349.19,
38577
- "arena_rank": 132,
38578
  "arena_votes": 2220
38579
  },
38580
  {
38581
  "name": "step-3",
38582
  "arena_name": "step-3",
38583
  "arena_org": "StepFun",
38584
- "arena_elo": 1347.99,
38585
- "arena_rank": 134,
38586
- "arena_votes": 6566
38587
  },
38588
  {
38589
- "name": "ling-flash-2.0",
38590
- "arena_name": "ling-flash-2.0",
38591
- "arena_org": "Ant Group",
38592
- "arena_elo": 1347.81,
38593
- "arena_rank": 135,
38594
- "arena_votes": 6962
38595
  },
38596
  {
38597
  "name": "amazon-nova-experimental-chat-10-09",
38598
  "arena_name": "amazon-nova-experimental-chat-10-09",
38599
  "arena_org": "Amazon",
38600
- "arena_elo": 1347.64,
38601
- "arena_rank": 136,
38602
- "arena_votes": 2867
38603
  },
38604
  {
38605
- "name": "llama-3.1-nemotron-ultra-253b-v1",
38606
- "arena_name": "llama-3.1-nemotron-ultra-253b-v1",
38607
- "arena_org": "Nvidia",
38608
- "arena_elo": 1347.5,
38609
- "arena_rank": 139,
38610
- "arena_votes": 2549
38611
  },
38612
  {
38613
  "name": "qwen-plus-0125",
38614
  "arena_name": "qwen-plus-0125",
38615
  "arena_org": "Alibaba",
38616
- "arena_elo": 1346.67,
38617
- "arena_rank": 140,
38618
  "arena_votes": 5819
38619
  },
 
 
 
 
 
 
 
 
38620
  {
38621
  "name": "glm-4-plus-0111",
38622
  "arena_name": "glm-4-plus-0111",
38623
  "arena_org": "Zhipu",
38624
- "arena_elo": 1343.4,
38625
- "arena_rank": 142,
38626
  "arena_votes": 5760
38627
  },
38628
- {
38629
- "name": "nvidia-llama-3.3-nemotron-super-49b-v1.5",
38630
- "arena_name": "nvidia-llama-3.3-nemotron-super-49b-v1.5",
38631
- "arena_org": "Nvidia",
38632
- "arena_elo": 1342,
38633
- "arena_rank": 145,
38634
- "arena_votes": 3400
38635
- },
38636
  {
38637
  "name": "hunyuan-turbo-0110",
38638
  "arena_name": "hunyuan-turbo-0110",
38639
  "arena_org": "Tencent",
38640
- "arena_elo": 1340.94,
38641
- "arena_rank": 146,
38642
  "arena_votes": 2290
38643
  },
38644
  {
38645
  "name": "nova-2-lite",
38646
  "arena_name": "nova-2-lite",
38647
  "arena_org": "Amazon",
38648
- "arena_elo": 1337.94,
38649
- "arena_rank": 148,
38650
- "arena_votes": 12060
38651
  },
38652
  {
38653
  "name": "grok-2-2024-08-13",
38654
  "arena_name": "grok-2-2024-08-13",
38655
  "arena_org": "xAI",
38656
- "arena_elo": 1335.55,
38657
- "arena_rank": 151,
38658
  "arena_votes": 63498
38659
  },
38660
  {
38661
  "name": "llama-3.1-405b-instruct-bf16",
38662
  "arena_name": "llama-3.1-405b-instruct-bf16",
38663
  "arena_org": "Meta",
38664
- "arena_elo": 1335.47,
38665
- "arena_rank": 152,
38666
  "arena_votes": 41375
38667
  },
38668
  {
38669
  "name": "gemini-advanced-0514",
38670
  "arena_name": "gemini-advanced-0514",
38671
  "arena_org": "Google",
38672
- "arena_elo": 1335.15,
38673
- "arena_rank": 154,
38674
  "arena_votes": 50148
38675
  },
38676
  {
38677
  "name": "step-2-16k-exp-202412",
38678
  "arena_name": "step-2-16k-exp-202412",
38679
  "arena_org": "StepFun",
38680
- "arena_elo": 1334.55,
38681
- "arena_rank": 155,
38682
  "arena_votes": 4833
38683
  },
38684
  {
38685
  "name": "llama-3.1-405b-instruct-fp8",
38686
  "arena_name": "llama-3.1-405b-instruct-fp8",
38687
  "arena_org": "Meta",
38688
- "arena_elo": 1333.66,
38689
- "arena_rank": 156,
38690
  "arena_votes": 59656
38691
  },
38692
  {
38693
  "name": "olmo-3.1-32b-instruct",
38694
  "arena_name": "olmo-3.1-32b-instruct",
38695
  "arena_org": "Ai2",
38696
- "arena_elo": 1331.39,
38697
- "arena_rank": 157,
38698
- "arena_votes": 12206
38699
  },
38700
  {
38701
  "name": "yi-lightning",
38702
  "arena_name": "yi-lightning",
38703
  "arena_org": "01 AI",
38704
- "arena_elo": 1328.96,
38705
- "arena_rank": 158,
38706
  "arena_votes": 27332,
38707
  "aider_pass_rate": 0.496
38708
  },
38709
- {
38710
- "name": "molmo-2-8b",
38711
- "arena_name": "molmo-2-8b",
38712
- "arena_org": "Ai2",
38713
- "arena_elo": 1328.92,
38714
- "arena_rank": 159,
38715
- "arena_votes": 817
38716
- },
38717
  {
38718
  "name": "llama-3.3-nemotron-49b-super-v1",
38719
  "arena_name": "llama-3.3-nemotron-49b-super-v1",
38720
  "arena_org": "Nvidia",
38721
- "arena_elo": 1327.96,
38722
- "arena_rank": 162,
38723
  "arena_votes": 2218
38724
  },
 
 
 
 
 
 
 
 
38725
  {
38726
  "name": "hunyuan-large-2025-02-10",
38727
  "arena_name": "hunyuan-large-2025-02-10",
38728
  "arena_org": "Tencent",
38729
- "arena_elo": 1326.51,
38730
- "arena_rank": 163,
38731
  "arena_votes": 3738
38732
  },
38733
  {
38734
  "name": "deepseek-v2.5-1210",
38735
  "arena_name": "deepseek-v2.5-1210",
38736
  "arena_org": "DeepSeek",
38737
- "arena_elo": 1323.83,
38738
- "arena_rank": 165,
38739
  "arena_votes": 6795,
38740
  "aider_pass_rate": 0.586
38741
  },
@@ -38743,8 +38896,8 @@
38743
  "name": "gemini-1.5-pro-001",
38744
  "arena_name": "gemini-1.5-pro-001",
38745
  "arena_org": "Google",
38746
- "arena_elo": 1323.41,
38747
- "arena_rank": 167,
38748
  "arena_votes": 79138,
38749
  "aider_pass_rate": 0.45899999999999996
38750
  },
@@ -38752,88 +38905,88 @@
38752
  "name": "llama-4-scout-17b-16e-instruct",
38753
  "arena_name": "llama-4-scout-17b-16e-instruct",
38754
  "arena_org": "Meta",
38755
- "arena_elo": 1322.73,
38756
- "arena_rank": 168,
38757
- "arena_votes": 30938
38758
  },
38759
  {
38760
  "name": "step-1o-turbo-202506",
38761
  "arena_name": "step-1o-turbo-202506",
38762
  "arena_org": "StepFun",
38763
- "arena_elo": 1322.02,
38764
- "arena_rank": 171,
38765
- "arena_votes": 9585
38766
  },
38767
  {
38768
  "name": "ring-flash-2.0",
38769
  "arena_name": "ring-flash-2.0",
38770
  "arena_org": "Ant Group",
38771
- "arena_elo": 1320.97,
38772
- "arena_rank": 172,
38773
- "arena_votes": 7104
38774
  },
38775
  {
38776
  "name": "glm-4-plus",
38777
  "arena_name": "glm-4-plus",
38778
  "arena_org": "Zhipu AI",
38779
- "arena_elo": 1319.72,
38780
- "arena_rank": 173,
38781
  "arena_votes": 26126
38782
  },
38783
  {
38784
  "name": "gemma-3n-e4b-it",
38785
  "arena_name": "gemma-3n-e4b-it",
38786
  "arena_org": "Google",
38787
- "arena_elo": 1319.57,
38788
- "arena_rank": 174,
38789
- "arena_votes": 23137
 
 
 
 
 
 
 
 
38790
  },
38791
  {
38792
  "name": "nvidia-nemotron-3-nano-30b-a3b-bf16",
38793
  "arena_name": "nvidia-nemotron-3-nano-30b-a3b-bf16",
38794
  "arena_org": "Nvidia",
38795
- "arena_elo": 1318.48,
38796
- "arena_rank": 176,
38797
- "arena_votes": 15376
38798
  },
38799
  {
38800
  "name": "qwen-max-0919",
38801
  "arena_name": "qwen-max-0919",
38802
  "arena_org": "Alibaba",
38803
- "arena_elo": 1318.37,
38804
- "arena_rank": 177,
38805
  "arena_votes": 16478
38806
  },
38807
- {
38808
- "name": "gpt-oss-20b",
38809
- "arena_name": "gpt-oss-20b",
38810
- "arena_org": "OpenAI",
38811
- "arena_elo": 1317.9,
38812
- "arena_rank": 179,
38813
- "arena_votes": 10748
38814
- },
38815
  {
38816
  "name": "qwen2.5-plus-1127",
38817
  "arena_name": "qwen2.5-plus-1127",
38818
  "arena_org": "Alibaba",
38819
- "arena_elo": 1315.71,
38820
- "arena_rank": 180,
38821
  "arena_votes": 10187
38822
  },
38823
  {
38824
  "name": "athene-v2-chat",
38825
  "arena_name": "athene-v2-chat",
38826
  "arena_org": "NexusFlow",
38827
- "arena_elo": 1314.85,
38828
- "arena_rank": 181,
38829
  "arena_votes": 24739
38830
  },
38831
  {
38832
  "name": "gpt-4-1106-preview",
38833
  "arena_name": "gpt-4-1106-preview",
38834
  "arena_org": "OpenAI",
38835
- "arena_elo": 1313.29,
38836
- "arena_rank": 184,
38837
  "arena_votes": 100105,
38838
  "aider_pass_rate": 0.519
38839
  },
@@ -38841,265 +38994,265 @@
38841
  "name": "hunyuan-standard-2025-02-10",
38842
  "arena_name": "hunyuan-standard-2025-02-10",
38843
  "arena_org": "Tencent",
38844
- "arena_elo": 1311.54,
38845
- "arena_rank": 185,
38846
  "arena_votes": 3904
38847
  },
38848
- {
38849
- "name": "mercury",
38850
- "arena_name": "mercury",
38851
- "arena_org": "Inception AI",
38852
- "arena_elo": 1308.76,
38853
- "arena_rank": 187,
38854
- "arena_votes": 1878
38855
- },
38856
  {
38857
  "name": "grok-2-mini-2024-08-13",
38858
  "arena_name": "grok-2-mini-2024-08-13",
38859
  "arena_org": "xAI",
38860
- "arena_elo": 1308.43,
38861
- "arena_rank": 188,
38862
  "arena_votes": 52567
38863
  },
 
 
 
 
 
 
 
 
38864
  {
38865
  "name": "olmo-3-32b-think",
38866
  "arena_name": "olmo-3-32b-think",
38867
  "arena_org": "Ai2",
38868
- "arena_elo": 1306.69,
38869
- "arena_rank": 190,
38870
- "arena_votes": 5859
38871
  },
38872
  {
38873
  "name": "athene-70b-0725",
38874
  "arena_name": "athene-70b-0725",
38875
  "arena_org": "NexusFlow",
38876
- "arena_elo": 1306.38,
38877
- "arena_rank": 191,
38878
  "arena_votes": 19621
38879
  },
38880
  {
38881
  "name": "magistral-medium-2506",
38882
  "arena_name": "magistral-medium-2506",
38883
  "arena_org": "Mistral",
38884
- "arena_elo": 1305.45,
38885
- "arena_rank": 193,
38886
- "arena_votes": 11945
38887
  },
38888
  {
38889
  "name": "mistral-small-3.1-24b-instruct-2503",
38890
  "arena_name": "mistral-small-3.1-24b-instruct-2503",
38891
  "arena_org": "Mistral",
38892
- "arena_elo": 1304.11,
38893
- "arena_rank": 194,
38894
- "arena_votes": 33824
38895
  },
38896
  {
38897
  "name": "hunyuan-large-vision",
38898
  "arena_name": "hunyuan-large-vision",
38899
  "arena_org": "Tencent",
38900
- "arena_elo": 1296.2,
38901
- "arena_rank": 198,
38902
- "arena_votes": 5553
38903
  },
38904
  {
38905
  "name": "amazon-nova-pro-v1.0",
38906
  "arena_name": "amazon-nova-pro-v1.0",
38907
  "arena_org": "Amazon",
38908
- "arena_elo": 1290.42,
38909
- "arena_rank": 200,
38910
  "arena_votes": 24745
38911
  },
38912
  {
38913
  "name": "reka-core-20240904",
38914
  "arena_name": "reka-core-20240904",
38915
  "arena_org": "Reka AI",
38916
- "arena_elo": 1288.23,
38917
- "arena_rank": 203,
38918
  "arena_votes": 7312
38919
  },
 
 
 
 
 
 
 
 
38920
  {
38921
  "name": "gpt-4-0314",
38922
  "arena_name": "gpt-4-0314",
38923
  "arena_org": "OpenAI",
38924
- "arena_elo": 1287.15,
38925
- "arena_rank": 204,
38926
  "arena_votes": 54173,
38927
  "aider_pass_rate": 0.504
38928
  },
38929
  {
38930
- "name": "ibm-granite-h-small",
38931
- "arena_name": "ibm-granite-h-small",
38932
- "arena_org": "IBM",
38933
- "arena_elo": 1286.97,
38934
- "arena_rank": 205,
38935
- "arena_votes": 5589
38936
  },
38937
  {
38938
  "name": "llama-3.1-nemotron-51b-instruct",
38939
  "arena_name": "llama-3.1-nemotron-51b-instruct",
38940
  "arena_org": "Nvidia",
38941
- "arena_elo": 1286.52,
38942
- "arena_rank": 207,
38943
  "arena_votes": 3749
38944
  },
38945
  {
38946
  "name": "gemini-1.5-flash-001",
38947
  "arena_name": "gemini-1.5-flash-001",
38948
  "arena_org": "Google",
38949
- "arena_elo": 1285.98,
38950
- "arena_rank": 208,
38951
  "arena_votes": 62833
38952
  },
38953
- {
38954
- "name": "olmo-3.1-32b-think",
38955
- "arena_name": "olmo-3.1-32b-think",
38956
- "arena_org": "Ai2",
38957
- "arena_elo": 1285.29,
38958
- "arena_rank": 209,
38959
- "arena_votes": 8408
38960
- },
38961
  {
38962
  "name": "nemotron-4-340b-instruct",
38963
  "arena_name": "nemotron-4-340b-instruct",
38964
  "arena_org": "Nvidia",
38965
- "arena_elo": 1277.58,
38966
- "arena_rank": 212,
38967
  "arena_votes": 19659
38968
  },
38969
  {
38970
  "name": "llama-3-70b-instruct",
38971
  "arena_name": "llama-3-70b-instruct",
38972
  "arena_org": "Meta",
38973
- "arena_elo": 1276.3,
38974
- "arena_rank": 214,
38975
  "arena_votes": 156876
38976
  },
38977
  {
38978
  "name": "mistral-small-24b-instruct-2501",
38979
  "arena_name": "mistral-small-24b-instruct-2501",
38980
  "arena_org": "Mistral",
38981
- "arena_elo": 1274.38,
38982
- "arena_rank": 216,
38983
  "arena_votes": 14681
38984
  },
38985
  {
38986
  "name": "glm-4-0520",
38987
  "arena_name": "glm-4-0520",
38988
  "arena_org": "Zhipu AI",
38989
- "arena_elo": 1273.66,
38990
- "arena_rank": 217,
38991
  "arena_votes": 9788
38992
  },
38993
  {
38994
  "name": "reka-flash-20240904",
38995
  "arena_name": "reka-flash-20240904",
38996
  "arena_org": "Reka AI",
38997
- "arena_elo": 1272.32,
38998
- "arena_rank": 218,
38999
  "arena_votes": 7536
39000
  },
39001
  {
39002
  "name": "c4ai-aya-expanse-32b",
39003
  "arena_name": "c4ai-aya-expanse-32b",
39004
  "arena_org": "Cohere",
39005
- "arena_elo": 1267.3,
39006
- "arena_rank": 220,
39007
  "arena_votes": 27124
39008
  },
39009
  {
39010
  "name": "amazon-nova-lite-v1.0",
39011
  "arena_name": "amazon-nova-lite-v1.0",
39012
  "arena_org": "Amazon",
39013
- "arena_elo": 1260.89,
39014
- "arena_rank": 226,
39015
  "arena_votes": 19372
39016
  },
39017
  {
39018
  "name": "olmo-2-0325-32b-instruct",
39019
  "arena_name": "olmo-2-0325-32b-instruct",
39020
  "arena_org": "Ai2",
39021
- "arena_elo": 1252.3,
39022
- "arena_rank": 229,
39023
  "arena_votes": 3334
39024
  },
39025
  {
39026
  "name": "amazon-nova-micro-v1.0",
39027
  "arena_name": "amazon-nova-micro-v1.0",
39028
  "arena_org": "Amazon",
39029
- "arena_elo": 1241.22,
39030
- "arena_rank": 232,
39031
  "arena_votes": 19364
39032
  },
39033
  {
39034
  "name": "ministral-8b-2410",
39035
  "arena_name": "ministral-8b-2410",
39036
  "arena_org": "Mistral",
39037
- "arena_elo": 1237.51,
39038
- "arena_rank": 234,
39039
  "arena_votes": 4781
39040
  },
39041
  {
39042
  "name": "gemini-pro-dev-api",
39043
  "arena_name": "gemini-pro-dev-api",
39044
  "arena_org": "Google",
39045
- "arena_elo": 1235.26,
39046
- "arena_rank": 235,
39047
  "arena_votes": 18354
39048
  },
39049
  {
39050
  "name": "hunyuan-standard-256k",
39051
  "arena_name": "hunyuan-standard-256k",
39052
  "arena_org": "Tencent",
39053
- "arena_elo": 1233.78,
39054
- "arena_rank": 237,
39055
  "arena_votes": 2728
39056
  },
39057
  {
39058
  "name": "reka-flash-21b-20240226-online",
39059
  "arena_name": "reka-flash-21b-20240226-online",
39060
  "arena_org": "Reka AI",
39061
- "arena_elo": 1233.46,
39062
- "arena_rank": 238,
39063
  "arena_votes": 15450
39064
  },
39065
  {
39066
  "name": "reka-flash-21b-20240226",
39067
  "arena_name": "reka-flash-21b-20240226",
39068
  "arena_org": "Reka AI",
39069
- "arena_elo": 1226.69,
39070
- "arena_rank": 242,
39071
  "arena_votes": 24806
39072
  },
39073
  {
39074
  "name": "c4ai-aya-expanse-8b",
39075
  "arena_name": "c4ai-aya-expanse-8b",
39076
  "arena_org": "Cohere",
39077
- "arena_elo": 1223.23,
39078
- "arena_rank": 245,
39079
  "arena_votes": 9818
39080
  },
39081
  {
39082
  "name": "mistral-medium",
39083
  "arena_name": "mistral-medium",
39084
  "arena_org": "Mistral",
39085
- "arena_elo": 1223.19,
39086
- "arena_rank": 246,
39087
  "arena_votes": 34550
39088
  },
39089
  {
39090
  "name": "gemini-pro",
39091
  "arena_name": "gemini-pro",
39092
  "arena_org": "Google",
39093
- "arena_elo": 1221.97,
39094
- "arena_rank": 247,
39095
  "arena_votes": 6390
39096
  },
39097
  {
39098
  "name": "gpt-3.5-turbo-1106",
39099
  "arena_name": "gpt-3.5-turbo-1106",
39100
  "arena_org": "OpenAI",
39101
- "arena_elo": 1202.59,
39102
- "arena_rank": 254,
39103
  "arena_votes": 16619,
39104
  "aider_pass_rate": 0.455
39105
  },
@@ -39107,280 +39260,280 @@
39107
  "name": "dbrx-instruct-preview",
39108
  "arena_name": "dbrx-instruct-preview",
39109
  "arena_org": "Databricks",
39110
- "arena_elo": 1195.22,
39111
- "arena_rank": 258,
39112
  "arena_votes": 32191
39113
  },
39114
  {
39115
  "name": "wizardlm-70b",
39116
  "arena_name": "wizardlm-70b",
39117
  "arena_org": "Microsoft",
39118
- "arena_elo": 1184.82,
39119
- "arena_rank": 261,
39120
  "arena_votes": 8214
39121
  },
39122
  {
39123
  "name": "snowflake-arctic-instruct",
39124
  "arena_name": "snowflake-arctic-instruct",
39125
  "arena_org": "Snowflake",
39126
- "arena_elo": 1179.63,
39127
- "arena_rank": 268,
39128
  "arena_votes": 32832
39129
  },
39130
  {
39131
  "name": "tulu-2-dpo-70b",
39132
  "arena_name": "tulu-2-dpo-70b",
39133
  "arena_org": "AllenAI/UW",
39134
- "arena_elo": 1178.2,
39135
- "arena_rank": 270,
39136
  "arena_votes": 6535
39137
  },
39138
  {
39139
  "name": "vicuna-33b",
39140
  "arena_name": "vicuna-33b",
39141
  "arena_org": "LMSYS",
39142
- "arena_elo": 1172.92,
39143
- "arena_rank": 272,
39144
  "arena_votes": 22479
39145
  },
39146
  {
39147
  "name": "llama-2-70b-chat",
39148
  "arena_name": "llama-2-70b-chat",
39149
  "arena_org": "Meta",
39150
- "arena_elo": 1170.95,
39151
- "arena_rank": 275,
39152
  "arena_votes": 38492
39153
  },
39154
  {
39155
  "name": "llama2-70b-steerlm-chat",
39156
  "arena_name": "llama2-70b-steerlm-chat",
39157
  "arena_org": "Nvidia",
39158
- "arena_elo": 1155.52,
39159
- "arena_rank": 281,
39160
  "arena_votes": 3585
39161
  },
39162
  {
39163
  "name": "dolphin-2.2.1-mistral-7b",
39164
  "arena_name": "dolphin-2.2.1-mistral-7b",
39165
  "arena_org": "Cognitive Computations",
39166
- "arena_elo": 1152.14,
39167
- "arena_rank": 283,
39168
  "arena_votes": 1679
39169
  },
39170
  {
39171
  "name": "mpt-30b-chat",
39172
  "arena_name": "mpt-30b-chat",
39173
  "arena_org": "MosaicML",
39174
- "arena_elo": 1150.22,
39175
- "arena_rank": 284,
39176
  "arena_votes": 2572
39177
  },
39178
  {
39179
  "name": "wizardlm-13b",
39180
  "arena_name": "wizardlm-13b",
39181
  "arena_org": "Microsoft",
39182
- "arena_elo": 1149.34,
39183
- "arena_rank": 286,
39184
  "arena_votes": 7044
39185
  },
39186
  {
39187
  "name": "falcon-180b-chat",
39188
  "arena_name": "falcon-180b-chat",
39189
  "arena_org": "TII",
39190
- "arena_elo": 1147.15,
39191
- "arena_rank": 287,
39192
  "arena_votes": 1295
39193
  },
39194
  {
39195
  "name": "phi-3-mini-4k-instruct-june-2024",
39196
  "arena_name": "phi-3-mini-4k-instruct-june-2024",
39197
  "arena_org": "Microsoft",
39198
- "arena_elo": 1143.25,
39199
- "arena_rank": 289,
39200
  "arena_votes": 12297
39201
  },
39202
  {
39203
  "name": "llama-2-13b-chat",
39204
  "arena_name": "llama-2-13b-chat",
39205
  "arena_org": "Meta",
39206
- "arena_elo": 1141.64,
39207
- "arena_rank": 290,
39208
  "arena_votes": 19174
39209
  },
39210
  {
39211
  "name": "vicuna-13b",
39212
  "arena_name": "vicuna-13b",
39213
  "arena_org": "LMSYS",
39214
- "arena_elo": 1141.04,
39215
- "arena_rank": 291,
39216
  "arena_votes": 19367
39217
  },
39218
  {
39219
  "name": "qwen-14b-chat",
39220
  "arena_name": "qwen-14b-chat",
39221
  "arena_org": "Alibaba",
39222
- "arena_elo": 1138.7,
39223
- "arena_rank": 292,
39224
  "arena_votes": 4964
39225
  },
39226
  {
39227
  "name": "palm-2",
39228
  "arena_name": "palm-2",
39229
  "arena_org": "Google",
39230
- "arena_elo": 1137.36,
39231
- "arena_rank": 293,
39232
  "arena_votes": 8554
39233
  },
39234
  {
39235
  "name": "codellama-34b-instruct",
39236
  "arena_name": "codellama-34b-instruct",
39237
  "arena_org": "Meta",
39238
- "arena_elo": 1136.7,
39239
- "arena_rank": 294,
39240
  "arena_votes": 7366
39241
  },
39242
  {
39243
  "name": "guanaco-33b",
39244
  "arena_name": "guanaco-33b",
39245
  "arena_org": "UW",
39246
- "arena_elo": 1127.45,
39247
- "arena_rank": 299,
39248
  "arena_votes": 2921
39249
  },
39250
  {
39251
  "name": "stripedhyena-nous-7b",
39252
  "arena_name": "stripedhyena-nous-7b",
39253
  "arena_org": "Together AI",
39254
- "arena_elo": 1121.1,
39255
- "arena_rank": 301,
39256
  "arena_votes": 5182
39257
  },
39258
  {
39259
  "name": "codellama-70b-instruct",
39260
  "arena_name": "codellama-70b-instruct",
39261
  "arena_org": "Meta",
39262
- "arena_elo": 1119.19,
39263
- "arena_rank": 302,
39264
  "arena_votes": 1143
39265
  },
39266
  {
39267
  "name": "vicuna-7b",
39268
  "arena_name": "vicuna-7b",
39269
  "arena_org": "LMSYS",
39270
- "arena_elo": 1114.75,
39271
- "arena_rank": 303,
39272
  "arena_votes": 6923
39273
  },
39274
  {
39275
  "name": "mistral-7b-instruct",
39276
  "arena_name": "mistral-7b-instruct",
39277
  "arena_org": "Mistral",
39278
- "arena_elo": 1109.73,
39279
- "arena_rank": 307,
39280
  "arena_votes": 8977
39281
  },
39282
  {
39283
  "name": "llama-2-7b-chat",
39284
  "arena_name": "llama-2-7b-chat",
39285
  "arena_org": "Meta",
39286
- "arena_elo": 1108.3,
39287
- "arena_rank": 308,
39288
  "arena_votes": 14148
39289
  },
39290
  {
39291
  "name": "olmo-7b-instruct",
39292
  "arena_name": "olmo-7b-instruct",
39293
  "arena_org": "Ai2",
39294
- "arena_elo": 1074.74,
39295
- "arena_rank": 311,
39296
  "arena_votes": 6328
39297
  },
39298
  {
39299
  "name": "koala-13b",
39300
  "arena_name": "koala-13b",
39301
  "arena_org": "UC Berkeley",
39302
- "arena_elo": 1070.52,
39303
- "arena_rank": 312,
39304
  "arena_votes": 6965
39305
  },
39306
  {
39307
  "name": "alpaca-13b",
39308
  "arena_name": "alpaca-13b",
39309
  "arena_org": "Stanford",
39310
- "arena_elo": 1067.49,
39311
- "arena_rank": 313,
39312
  "arena_votes": 5745
39313
  },
39314
  {
39315
  "name": "gpt4all-13b-snoozy",
39316
  "arena_name": "gpt4all-13b-snoozy",
39317
  "arena_org": "Nomic AI",
39318
- "arena_elo": 1066.04,
39319
- "arena_rank": 314,
39320
  "arena_votes": 1743
39321
  },
39322
  {
39323
  "name": "mpt-7b-chat",
39324
  "arena_name": "mpt-7b-chat",
39325
  "arena_org": "MosaicML",
39326
- "arena_elo": 1061.89,
39327
- "arena_rank": 315,
39328
  "arena_votes": 3924
39329
  },
39330
  {
39331
  "name": "chatglm3-6b",
39332
  "arena_name": "chatglm3-6b",
39333
  "arena_org": "Tsinghua",
39334
- "arena_elo": 1056.15,
39335
- "arena_rank": 316,
39336
  "arena_votes": 4658
39337
  },
39338
  {
39339
  "name": "RWKV-4-Raven-14B",
39340
  "arena_name": "RWKV-4-Raven-14B",
39341
  "arena_org": "RWKV",
39342
- "arena_elo": 1041.39,
39343
- "arena_rank": 317,
39344
  "arena_votes": 4845
39345
  },
39346
  {
39347
  "name": "chatglm2-6b",
39348
  "arena_name": "chatglm2-6b",
39349
  "arena_org": "Tsinghua",
39350
- "arena_elo": 1024.25,
39351
- "arena_rank": 318,
39352
  "arena_votes": 2658
39353
  },
39354
  {
39355
  "name": "oasst-pythia-12b",
39356
  "arena_name": "oasst-pythia-12b",
39357
  "arena_org": "OpenAssistant",
39358
- "arena_elo": 1022.13,
39359
- "arena_rank": 319,
39360
  "arena_votes": 6310
39361
  },
39362
  {
39363
  "name": "chatglm-6b",
39364
  "arena_name": "chatglm-6b",
39365
  "arena_org": "Tsinghua",
39366
- "arena_elo": 995.668,
39367
- "arena_rank": 320,
39368
  "arena_votes": 4914
39369
  },
39370
  {
39371
  "name": "fastchat-t5-3b",
39372
  "arena_name": "fastchat-t5-3b",
39373
  "arena_org": "LMSYS",
39374
- "arena_elo": 991.381,
39375
- "arena_rank": 321,
39376
  "arena_votes": 4203
39377
  },
39378
  {
39379
  "name": "stablelm-tuned-alpha-7b",
39380
  "arena_name": "stablelm-tuned-alpha-7b",
39381
  "arena_org": "Stability AI",
39382
- "arena_elo": 952.686,
39383
- "arena_rank": 324,
39384
  "arena_votes": 3287
39385
  },
39386
  {
 
7
  "gpqa": 0.369,
8
  "arc": 0.93,
9
  "gsm8k": 0.87,
10
+ "arena_elo": 1288.4,
11
+ "arena_rank": 207,
12
  "arena_votes": 8662
13
  },
14
  {
 
19
  "gpqa": 0.323,
20
  "arc": 0.857,
21
  "gsm8k": 0.758,
22
+ "arena_elo": 1238.58,
23
+ "arena_rank": 239,
24
  "arena_votes": 8858
25
  },
26
  {
 
82
  "lb_language": 0.39707333333333333,
83
  "lb_if": 0.6187925,
84
  "lb_data_analysis": 0.5411900000000001,
85
+ "arena_elo": 1322.73,
86
+ "arena_rank": 172,
87
+ "arena_votes": 70555,
88
  "aider_pass_rate": 0.617
89
  },
90
  {
 
106
  "lb_language": 0.56937,
107
  "lb_if": 0.7229999999999999,
108
  "lb_data_analysis": 0.5411,
109
+ "arena_elo": 1341.74,
110
+ "arena_rank": 150,
111
  "arena_votes": 82419,
112
  "aider_pass_rate": 0.5710000000000001
113
  },
 
132
  "lb_language": 0.54477,
133
  "lb_if": 0.69296,
134
  "lb_data_analysis": 0.5618650000000001,
135
+ "arena_elo": 1371.56,
136
+ "arena_rank": 117,
137
+ "arena_votes": 88853,
138
  "aider_pass_rate": 0.6920000000000001
139
  },
140
  {
 
157
  "lb_language": 0.30073333333333335,
158
  "lb_if": 0.6402924999999999,
159
  "lb_data_analysis": 0.3731,
160
+ "arena_elo": 1260.31,
161
+ "arena_rank": 231,
162
  "arena_votes": 117701,
163
  "aider_pass_rate": 0.406
164
  },
 
183
  "lb_language": 0.53574,
184
  "lb_if": 0.6388750000000001,
185
  "lb_data_analysis": 0.5784,
186
+ "arena_elo": 1321.14,
187
+ "arena_rank": 177,
188
  "arena_votes": 194909,
189
  "aider_pass_rate": 0.534
190
  },
 
209
  "lb_language": 0.38083333333333336,
210
  "lb_if": 0.6500425,
211
  "lb_data_analysis": 0.38839999999999997,
212
+ "arena_elo": 1280.26,
213
+ "arena_rank": 216,
214
  "arena_votes": 109284,
215
  "aider_pass_rate": 0.436
216
  },
 
228
  "lb_language": 0.14644333333333334,
229
  "lb_if": 0.571625,
230
  "lb_data_analysis": 0.2354,
231
+ "arena_elo": 1226.17,
232
+ "arena_rank": 247,
233
  "arena_votes": 54036
234
  },
235
  {
 
249
  "lb_language": 0.5477066666666667,
250
  "lb_if": 0.8050825,
251
  "lb_data_analysis": 0.69625,
252
+ "arena_elo": 1397.57,
253
+ "arena_rank": 89,
254
  "arena_votes": 18524
255
  },
256
  {
 
268
  "lb_language": 0.3518266666666667,
269
  "lb_if": 0.6915024999999999,
270
  "lb_data_analysis": 0.4417,
271
+ "arena_elo": 1306.76,
272
+ "arena_rank": 194,
273
  "arena_votes": 24572,
274
  "aider_pass_rate": 0.5489999999999999
275
  },
 
289
  "lb_language": 0.47484666666666664,
290
  "lb_if": 0.75246,
291
  "lb_data_analysis": 0.6241,
292
+ "arena_elo": 1358.28,
293
+ "arena_rank": 128,
294
  "arena_votes": 21770
295
  },
296
  {
 
385
  "lb_language": 0.32621666666666665,
386
  "lb_if": 0.5810025000000001,
387
  "lb_data_analysis": 0.4481,
388
+ "arena_elo": 1287.76,
389
+ "arena_rank": 208,
390
  "arena_votes": 75754
391
  },
392
  {
 
415
  "lb_language": 0.25531,
416
  "lb_if": 0.52621,
417
  "lb_data_analysis": 0.2959,
418
+ "arena_elo": 1265.22,
419
+ "arena_rank": 227,
420
  "arena_votes": 54611
421
  },
422
  {
 
452
  "hf_math_lvl5": 0.3806646525679758,
453
  "hf_musr": 0.45806250000000004,
454
  "hf_avg": 43.409948245645786,
455
+ "arena_elo": 1293.02,
456
+ "arena_rank": 205,
457
  "arena_votes": 55240,
458
  "aider_pass_rate": 0.436
459
  },
 
477
  "hf_math_lvl5": 0.1729607250755287,
478
  "hf_musr": 0.3845416666666666,
479
  "hf_avg": 28.01011138792457,
480
+ "arena_elo": 1211.19,
481
+ "arena_rank": 257,
482
  "arena_votes": 49605,
483
  "aider_pass_rate": 0.263
484
  },
 
509
  "hf_math_lvl5": 0.17673716012084592,
510
  "hf_musr": 0.3528541666666667,
511
  "hf_avg": 24.204650807793456,
512
+ "arena_elo": 1166.02,
513
+ "arena_rank": 283,
514
  "arena_votes": 7936
515
  },
516
  {
 
538
  "hf_math_lvl5": 0.48338368580060426,
539
  "hf_musr": 0.44612500000000005,
540
  "hf_avg": 44.84747145129876,
541
+ "arena_elo": 1318.26,
542
+ "arena_rank": 181,
543
+ "arena_votes": 55149,
544
  "aider_pass_rate": 0.42100000000000004
545
  },
546
  {
 
628
  "lb_language": 0.29333666666666663,
629
  "lb_if": 0.5838349999999999,
630
  "lb_data_analysis": 0.4376,
631
+ "arena_elo": 1255.68,
632
+ "arena_rank": 234,
633
  "arena_votes": 24126
634
  },
635
  {
 
729
  "lb_language": 0.31805,
730
  "lb_if": 0.6957099999999999,
731
  "lb_data_analysis": 0.33599999999999997,
732
+ "arena_elo": 1298.52,
733
+ "arena_rank": 203,
734
  "arena_votes": 7140
735
  },
736
  {
 
750
  "lb_language": 0.2421633333333333,
751
  "lb_if": 0.604665,
752
  "lb_data_analysis": 0.3682,
753
+ "arena_elo": 1223.27,
754
+ "arena_rank": 249,
755
  "arena_votes": 66207,
756
  "aider_pass_rate": 0.414
757
  },
 
773
  "lb_language": 0.4956833333333333,
774
  "lb_if": 0.717875,
775
  "lb_data_analysis": 0.39039999999999997,
776
+ "arena_elo": 1274.35,
777
+ "arena_rank": 221,
778
  "arena_votes": 88723,
779
  "aider_pass_rate": 0.466
780
  },
 
794
  "lb_language": 0.45262,
795
  "lb_if": 0.713875,
796
  "lb_data_analysis": 0.4998,
797
+ "arena_elo": 1323.69,
798
+ "arena_rank": 170,
799
  "arena_votes": 98114
800
  },
801
  {
 
815
  "lb_language": 0.5393533333333334,
816
  "lb_if": 0.7217100000000001,
817
  "lb_data_analysis": 0.4661,
818
+ "arena_elo": 1345.32,
819
+ "arena_rank": 147,
820
  "arena_votes": 112881,
821
  "aider_pass_rate": 0.602
822
  },
 
834
  "lb_language": 0.4563466666666667,
835
  "lb_if": 0.6858299999999999,
836
  "lb_data_analysis": 0.6236999999999999,
837
+ "arena_elo": 1334.54,
838
+ "arena_rank": 159,
839
  "arena_votes": 45499,
840
  "aider_pass_rate": 0.5710000000000001
841
  },
 
857
  "lb_language": 0.29879333333333336,
858
  "lb_if": 0.5679974999999999,
859
  "lb_data_analysis": 0.55099,
860
+ "arena_elo": 1317.42,
861
+ "arena_rank": 185,
862
+ "arena_votes": 68757,
863
  "aider_pass_rate": 0.406
864
  },
865
  {
 
880
  "hf_math_lvl5": 0.37462235649546827,
881
  "hf_musr": 0.41384375,
882
  "hf_avg": 27.639223265636087,
883
+ "arena_elo": 1401.7,
884
+ "arena_rank": 82,
885
  "arena_votes": 27807,
886
  "aider_pass_rate": 0.654
887
  },
 
892
  "mmlu": 0.852,
893
  "gpqa": 0.6,
894
  "math": 0.9,
895
+ "arena_elo": 1336.65,
896
+ "arena_rank": 155,
897
  "arena_votes": 51981,
898
  "aider_pass_rate": 0.5
899
  },
 
904
  "mmlu": 0.908,
905
  "gpqa": 0.733,
906
  "mgsm": 0.908,
907
+ "arena_elo": 1387.82,
908
+ "arena_rank": 100,
909
  "arena_votes": 31122,
910
  "aider_pass_rate": 0.579
911
  },
 
921
  "mmlu": 0.869,
922
  "math": 0.979,
923
  "mgsm": 0.92,
924
+ "arena_elo": 1347.69,
925
+ "arena_rank": 140,
926
+ "arena_votes": 57950
927
  },
928
  {
929
  "slug": "openai/o3",
 
997
  "lb_language": 0.38114999999999993,
998
  "lb_if": 0.7550025,
999
  "lb_data_analysis": 0.4718,
1000
+ "arena_elo": 1302.47,
1001
+ "arena_rank": 202,
1002
  "arena_votes": 39406
1003
  },
1004
  {
 
1044
  "lb_language": 0.23245333333333332,
1045
  "lb_if": 0.5869175,
1046
  "lb_data_analysis": 0.48810000000000003,
1047
+ "arena_elo": 1270.13,
1048
+ "arena_rank": 225,
1049
  "arena_votes": 5432,
1050
  "aider_pass_rate": 0.594
1051
  },
 
1096
  "lb_language": 0.29213666666666666,
1097
  "lb_if": 0.68271,
1098
  "lb_data_analysis": 0.1636,
1099
+ "arena_elo": 1261.13,
1100
+ "arena_rank": 230,
1101
  "arena_votes": 37325,
1102
  "aider_pass_rate": 0.444
1103
  },
 
1160
  "lb_language": 0.21091000000000001,
1161
  "lb_if": 0.35587499999999994,
1162
  "lb_data_analysis": 0.25925,
1163
+ "arena_elo": 1156.25,
1164
+ "arena_rank": 285,
1165
  "arena_votes": 3231
1166
  },
1167
  {
 
1263
  "hf_math_lvl5": 0.277190332326284,
1264
  "hf_musr": 0.4281979166666667,
1265
  "hf_avg": 33.35799367075618,
1266
+ "arena_elo": 1212.77,
1267
+ "arena_rank": 255,
1268
  "arena_votes": 24146
1269
  },
1270
  {
 
1386
  "hf_math_lvl5": 0.06268882175226587,
1387
  "hf_musr": 0.39784375,
1388
  "hf_avg": 24.226662652803373,
1389
+ "arena_elo": 1183.11,
1390
+ "arena_rank": 269,
1391
  "arena_votes": 15483
1392
  },
1393
  {
 
1673
  "hf_math_lvl5": 0.03851963746223565,
1674
  "hf_musr": 0.47709375000000004,
1675
  "hf_avg": 14.343669671742774,
1676
+ "arena_elo": 1222.56,
1677
+ "arena_rank": 250,
1678
  "arena_votes": 104642
1679
  },
1680
  {
 
6142
  "lb_language": 0.07196666666666666,
6143
  "lb_if": 0.5279175,
6144
  "lb_data_analysis": 0.081,
6145
+ "arena_elo": 1126.09,
6146
+ "arena_rank": 306,
6147
  "arena_votes": 1785
6148
  },
6149
  {
 
6164
  "lb_language": 0.042846666666666665,
6165
  "lb_if": 0.48317,
6166
  "lb_data_analysis": 0.0762,
6167
+ "arena_elo": 1130.23,
6168
+ "arena_rank": 302,
6169
  "arena_votes": 11118
6170
  },
6171
  {
 
6191
  "hf_math_lvl5": 0.20468277945619334,
6192
  "hf_musr": 0.4465208333333333,
6193
  "hf_avg": 34.125963384670946,
6194
+ "arena_elo": 1211.97,
6195
+ "arena_rank": 256,
6196
  "arena_votes": 4652
6197
  },
6198
  {
 
6290
  "hf_math_lvl5": 0.0581570996978852,
6291
  "hf_musr": 0.342125,
6292
  "hf_avg": 15.02227766709556,
6293
+ "arena_elo": 1113.56,
6294
+ "arena_rank": 311,
6295
  "arena_votes": 2199
6296
  },
6297
  {
 
10127
  "hf_math_lvl5": 0.12235649546827794,
10128
  "hf_musr": 0.4595416666666667,
10129
  "hf_avg": 27.353190438571634,
10130
+ "arena_elo": 1163.95,
10131
+ "arena_rank": 284,
10132
  "arena_votes": 3777
10133
  },
10134
  {
 
11176
  "lb_language": 0.5148133333333332,
11177
  "lb_if": 0.81829,
11178
  "lb_data_analysis": 0.69529,
11179
+ "arena_elo": 1335.63,
11180
+ "arena_rank": 156,
11181
+ "arena_votes": 25749
11182
  },
11183
  {
11184
  "hf_id": "Qwen/Qwen1.5-0.5B",
 
11272
  "lb_language": 0.13224333333333332,
11273
  "lb_if": 0.5526275,
11274
  "lb_data_analysis": 0.20179999999999998,
11275
+ "arena_elo": 1233.37,
11276
+ "arena_rank": 242,
11277
  "arena_votes": 26195,
11278
  "aider_pass_rate": 0.308
11279
  },
 
11300
  "hf_math_lvl5": 0.15256797583081572,
11301
  "hf_musr": 0.43997916666666664,
11302
  "hf_avg": 23.566106475051374,
11303
+ "arena_elo": 1190.19,
11304
+ "arena_rank": 266,
11305
  "arena_votes": 17839
11306
  },
11307
  {
 
11327
  "hf_math_lvl5": 0.19561933534743203,
11328
  "hf_musr": 0.4159791666666666,
11329
  "hf_avg": 29.25746822860332,
11330
+ "arena_elo": 1203.09,
11331
+ "arena_rank": 259,
11332
  "arena_votes": 21741
11333
  },
11334
  {
 
11361
  "lb_language": 0.05798333333333333,
11362
  "lb_if": 0.27749999999999997,
11363
  "lb_data_analysis": 0.0469,
11364
+ "arena_elo": 1089.35,
11365
+ "arena_rank": 316,
11366
  "arena_votes": 7597
11367
  },
11368
  {
 
11395
  "lb_language": 0.061816666666666666,
11396
  "lb_if": 0.4411675,
11397
  "lb_data_analysis": 0.0435,
11398
+ "arena_elo": 1143.03,
11399
+ "arena_rank": 294,
11400
  "arena_votes": 4737
11401
  },
11402
  {
 
16644
  "hf_math_lvl5": 0.4501510574018127,
16645
  "hf_musr": 0.4948333333333334,
16646
  "hf_avg": 42.33178738532094,
16647
+ "arena_elo": 1286.08,
16648
+ "arena_rank": 212,
16649
  "arena_votes": 2846
16650
  },
16651
  {
 
16695
  "hf_math_lvl5": 0.19637462235649547,
16696
  "hf_musr": 0.41746875,
16697
  "hf_avg": 26.034998081672143,
16698
+ "arena_elo": 1220.6,
16699
+ "arena_rank": 254,
16700
  "arena_votes": 2896
16701
  },
16702
  {
 
18637
  "hf_math_lvl5": 0.08383685800604229,
18638
  "hf_musr": 0.41201041666666666,
18639
  "hf_avg": 20.83936104726783,
18640
+ "arena_elo": 1166.75,
18641
+ "arena_rank": 282,
18642
  "arena_votes": 10224
18643
  },
18644
  {
 
19608
  "hf_math_lvl5": 0.013595166163141994,
19609
  "hf_musr": 0.37390625000000005,
19610
  "hf_avg": 6.3704357034963754,
19611
+ "arena_elo": 979.252,
19612
+ "arena_rank": 328,
19613
  "arena_votes": 3412
19614
  },
19615
  {
 
19759
  "hf_math_lvl5": 0.09290030211480363,
19760
  "hf_musr": 0.5058645833333334,
19761
  "hf_avg": 27.310631874736753,
19762
+ "arena_elo": 1183.6,
19763
+ "arena_rank": 268,
19764
  "arena_votes": 4932
19765
  },
19766
  {
 
21237
  "hf_math_lvl5": 0.01812688821752266,
21238
  "hf_musr": 0.33939583333333334,
21239
  "hf_avg": 8.053373854341979,
21240
+ "arena_elo": 1113.71,
21241
+ "arena_rank": 310,
21242
  "arena_votes": 10854
21243
  },
21244
  {
 
21259
  "lb_language": 0.10647333333333332,
21260
  "lb_if": 0.443375,
21261
  "lb_data_analysis": 0.0726,
21262
+ "arena_elo": 1179.83,
21263
+ "arena_rank": 273,
21264
  "arena_votes": 23893
21265
  },
21266
  {
 
21298
  "hf_math_lvl5": 0.0007552870090634441,
21299
  "hf_musr": 0.39288541666666665,
21300
  "hf_avg": 17.046939294966545,
21301
+ "arena_elo": 1198.66,
21302
+ "arena_rank": 261,
21303
  "arena_votes": 46616
21304
  },
21305
  {
 
21349
  "hf_math_lvl5": 0.02039274924471299,
21350
  "hf_musr": 0.334125,
21351
  "hf_avg": 7.485804130315127,
21352
+ "arena_elo": 1091.14,
21353
+ "arena_rank": 315,
21354
  "arena_votes": 4780
21355
  },
21356
  {
 
21376
  "hf_math_lvl5": 0.02945619335347432,
21377
  "hf_musr": 0.42742708333333335,
21378
  "hf_avg": 13.067087110466217,
21379
+ "arena_elo": 1135.54,
21380
+ "arena_rank": 301,
21381
  "arena_votes": 8925
21382
  },
21383
  {
 
22381
  "hf_math_lvl5": 0.02039274924471299,
22382
  "hf_musr": 0.34621875,
22383
  "hf_avg": 9.39218439885523,
22384
+ "arena_elo": 971.349,
22385
+ "arena_rank": 329,
22386
  "arena_votes": 2391
22387
  },
22388
  {
 
22696
  "hf_math_lvl5": 0.09214501510574018,
22697
  "hf_musr": 0.35148958333333336,
22698
  "hf_avg": 18.396095114284222,
22699
+ "arena_elo": 1155.28,
22700
+ "arena_rank": 286,
22701
  "arena_votes": 6837
22702
  },
22703
  {
 
22747
  "hf_math_lvl5": 0.1419939577039275,
22748
  "hf_musr": 0.3900625,
22749
  "hf_avg": 24.027678753483297,
22750
+ "arena_elo": 1181.3,
22751
+ "arena_rank": 272,
22752
  "arena_votes": 6638
22753
  },
22754
  {
 
22798
  "hf_math_lvl5": 0.15256797583081572,
22799
  "hf_musr": 0.3605416666666667,
22800
  "hf_avg": 21.712212822028288,
22801
+ "arena_elo": 1178.27,
22802
+ "arena_rank": 275,
22803
  "arena_votes": 3188
22804
  },
22805
  {
 
22849
  "hf_math_lvl5": 0.21978851963746224,
22850
  "hf_musr": 0.47070833333333334,
22851
  "hf_avg": 30.6030430081627,
22852
+ "arena_elo": 1207.73,
22853
+ "arena_rank": 258,
22854
  "arena_votes": 3090
22855
  },
22856
  {
 
23318
  "hf_math_lvl5": 0.4078549848942598,
23319
  "hf_musr": 0.4558229166666667,
23320
  "hf_avg": 38.87959582082076,
23321
+ "arena_elo": 1190.75,
23322
+ "arena_rank": 265,
23323
  "arena_votes": 9901
23324
  },
23325
  {
 
25538
  "hf_math_lvl5": 0.0702416918429003,
25539
  "hf_musr": 0.3328541666666667,
25540
  "hf_avg": 14.443126333711135,
25541
+ "arena_elo": 1110.58,
25542
+ "arena_rank": 312,
25543
  "arena_votes": 8045
25544
  },
25545
  {
 
25719
  "lb_language": 0.13909000000000002,
25720
  "lb_if": 0.5330400000000001,
25721
  "lb_data_analysis": 0.2044,
25722
+ "arena_elo": 1197.21,
25723
+ "arena_rank": 262,
25724
  "arena_votes": 25055
25725
  },
25726
  {
 
25741
  "lb_language": 0.09153666666666667,
25742
  "lb_if": 0.39083500000000004,
25743
  "lb_data_analysis": 0.26030000000000003,
25744
+ "arena_elo": 1128.43,
25745
+ "arena_rank": 303,
25746
  "arena_votes": 20685
25747
  },
25748
  {
 
25763
  "lb_language": 0.08559,
25764
  "lb_if": 0.363625,
25765
  "lb_data_analysis": 0.2232,
25766
+ "arena_elo": 1127.64,
25767
+ "arena_rank": 304,
25768
  "arena_votes": 20118
25769
  },
25770
  {
 
25823
  "lb_language": 0.12944,
25824
  "lb_if": 0.472,
25825
  "lb_data_analysis": 0.2343,
25826
+ "arena_elo": 1170.35,
25827
+ "arena_rank": 280,
25828
  "arena_votes": 17766
25829
  },
25830
  {
 
26072
  "lb_language": 0.09055,
26073
  "lb_if": 0.5165025,
26074
  "lb_data_analysis": 0.059300000000000005,
26075
+ "arena_elo": 1148.81,
26076
+ "arena_rank": 291,
26077
  "arena_votes": 19402
26078
  },
26079
  {
 
26197
  "lb_language": 0.26477666666666666,
26198
  "lb_if": 0.63167,
26199
  "lb_data_analysis": 0.255,
26200
+ "arena_elo": 1228.68,
26201
+ "arena_rank": 246,
26202
  "arena_votes": 51416
26203
  },
26204
  {
 
26231
  "lb_language": 0.13761333333333334,
26232
  "lb_if": 0.4480825,
26233
  "lb_data_analysis": 0.1619,
26234
+ "arena_elo": 1196.37,
26235
+ "arena_rank": 263,
26236
  "arena_votes": 73503
26237
  },
26238
  {
 
28559
  "hf_math_lvl5": 0.07628398791540786,
28560
  "hf_musr": 0.42543749999999997,
28561
  "hf_avg": 22.70925524673515,
28562
+ "arena_elo": 1181.47,
28563
+ "arena_rank": 270,
28564
  "arena_votes": 12637
28565
  },
28566
  {
 
28598
  "hf_math_lvl5": 0.07250755287009064,
28599
  "hf_musr": 0.4228645833333333,
28600
  "hf_avg": 21.635827111564595,
28601
+ "arena_elo": 1181.4,
28602
+ "arena_rank": 271,
28603
  "arena_votes": 7968
28604
  },
28605
  {
 
29752
  "hf_math_lvl5": 0.07099697885196375,
29753
  "hf_musr": 0.41232291666666665,
29754
  "hf_avg": 22.3449346084354,
29755
+ "arena_elo": 1279.01,
29756
+ "arena_rank": 217,
29757
  "arena_votes": 10072
29758
  },
29759
  {
 
33248
  "lb_language": 0.11368333333333334,
33249
  "lb_if": 0.52779,
33250
  "lb_data_analysis": 0.1738,
33251
+ "arena_elo": 1174.38,
33252
+ "arena_rank": 277,
33253
  "arena_votes": 5006
33254
  },
33255
  {
 
34302
  "hf_math_lvl5": 0.05664652567975831,
34303
  "hf_musr": 0.3899375,
34304
  "hf_avg": 20.57236409322395,
34305
+ "arena_elo": 1151.55,
34306
+ "arena_rank": 288,
34307
  "arena_votes": 4155
34308
  },
34309
  {
 
35718
  "lb_language": 0.2793333333333334,
35719
  "lb_if": 0.5561674999999999,
35720
  "lb_data_analysis": 0.39766500000000005,
35721
+ "arena_elo": 1249.47,
35722
+ "arena_rank": 236,
35723
  "arena_votes": 10140
35724
  },
35725
  {
 
35731
  "lb_language": 0.23921666666666663,
35732
  "lb_if": 0.7150825,
35733
  "lb_data_analysis": 0.179,
35734
+ "arena_elo": 1261.18,
35735
+ "arena_rank": 229,
35736
  "arena_votes": 77554,
35737
  "aider_pass_rate": 0.218
35738
  },
 
35746
  "lb_language": 0.3086066666666667,
35747
  "lb_if": 0.5761225,
35748
  "lb_data_analysis": 0.492345,
35749
+ "arena_elo": 1275.86,
35750
+ "arena_rank": 219,
35751
  "arena_votes": 9866
35752
  },
35753
  {
 
35759
  "lb_language": 0.33044,
35760
  "lb_if": 0.6718325,
35761
  "lb_data_analysis": 0.3438,
35762
+ "arena_elo": 1263.7,
35763
+ "arena_rank": 228,
35764
  "arena_votes": 15147
35765
  },
35766
  {
 
35865
  "lb_language": 0.43553333333333333,
35866
  "lb_if": 0.6392074999999999,
35867
  "lb_data_analysis": 0.5308999999999999,
35868
+ "arena_elo": 1312.65,
35869
+ "arena_rank": 189,
35870
  "arena_votes": 93439,
35871
  "aider_pass_rate": 0.556
35872
  },
 
35919
  "lb_language": 0.28744,
35920
  "lb_if": 0.6819175000000001,
35921
  "lb_data_analysis": 0.3983,
35922
+ "arena_elo": 1241.63,
35923
+ "arena_rank": 237,
35924
  "arena_votes": 62436
35925
  },
35926
  {
 
35932
  "lb_language": 0.3979266666666667,
35933
  "lb_if": 0.7184575000000001,
35934
  "lb_data_analysis": 0.42910000000000004,
35935
+ "arena_elo": 1313.58,
35936
+ "arena_rank": 188,
35937
  "arena_votes": 45459
35938
  },
35939
  {
 
35965
  "lb_language": 0.11368333333333332,
35966
  "lb_if": 0.5824975,
35967
  "lb_data_analysis": 0.2347,
35968
+ "arena_elo": 1232.45,
35969
+ "arena_rank": 245,
35970
  "arena_votes": 39302
35971
  },
35972
  {
 
35988
  "lb_language": 0.07264333333333332,
35989
  "lb_if": 0.3832075,
35990
  "lb_data_analysis": 0.03,
35991
+ "arena_elo": 1170.9,
35992
+ "arena_rank": 279,
35993
  "arena_votes": 16056
35994
  },
35995
  {
 
36044
  "lb_language": 0.29534,
36045
  "lb_if": 0.8454575,
36046
  "lb_data_analysis": 0.39359999999999995,
36047
+ "arena_elo": 1309.34,
36048
+ "arena_rank": 192,
36049
  "arena_votes": 34902
36050
  },
36051
  {
 
36057
  "lb_language": 0.4740566666666666,
36058
  "lb_if": 0.7774575,
36059
  "lb_data_analysis": 0.5145,
36060
+ "arena_elo": 1350.89,
36061
+ "arena_rank": 136,
36062
  "arena_votes": 55606,
36063
  "aider_pass_rate": 0.496
36064
  },
 
36212
  "lb_language": 0.3427633333333333,
36213
  "lb_if": 0.782835,
36214
  "lb_data_analysis": 0.5621,
36215
+ "arena_elo": 1352.95,
36216
+ "arena_rank": 135,
36217
  "arena_votes": 24955
36218
  },
36219
  {
 
36298
  "lb_language": 0.40453333333333336,
36299
  "lb_if": 0.67929,
36300
  "lb_data_analysis": 0.541955,
36301
+ "arena_elo": 1304.87,
36302
+ "arena_rank": 198,
36303
  "arena_votes": 28073,
36304
  "aider_pass_rate": 0.466
36305
  },
 
36404
  "lb_language": 0.5836933333333333,
36405
  "lb_if": 0.7534574999999999,
36406
  "lb_data_analysis": 0.64271,
36407
+ "arena_elo": 1374.47,
36408
+ "arena_rank": 114,
36409
+ "arena_votes": 32882
36410
  },
36411
  {
36412
  "name": "gpt-4.5-preview",
 
36449
  "lb_language": 0.41314333333333336,
36450
  "lb_if": 0.7490399999999999,
36451
  "lb_data_analysis": 0.387965,
36452
+ "arena_elo": 1365.3,
36453
+ "arena_rank": 122,
36454
+ "arena_votes": 48195
36455
  },
36456
  {
36457
  "name": "gemini-2.5-pro-exp-03-25",
 
36473
  "lb_language": 0.4682266666666666,
36474
  "lb_if": 0.8147075,
36475
  "lb_data_analysis": 0.64019,
36476
+ "arena_elo": 1394.34,
36477
+ "arena_rank": 93,
36478
+ "arena_votes": 46144
36479
  },
36480
  {
36481
  "name": "chatgpt-4o-latest-2025-03-27",
 
36519
  "lb_language": 0.6319400000000001,
36520
  "lb_if": 0.764915,
36521
  "lb_data_analysis": 0.599645,
36522
+ "arena_elo": 1370.74,
36523
+ "arena_rank": 118,
36524
+ "arena_votes": 43753
36525
  },
36526
  {
36527
  "name": "command-a-03-2025",
 
36533
  "lb_language": 0.36696,
36534
  "lb_if": 0.82904,
36535
  "lb_data_analysis": 0.48457000000000006,
36536
+ "arena_elo": 1353.53,
36537
+ "arena_rank": 133,
36538
+ "arena_votes": 57068
36539
  },
36540
  {
36541
  "name": "gemini-1.5-flash-8b-001",
 
36546
  "lb_language": 0.22867666666666667,
36547
  "lb_if": 0.6971649999999999,
36548
  "lb_data_analysis": 0.4241,
36549
+ "arena_elo": 1258.37,
36550
+ "arena_rank": 233,
36551
  "arena_votes": 35558
36552
  },
36553
  {
 
36559
  "lb_language": 0.42386999999999997,
36560
  "lb_if": 0.8578749999999999,
36561
  "lb_data_analysis": 0.7332000000000001,
36562
+ "arena_elo": 1360.31,
36563
+ "arena_rank": 127,
36564
+ "arena_votes": 44240
36565
  },
36566
  {
36567
  "name": "gemini-2.0-flash-lite-001",
 
36583
  "lb_language": 0.3126966666666667,
36584
  "lb_if": 0.7382925,
36585
  "lb_data_analysis": 0.4284,
36586
+ "arena_elo": 1341.52,
36587
+ "arena_rank": 151,
36588
  "arena_votes": 3829
36589
  },
36590
  {
 
36596
  "lb_language": 0.15059333333333333,
36597
  "lb_if": 0.6358325,
36598
  "lb_data_analysis": 0.36950000000000005,
36599
+ "arena_elo": 1302.91,
36600
+ "arena_rank": 200,
36601
  "arena_votes": 4171
36602
  },
36603
  {
 
36610
  "lb_language": 0.6475866666666666,
36611
  "lb_if": 0.72325,
36612
  "lb_data_analysis": 0.600695,
36613
+ "arena_elo": 1444.25,
36614
+ "arena_rank": 32,
36615
  "arena_votes": 14547
36616
  },
36617
  {
 
36623
  "lb_language": 0.4964766666666667,
36624
  "lb_if": 0.7574575,
36625
  "lb_data_analysis": 0.6155,
36626
+ "arena_elo": 1326.83,
36627
+ "arena_rank": 167,
36628
+ "arena_votes": 40529
36629
  },
36630
  {
36631
  "name": "grok-3-beta",
 
36659
  "lb_language": 0.54551,
36660
  "lb_if": 0.7704575,
36661
  "lb_data_analysis": 0.66404,
36662
+ "arena_elo": 1413.19,
36663
+ "arena_rank": 68,
36664
+ "arena_votes": 51831
36665
  },
36666
  {
36667
  "name": "gpt-4.1-mini-2025-04-14",
 
36673
  "lb_language": 0.37996,
36674
  "lb_if": 0.7030825,
36675
  "lb_data_analysis": 0.6133799999999999,
36676
+ "arena_elo": 1382.03,
36677
+ "arena_rank": 109,
36678
+ "arena_votes": 39876
36679
  },
36680
  {
36681
  "name": "gpt-4.1-nano-2025-04-14",
 
36687
  "lb_language": 0.30958,
36688
  "lb_if": 0.5753725,
36689
  "lb_data_analysis": 0.498195,
36690
+ "arena_elo": 1321.52,
36691
+ "arena_rank": 175,
36692
  "arena_votes": 6103
36693
  },
36694
  {
 
36778
  "lb_language": 0.6482266666666666,
36779
  "lb_if": 0.79954,
36780
  "lb_data_analysis": 0.7153849999999999,
36781
+ "arena_elo": 1421.02,
36782
+ "arena_rank": 55,
36783
+ "arena_votes": 18831
36784
  },
36785
  {
36786
  "name": "gemini-2.5-flash-preview-05-20",
 
36847
  "lb_language": 0.44743666666666665,
36848
  "lb_if": 0.7139575,
36849
  "lb_data_analysis": 0.602025,
36850
+ "arena_elo": 1386.02,
36851
+ "arena_rank": 105,
36852
+ "arena_votes": 33805
36853
  },
36854
  {
36855
  "name": "phi-4-reasoning-plus",
 
36883
  "lb_language": 0.60609,
36884
  "lb_if": 0.8772925,
36885
  "lb_data_analysis": 0.68308,
36886
+ "arena_elo": 1374.5,
36887
+ "arena_rank": 113,
36888
+ "arena_votes": 26679
36889
  },
36890
  {
36891
  "name": "qwen3-30b-a3b",
 
36897
  "lb_language": 0.54465,
36898
  "lb_if": 0.21108249999999998,
36899
  "lb_data_analysis": 0.44922666666666666,
36900
+ "arena_elo": 1327.69,
36901
+ "arena_rank": 165,
36902
+ "arena_votes": 26908
36903
  },
36904
  {
36905
  "name": "qwen3-32b",
 
36911
  "lb_language": 0.5554233333333333,
36912
  "lb_if": 0.1777075,
36913
  "lb_data_analysis": 0.4654,
36914
+ "arena_elo": 1347,
36915
+ "arena_rank": 142,
36916
  "arena_votes": 3926
36917
  },
36918
  {
 
36936
  "lb_language": 0.7599833333333333,
36937
  "lb_if": 0.2352075,
36938
  "lb_data_analysis": 0.47005,
36939
+ "arena_elo": 1452.62,
36940
+ "arena_rank": 23,
36941
+ "arena_votes": 53556
36942
  },
36943
  {
36944
  "name": "deepseek-v3.1-terminus",
 
36950
  "lb_language": 0.63882,
36951
  "lb_if": 0.8189575,
36952
  "lb_data_analysis": 0.67298,
36953
+ "arena_elo": 1415.62,
36954
+ "arena_rank": 65,
36955
+ "arena_votes": 3736
36956
  },
36957
  {
36958
  "name": "gemini-2.5-flash-06-05",
 
36997
  "lb_language": 0.6534300000000001,
36998
  "lb_if": 0.2767925,
36999
  "lb_data_analysis": 0.6098266666666666,
37000
+ "arena_elo": 1405.3,
37001
+ "arena_rank": 79,
37002
+ "arena_votes": 33278
37003
  },
37004
  {
37005
  "name": "gemini-2.5-pro-06-05",
 
37022
  "lb_language": 0.6162266666666666,
37023
  "lb_if": 0.8157925,
37024
  "lb_data_analysis": 0.6628999999999999,
37025
+ "arena_elo": 1410.68,
37026
+ "arena_rank": 72,
37027
+ "arena_votes": 24640
37028
  },
37029
  {
37030
  "name": "glm-4.5-air",
 
37036
  "lb_language": 0.44289666666666666,
37037
  "lb_if": 0.7883775000000001,
37038
  "lb_data_analysis": 0.65962,
37039
+ "arena_elo": 1372.36,
37040
+ "arena_rank": 116,
37041
+ "arena_votes": 31546
37042
  },
37043
  {
37044
  "name": "glm-4.6",
 
37050
  "lb_language": 0.5898633333333333,
37051
  "lb_if": 0.26192,
37052
  "lb_data_analysis": 0.5194766666666667,
37053
+ "arena_elo": 1425.85,
37054
+ "arena_rank": 47,
37055
+ "arena_votes": 36102
37056
  },
37057
  {
37058
  "name": "gpt-5",
 
37086
  "lb_language": 0.8082699999999999,
37087
  "lb_if": 0.8811249999999999,
37088
  "lb_data_analysis": 0.716345,
37089
+ "arena_elo": 1433.82,
37090
+ "arena_rank": 40,
37091
+ "arena_votes": 32470
37092
  },
37093
  {
37094
  "name": "gpt-5-low",
 
37122
  "lb_language": 0.7552066666666667,
37123
  "lb_if": 0.65271,
37124
  "lb_data_analysis": 0.55195,
37125
+ "arena_elo": 1389.79,
37126
+ "arena_rank": 97,
37127
+ "arena_votes": 27372
37128
  },
37129
  {
37130
  "name": "gpt-5-mini-low",
 
37180
  "lb_language": 0.46841666666666665,
37181
  "lb_if": 0.5569975,
37182
  "lb_data_analysis": 0.4340566666666667,
37183
+ "arena_elo": 1336.97,
37184
+ "arena_rank": 154,
37185
+ "arena_votes": 8349
37186
  },
37187
  {
37188
  "name": "gpt-5-nano-low",
 
37216
  "lb_language": 0.62963,
37217
  "lb_if": 0.7300425,
37218
  "lb_data_analysis": 0.644815,
37219
+ "arena_elo": 1426.22,
37220
+ "arena_rank": 46,
37221
+ "arena_votes": 32009
37222
  },
37223
  {
37224
  "name": "gpt-oss-120b",
 
37230
  "lb_language": 0.48590666666666665,
37231
  "lb_if": 0.5029175,
37232
  "lb_data_analysis": 0.38804999999999995,
37233
+ "arena_elo": 1353.82,
37234
+ "arena_rank": 132,
37235
+ "arena_votes": 31077
37236
  },
37237
  {
37238
  "name": "grok-4-0709",
 
37244
  "lb_language": 0.76388,
37245
  "lb_if": 0.29075,
37246
  "lb_data_analysis": 0.6337666666666667,
37247
+ "arena_elo": 1410.08,
37248
+ "arena_rank": 73,
37249
+ "arena_votes": 42034
37250
  },
37251
  {
37252
  "name": "grok-code-fast-1-0825",
 
37280
  "lb_language": 0.6606966666666668,
37281
  "lb_if": 0.2172075,
37282
  "lb_data_analysis": 0.4471566666666667,
37283
+ "arena_elo": 1422.08,
37284
+ "arena_rank": 53,
37285
+ "arena_votes": 77683
37286
  },
37287
  {
37288
  "name": "qwen3-235b-a22b-thinking-2507",
 
37294
  "lb_language": 0.6952366666666666,
37295
  "lb_if": 0.40641999999999995,
37296
  "lb_data_analysis": 0.5218266666666667,
37297
+ "arena_elo": 1399.16,
37298
+ "arena_rank": 87,
37299
+ "arena_votes": 9128
37300
  },
37301
  {
37302
  "name": "qwen3-coder-480b-a35b-instruct",
 
37308
  "lb_language": 0.6426233333333333,
37309
  "lb_if": 0.741625,
37310
  "lb_data_analysis": 0.64683,
37311
+ "arena_elo": 1387.09,
37312
+ "arena_rank": 102,
37313
+ "arena_votes": 26162
37314
  },
37315
  {
37316
  "name": "qwen3-max-2025-09-23",
 
37322
  "lb_language": 0.7144733333333333,
37323
  "lb_if": 0.76546,
37324
  "lb_data_analysis": 0.6536649999999999,
37325
+ "arena_elo": 1424.43,
37326
+ "arena_rank": 50,
37327
+ "arena_votes": 9273
37328
  },
37329
  {
37330
  "name": "qwen3-next-80b-a3b-instruct",
 
37336
  "lb_language": 0.6633766666666666,
37337
  "lb_if": 0.191875,
37338
  "lb_data_analysis": 0.49784,
37339
+ "arena_elo": 1401.49,
37340
+ "arena_rank": 83,
37341
+ "arena_votes": 23187
37342
  },
37343
  {
37344
  "name": "qwen3-next-80b-a3b",
 
37350
  "lb_language": 0.5631166666666667,
37351
  "lb_if": 0.41541999999999996,
37352
  "lb_data_analysis": 0.5358333333333333,
37353
+ "arena_elo": 1368.85,
37354
+ "arena_rank": 119,
37355
+ "arena_votes": 13906
37356
  },
37357
  {
37358
  "name": "claude-haiku-4-5-20251001",
 
37364
  "lb_language": 0.5704566666666667,
37365
  "lb_if": 0.17754250000000002,
37366
  "lb_data_analysis": 0.45124999999999993,
37367
+ "arena_elo": 1406.84,
37368
+ "arena_rank": 76,
37369
+ "arena_votes": 54261
37370
  },
37371
  {
37372
  "name": "deepseek-v3.2-exp",
 
37378
  "lb_language": 0.65596,
37379
  "lb_if": 0.1932925,
37380
  "lb_data_analysis": 0.4425866666666667,
37381
+ "arena_elo": 1423.24,
37382
+ "arena_rank": 52,
37383
+ "arena_votes": 12088
37384
  },
37385
  {
37386
  "name": "minimax-m2",
 
37392
  "lb_language": 0.47647666666666666,
37393
  "lb_if": 0.810165,
37394
  "lb_data_analysis": 0.6755800000000001,
37395
+ "arena_elo": 1347.22,
37396
+ "arena_rank": 141,
37397
+ "arena_votes": 6950
37398
  },
37399
  {
37400
  "name": "kimi-k2",
 
37516
  "lb_language": 0.7432699999999999,
37517
  "lb_if": 0.28204,
37518
  "lb_data_analysis": 0.52238,
37519
+ "arena_elo": 1431.4,
37520
+ "arena_rank": 43,
37521
+ "arena_votes": 37473
37522
  },
37523
  {
37524
  "name": "claude-opus-4-5-20251101",
 
37530
  "lb_language": 0.7709166666666668,
37531
  "lb_if": 0.26591750000000003,
37532
  "lb_data_analysis": 0.4561233333333334,
37533
+ "arena_elo": 1469.2,
37534
+ "arena_rank": 12,
37535
+ "arena_votes": 41976
37536
  },
37537
  {
37538
  "name": "deepseek-v3.2",
 
37544
  "lb_language": 0.6423933333333333,
37545
  "lb_if": 0.230625,
37546
  "lb_data_analysis": 0.45034,
37547
+ "arena_elo": 1424.52,
37548
+ "arena_rank": 49,
37549
+ "arena_votes": 36511
37550
  },
37551
  {
37552
  "name": "deepseek-v3.2-speciale",
 
37602
  "lb_language": 0.49737666666666663,
37603
  "lb_if": 0.1706225,
37604
  "lb_data_analysis": 0.46410666666666667,
37605
+ "arena_elo": 1378,
37606
+ "arena_rank": 111,
37607
+ "arena_votes": 2836
37608
  },
37609
  {
37610
  "name": "gpt-5.1-2025-11-13-low",
 
37715
  "lb_language": 0.6522633333333333,
37716
  "lb_if": 0.3565825,
37717
  "lb_data_analysis": 0.5517133333333334,
37718
+ "arena_elo": 1442.63,
37719
+ "arena_rank": 34,
37720
+ "arena_votes": 12242
37721
  },
37722
  {
37723
  "name": "arcee-trinity-large-preview",
 
37740
  "lb_language": 0.8326966666666666,
37741
  "lb_if": 0.633125,
37742
  "lb_data_analysis": 0.6989299999999999,
37743
+ "arena_elo": 1500.87,
37744
+ "arena_rank": 2,
37745
+ "arena_votes": 12546
37746
  },
37747
  {
37748
  "name": "claude-sonnet-4-6",
 
37754
  "lb_language": 0.7769333333333334,
37755
  "lb_if": 0.639165,
37756
  "lb_data_analysis": 0.7605666666666667,
37757
+ "arena_elo": 1464.73,
37758
+ "arena_rank": 13,
37759
+ "arena_votes": 9843
37760
  },
37761
  {
37762
  "name": "gemini-3.1-pro-preview-high",
 
37790
  "lb_language": 0.7752800000000001,
37791
  "lb_if": 0.5532900000000001,
37792
  "lb_data_analysis": 0.67896,
37793
+ "arena_elo": 1455.3,
37794
+ "arena_rank": 21,
37795
+ "arena_votes": 11093
37796
  },
37797
  {
37798
  "name": "gpt-5.2-codex",
 
37848
  "lb_language": 0.8300899999999999,
37849
  "lb_if": 0.6495425,
37850
  "lb_data_analysis": 0.7704833333333333,
37851
+ "arena_elo": 1485.21,
37852
  "arena_rank": 6,
37853
+ "arena_votes": 4965
37854
  },
37855
  {
37856
  "name": "gpt-5.4-xhigh",
 
37863
  "lb_if": 0.7021674999999999,
37864
  "lb_data_analysis": 0.7931333333333334
37865
  },
37866
+ {
37867
+ "name": "gpt-5.4-mini",
37868
+ "lb_name": "gpt-5.4-mini",
37869
+ "lb_global": 0.3387682608695652,
37870
+ "lb_reasoning": 0.21894249999999998,
37871
+ "lb_coding": 0.40090999999999993,
37872
+ "lb_math": 0.3704475,
37873
+ "lb_language": 0.41778999999999994,
37874
+ "lb_if": 0.18875499999999998,
37875
+ "lb_data_analysis": 0.47372333333333333
37876
+ },
37877
+ {
37878
+ "name": "gpt-5.4-mini-high",
37879
+ "lb_name": "gpt-5.4-mini-high",
37880
+ "lb_global": 0.636528260869565,
37881
+ "lb_reasoning": 0.6966975,
37882
+ "lb_coding": 0.517444,
37883
+ "lb_math": 0.740985,
37884
+ "lb_language": 0.6575866666666667,
37885
+ "lb_if": 0.5628575,
37886
+ "lb_data_analysis": 0.69267
37887
+ },
37888
+ {
37889
+ "name": "gpt-5.4-mini-low",
37890
+ "lb_name": "gpt-5.4-mini-low",
37891
+ "lb_global": 0.4818378260869565,
37892
+ "lb_reasoning": 0.40343,
37893
+ "lb_coding": 0.433202,
37894
+ "lb_math": 0.640895,
37895
+ "lb_language": 0.5759366666666667,
37896
+ "lb_if": 0.36368749999999994,
37897
+ "lb_data_analysis": 0.5188
37898
+ },
37899
+ {
37900
+ "name": "gpt-5.4-mini-medium",
37901
+ "lb_name": "gpt-5.4-mini-medium",
37902
+ "lb_global": 0.5811995652173914,
37903
+ "lb_reasoning": 0.6204500000000001,
37904
+ "lb_coding": 0.44791800000000004,
37905
+ "lb_math": 0.704025,
37906
+ "lb_language": 0.6237033333333333,
37907
+ "lb_if": 0.5075500000000001,
37908
+ "lb_data_analysis": 0.64293
37909
+ },
37910
+ {
37911
+ "name": "gpt-5.4-mini-xhigh",
37912
+ "lb_name": "gpt-5.4-mini-xhigh",
37913
+ "lb_global": 0.6774378260869566,
37914
+ "lb_reasoning": 0.7249675,
37915
+ "lb_coding": 0.571232,
37916
+ "lb_math": 0.7855549999999999,
37917
+ "lb_language": 0.71462,
37918
+ "lb_if": 0.6026525,
37919
+ "lb_data_analysis": 0.70945
37920
+ },
37921
+ {
37922
+ "name": "gpt-5.4-nano",
37923
+ "lb_name": "gpt-5.4-nano",
37924
+ "lb_global": 0.2992160869565218,
37925
+ "lb_reasoning": 0.1741025,
37926
+ "lb_coding": 0.41015199999999996,
37927
+ "lb_math": 0.36008249999999997,
37928
+ "lb_language": 0.28682,
37929
+ "lb_if": 0.164875,
37930
+ "lb_data_analysis": 0.3915033333333333
37931
+ },
37932
+ {
37933
+ "name": "gpt-5.4-nano-high",
37934
+ "lb_name": "gpt-5.4-nano-high",
37935
+ "lb_global": 0.6363969565217392,
37936
+ "lb_reasoning": 0.7200325,
37937
+ "lb_coding": 0.5682400000000001,
37938
+ "lb_math": 0.8859350000000001,
37939
+ "lb_language": 0.5475066666666667,
37940
+ "lb_if": 0.5374475000000001,
37941
+ "lb_data_analysis": 0.5265833333333334
37942
+ },
37943
+ {
37944
+ "name": "gpt-5.4-nano-low",
37945
+ "lb_name": "gpt-5.4-nano-low",
37946
+ "lb_global": 0.4769839130434783,
37947
+ "lb_reasoning": 0.4212825,
37948
+ "lb_coding": 0.50129,
37949
+ "lb_math": 0.65156,
37950
+ "lb_language": 0.45558666666666664,
37951
+ "lb_if": 0.3717525,
37952
+ "lb_data_analysis": 0.43968000000000007
37953
+ },
37954
+ {
37955
+ "name": "gpt-5.4-nano-medium",
37956
+ "lb_name": "gpt-5.4-nano-medium",
37957
+ "lb_global": 0.5895660869565217,
37958
+ "lb_reasoning": 0.6449025,
37959
+ "lb_coding": 0.525236,
37960
+ "lb_math": 0.8309575,
37961
+ "lb_language": 0.5103733333333333,
37962
+ "lb_if": 0.5094500000000001,
37963
+ "lb_data_analysis": 0.48716
37964
+ },
37965
+ {
37966
+ "name": "gpt-5.4-nano-xhigh",
37967
+ "lb_name": "gpt-5.4-nano-xhigh",
37968
+ "lb_global": 0.7130778260869566,
37969
+ "lb_reasoning": 0.8105125000000001,
37970
+ "lb_coding": 0.583284,
37971
+ "lb_math": 0.9127025,
37972
+ "lb_language": 0.62468,
37973
+ "lb_if": 0.6720475,
37974
+ "lb_data_analysis": 0.6764266666666666
37975
+ },
37976
  {
37977
  "name": "grok-4.20-beta-0309",
37978
  "lb_name": "grok-4.20-beta-0309-non-reasoning",
 
37993
  "lb_math": 0.8705550000000001,
37994
  "lb_language": 0.7771733333333333,
37995
  "lb_if": 0.6338775,
37996
+ "lb_data_analysis": 0.62857,
37997
+ "arena_elo": 1481.01,
37998
+ "arena_rank": 8,
37999
+ "arena_votes": 4504
38000
  },
38001
  {
38002
  "name": "kimi-k2.5",
 
38008
  "lb_language": 0.77666,
38009
  "lb_if": 0.574125,
38010
  "lb_data_analysis": 0.6135766666666667,
38011
+ "arena_elo": 1452.68,
38012
+ "arena_rank": 22,
38013
+ "arena_votes": 16262
38014
  },
38015
  {
38016
  "name": "minimax-m2.5",
 
38022
  "lb_language": 0.5510100000000001,
38023
  "lb_if": 0.5723325,
38024
  "lb_data_analysis": 0.49605000000000005,
38025
+ "arena_elo": 1405.31,
38026
+ "arena_rank": 78,
38027
+ "arena_votes": 11909
38028
  },
38029
  {
38030
  "name": "claude-opus-4-6-thinking",
38031
  "arena_name": "claude-opus-4-6-thinking",
38032
  "arena_org": "Anthropic",
38033
+ "arena_elo": 1502.13,
38034
+ "arena_rank": 1,
38035
+ "arena_votes": 11801
 
 
 
 
 
 
 
 
38036
  },
38037
  {
38038
  "name": "gemini-3.1-pro-preview",
38039
  "arena_name": "gemini-3.1-pro-preview",
38040
  "arena_org": "Google",
38041
+ "arena_elo": 1492.91,
38042
+ "arena_rank": 3,
38043
+ "arena_votes": 14677
38044
+ },
38045
+ {
38046
+ "name": "grok-4.20-beta1",
38047
+ "arena_name": "grok-4.20-beta1",
38048
+ "arena_org": "xAI",
38049
+ "arena_elo": 1491.51,
38050
  "arena_rank": 4,
38051
+ "arena_votes": 7396
38052
  },
38053
  {
38054
  "name": "gemini-3-pro",
38055
  "arena_name": "gemini-3-pro",
38056
  "arena_org": "Google",
38057
+ "arena_elo": 1486.49,
38058
  "arena_rank": 5,
38059
+ "arena_votes": 41762
38060
  },
38061
  {
38062
  "name": "gpt-5.2-chat-latest-20260210",
38063
  "arena_name": "gpt-5.2-chat-latest-20260210",
38064
  "arena_org": "OpenAI",
38065
+ "arena_elo": 1481.77,
38066
  "arena_rank": 7,
38067
+ "arena_votes": 10140
38068
  },
38069
  {
38070
  "name": "gemini-3-flash",
38071
  "arena_name": "gemini-3-flash",
38072
  "arena_org": "Google",
38073
+ "arena_elo": 1474.57,
 
 
 
 
 
 
 
 
38074
  "arena_rank": 9,
38075
+ "arena_votes": 31060
38076
  },
38077
  {
38078
  "name": "claude-opus-4-5-20251101-thinking-32k",
38079
  "arena_name": "claude-opus-4-5-20251101-thinking-32k",
38080
  "arena_org": "Anthropic",
38081
+ "arena_elo": 1473.72,
38082
  "arena_rank": 10,
38083
+ "arena_votes": 37036
38084
  },
38085
  {
38086
+ "name": "grok-4.1-thinking",
38087
+ "arena_name": "grok-4.1-thinking",
38088
+ "arena_org": "xAI",
38089
+ "arena_elo": 1471.72,
38090
+ "arena_rank": 11,
38091
+ "arena_votes": 43930
38092
+ },
38093
+ {
38094
+ "name": "qwen3.5-max-preview",
38095
+ "arena_name": "qwen3.5-max-preview",
38096
+ "arena_org": "Alibaba",
38097
+ "arena_elo": 1463.69,
38098
+ "arena_rank": 14,
38099
+ "arena_votes": 4252
38100
+ },
38101
+ {
38102
+ "name": "gpt-5.3-chat-latest",
38103
+ "arena_name": "gpt-5.3-chat-latest",
38104
+ "arena_org": "OpenAI",
38105
+ "arena_elo": 1463.53,
38106
+ "arena_rank": 15,
38107
+ "arena_votes": 8942
38108
  },
38109
  {
38110
  "name": "gemini-3-flash (thinking-minimal)",
38111
  "arena_name": "gemini-3-flash (thinking-minimal)",
38112
  "arena_org": "Google",
38113
+ "arena_elo": 1462.93,
38114
+ "arena_rank": 16,
38115
+ "arena_votes": 27448
38116
  },
38117
  {
38118
  "name": "gpt-5.4",
38119
  "arena_name": "gpt-5.4",
38120
  "arena_org": "OpenAI",
38121
+ "arena_elo": 1462.52,
38122
+ "arena_rank": 17,
38123
+ "arena_votes": 4972
38124
+ },
38125
+ {
38126
+ "name": "dola-seed-2.0-preview",
38127
+ "arena_name": "dola-seed-2.0-preview",
38128
+ "arena_org": "Bytedance",
38129
+ "arena_elo": 1461.51,
38130
+ "arena_rank": 18,
38131
+ "arena_votes": 10651
38132
  },
38133
  {
38134
  "name": "grok-4.1",
38135
  "arena_name": "grok-4.1",
38136
  "arena_org": "xAI",
38137
+ "arena_elo": 1460.7,
38138
+ "arena_rank": 19,
38139
+ "arena_votes": 47757
38140
  },
38141
  {
38142
  "name": "gpt-5.1-high",
38143
  "arena_name": "gpt-5.1-high",
38144
  "arena_org": "OpenAI",
38145
+ "arena_elo": 1455.38,
 
 
 
 
 
 
 
 
38146
  "arena_rank": 20,
38147
+ "arena_votes": 40759
38148
  },
38149
  {
38150
  "name": "claude-sonnet-4-5-20250929-thinking-32k",
38151
  "arena_name": "claude-sonnet-4-5-20250929-thinking-32k",
38152
  "arena_org": "Anthropic",
38153
+ "arena_elo": 1452.6,
38154
+ "arena_rank": 24,
38155
+ "arena_votes": 55811
38156
+ },
38157
+ {
38158
+ "name": "ernie-5.0-0110",
38159
+ "arena_name": "ernie-5.0-0110",
38160
+ "arena_org": "Baidu",
38161
+ "arena_elo": 1451.68,
38162
+ "arena_rank": 25,
38163
+ "arena_votes": 18715
38164
  },
38165
  {
38166
  "name": "qwen3.5-397b-a17b",
38167
  "arena_name": "qwen3.5-397b-a17b",
38168
  "arena_org": "Alibaba",
38169
+ "arena_elo": 1451.63,
38170
+ "arena_rank": 26,
38171
+ "arena_votes": 10431
38172
  },
38173
  {
38174
  "name": "ernie-5.0-preview-1203",
38175
  "arena_name": "ernie-5.0-preview-1203",
38176
  "arena_org": "Baidu",
38177
+ "arena_elo": 1449.6,
38178
+ "arena_rank": 27,
38179
+ "arena_votes": 9857
 
 
 
 
 
 
 
 
38180
  },
38181
  {
38182
  "name": "claude-opus-4-1-20250805-thinking-16k",
38183
  "arena_name": "claude-opus-4-1-20250805-thinking-16k",
38184
  "arena_org": "Anthropic",
38185
+ "arena_elo": 1448.51,
38186
+ "arena_rank": 28,
38187
+ "arena_votes": 50375
38188
+ },
38189
+ {
38190
+ "name": "gemini-2.5-pro",
38191
+ "arena_name": "gemini-2.5-pro",
38192
+ "arena_org": "Google",
38193
+ "arena_elo": 1448.18,
38194
+ "arena_rank": 29,
38195
+ "arena_votes": 103317
38196
  },
38197
  {
38198
  "name": "claude-opus-4-1-20250805",
38199
  "arena_name": "claude-opus-4-1-20250805",
38200
  "arena_org": "Anthropic",
38201
+ "arena_elo": 1446.88,
38202
+ "arena_rank": 30,
38203
+ "arena_votes": 78224
38204
  },
38205
  {
38206
+ "name": "mimo-v2-pro",
38207
+ "arena_name": "mimo-v2-pro",
38208
+ "arena_org": "Xiaomi",
38209
+ "arena_elo": 1444.57,
38210
+ "arena_rank": 31,
38211
+ "arena_votes": 3531
38212
  },
38213
  {
38214
  "name": "chatgpt-4o-latest-20250326",
38215
  "arena_name": "chatgpt-4o-latest-20250326",
38216
  "arena_org": "OpenAI",
38217
+ "arena_elo": 1442.8,
38218
+ "arena_rank": 33,
38219
+ "arena_votes": 83559
38220
+ },
38221
+ {
38222
+ "name": "gpt-5.2-high",
38223
+ "arena_name": "gpt-5.2-high",
38224
+ "arena_org": "OpenAI",
38225
+ "arena_elo": 1441.69,
38226
+ "arena_rank": 35,
38227
+ "arena_votes": 25328
38228
  },
38229
  {
38230
  "name": "gpt-5.2",
38231
  "arena_name": "gpt-5.2",
38232
  "arena_org": "OpenAI",
38233
+ "arena_elo": 1440.17,
38234
+ "arena_rank": 36,
38235
+ "arena_votes": 22231
38236
  },
38237
  {
38238
  "name": "gpt-5.1",
38239
  "arena_name": "gpt-5.1",
38240
  "arena_org": "OpenAI",
38241
+ "arena_elo": 1438.55,
38242
+ "arena_rank": 37,
38243
+ "arena_votes": 43475
 
 
 
 
 
 
 
 
38244
  },
38245
  {
38246
  "name": "gemini-3.1-flash-lite-preview",
38247
  "arena_name": "gemini-3.1-flash-lite-preview",
38248
  "arena_org": "Google",
38249
+ "arena_elo": 1437.61,
38250
+ "arena_rank": 38,
38251
+ "arena_votes": 3881
38252
  },
38253
  {
38254
  "name": "qwen3-max-preview",
38255
  "arena_name": "qwen3-max-preview",
38256
  "arena_org": "Alibaba",
38257
+ "arena_elo": 1434.74,
38258
+ "arena_rank": 39,
38259
+ "arena_votes": 28066
38260
+ },
38261
+ {
38262
+ "name": "kimi-k2.5-instant",
38263
+ "arena_name": "kimi-k2.5-instant",
38264
+ "arena_org": "Moonshot",
38265
+ "arena_elo": 1433.19,
38266
+ "arena_rank": 41,
38267
+ "arena_votes": 8257
38268
  },
38269
  {
38270
  "name": "o3-2025-04-16",
38271
  "arena_name": "o3-2025-04-16",
38272
  "arena_org": "OpenAI",
38273
+ "arena_elo": 1431.57,
38274
+ "arena_rank": 42,
38275
+ "arena_votes": 60698
38276
  },
38277
  {
38278
  "name": "kimi-k2-thinking-turbo",
38279
  "arena_name": "kimi-k2-thinking-turbo",
38280
  "arena_org": "Moonshot",
38281
+ "arena_elo": 1429.69,
38282
+ "arena_rank": 44,
38283
+ "arena_votes": 41738
38284
  },
38285
  {
38286
+ "name": "amazon-nova-experimental-chat-26-02-10",
38287
+ "arena_name": "amazon-nova-experimental-chat-26-02-10",
38288
+ "arena_org": "Amazon",
38289
+ "arena_elo": 1428.78,
38290
+ "arena_rank": 45,
38291
+ "arena_votes": 3467
38292
  },
38293
  {
38294
  "name": "deepseek-v3.2-exp-thinking",
38295
  "arena_name": "deepseek-v3.2-exp-thinking",
38296
  "arena_org": "DeepSeek",
38297
+ "arena_elo": 1424.73,
38298
+ "arena_rank": 48,
38299
+ "arena_votes": 9188
38300
  },
38301
  {
38302
+ "name": "claude-opus-4-20250514-thinking-16k",
38303
+ "arena_name": "claude-opus-4-20250514-thinking-16k",
38304
+ "arena_org": "Anthropic",
38305
+ "arena_elo": 1423.97,
38306
+ "arena_rank": 51,
38307
+ "arena_votes": 37503
38308
  },
38309
  {
38310
  "name": "deepseek-v3.2-thinking",
38311
  "arena_name": "deepseek-v3.2-thinking",
38312
  "arena_org": "DeepSeek",
38313
+ "arena_elo": 1421.6,
38314
+ "arena_rank": 54,
38315
+ "arena_votes": 31048
38316
+ },
38317
+ {
38318
+ "name": "grok-4-fast-chat",
38319
+ "arena_name": "grok-4-fast-chat",
38320
+ "arena_org": "xAI",
38321
+ "arena_elo": 1421.01,
38322
+ "arena_rank": 56,
38323
+ "arena_votes": 6901
38324
  },
38325
  {
38326
  "name": "ernie-5.0-preview-1022",
38327
  "arena_name": "ernie-5.0-preview-1022",
38328
  "arena_org": "Baidu",
38329
+ "arena_elo": 1418.91,
38330
+ "arena_rank": 57,
38331
+ "arena_votes": 4782
 
 
 
 
 
 
 
 
38332
  },
38333
  {
38334
  "name": "deepseek-v3.1",
38335
  "arena_name": "deepseek-v3.1",
38336
  "arena_org": "DeepSeek",
38337
+ "arena_elo": 1418.02,
38338
+ "arena_rank": 58,
38339
+ "arena_votes": 15150
38340
  },
38341
  {
38342
  "name": "kimi-k2-0905-preview",
38343
  "arena_name": "kimi-k2-0905-preview",
38344
  "arena_org": "Moonshot",
38345
+ "arena_elo": 1417.75,
38346
+ "arena_rank": 59,
38347
+ "arena_votes": 11924
38348
  },
38349
  {
38350
+ "name": "qwen3.5-122b-a10b",
38351
+ "arena_name": "qwen3.5-122b-a10b",
38352
+ "arena_org": "Alibaba",
38353
+ "arena_elo": 1417.32,
38354
+ "arena_rank": 60,
38355
+ "arena_votes": 6946
38356
  },
38357
  {
38358
  "name": "kimi-k2-0711-preview",
38359
  "arena_name": "kimi-k2-0711-preview",
38360
  "arena_org": "Moonshot",
38361
+ "arena_elo": 1417.05,
38362
+ "arena_rank": 61,
38363
+ "arena_votes": 28082
38364
+ },
38365
+ {
38366
+ "name": "deepseek-v3.1-thinking",
38367
+ "arena_name": "deepseek-v3.1-thinking",
38368
+ "arena_org": "DeepSeek",
38369
+ "arena_elo": 1416.93,
38370
+ "arena_rank": 62,
38371
+ "arena_votes": 11885
38372
+ },
38373
+ {
38374
+ "name": "deepseek-v3.1-terminus-thinking",
38375
+ "arena_name": "deepseek-v3.1-terminus-thinking",
38376
+ "arena_org": "DeepSeek",
38377
+ "arena_elo": 1416.41,
38378
+ "arena_rank": 63,
38379
+ "arena_votes": 3497
38380
  },
38381
  {
38382
  "name": "mistral-large-3",
38383
  "arena_name": "mistral-large-3",
38384
  "arena_org": "Mistral",
38385
+ "arena_elo": 1416.39,
38386
+ "arena_rank": 64,
38387
+ "arena_votes": 33200
38388
  },
38389
  {
38390
  "name": "qwen3-vl-235b-a22b-instruct",
38391
  "arena_name": "qwen3-vl-235b-a22b-instruct",
38392
  "arena_org": "Alibaba",
38393
+ "arena_elo": 1415.46,
38394
+ "arena_rank": 66,
38395
+ "arena_votes": 11645
 
 
 
 
 
 
 
 
38396
  },
38397
  {
38398
  "name": "amazon-nova-experimental-chat-26-01-10",
38399
  "arena_name": "amazon-nova-experimental-chat-26-01-10",
38400
  "arena_org": "Amazon",
38401
+ "arena_elo": 1414.43,
38402
+ "arena_rank": 67,
38403
+ "arena_votes": 3439
38404
  },
38405
  {
38406
  "name": "claude-opus-4-20250514",
38407
  "arena_name": "claude-opus-4-20250514",
38408
  "arena_org": "Anthropic",
38409
+ "arena_elo": 1412.58,
38410
+ "arena_rank": 69,
38411
+ "arena_votes": 44988
38412
  },
38413
  {
38414
  "name": "grok-3-preview-02-24",
38415
  "arena_name": "grok-3-preview-02-24",
38416
  "arena_org": "xAI",
38417
+ "arena_elo": 1411.76,
38418
+ "arena_rank": 70,
38419
+ "arena_votes": 33374
38420
  },
38421
  {
38422
  "name": "gemini-2.5-flash",
38423
  "arena_name": "gemini-2.5-flash",
38424
  "arena_org": "Google",
38425
+ "arena_elo": 1410.82,
38426
+ "arena_rank": 71,
38427
+ "arena_votes": 102736
38428
  },
38429
  {
38430
  "name": "mistral-medium-2508",
38431
  "arena_name": "mistral-medium-2508",
38432
  "arena_org": "Mistral",
38433
+ "arena_elo": 1409.9,
38434
+ "arena_rank": 74,
38435
+ "arena_votes": 72410
38436
+ },
38437
+ {
38438
+ "name": "minimax-m2.7",
38439
+ "arena_name": "minimax-m2.7",
38440
+ "arena_org": "MiniMax",
38441
+ "arena_elo": 1407.31,
38442
+ "arena_rank": 75,
38443
+ "arena_votes": 2981
38444
  },
38445
  {
38446
  "name": "qwen3.5-27b",
38447
  "arena_name": "qwen3.5-27b",
38448
  "arena_org": "Alibaba",
38449
+ "arena_elo": 1406.31,
38450
+ "arena_rank": 77,
38451
+ "arena_votes": 6957
38452
  },
38453
  {
38454
  "name": "grok-4-fast-reasoning",
38455
  "arena_name": "grok-4-fast-reasoning",
38456
  "arena_org": "xAI",
38457
+ "arena_elo": 1404.78,
38458
+ "arena_rank": 80,
38459
+ "arena_votes": 18993
38460
  },
38461
  {
38462
  "name": "qwen3-235b-a22b-no-thinking",
38463
  "arena_name": "qwen3-235b-a22b-no-thinking",
38464
  "arena_org": "Alibaba",
38465
+ "arena_elo": 1402.71,
38466
+ "arena_rank": 81,
38467
+ "arena_votes": 38797
38468
+ },
38469
+ {
38470
+ "name": "qwen3.5-flash",
38471
+ "arena_name": "qwen3.5-flash",
38472
+ "arena_org": "Alibaba",
38473
+ "arena_elo": 1401.49,
38474
+ "arena_rank": 84,
38475
+ "arena_votes": 7853
38476
+ },
38477
+ {
38478
+ "name": "qwen3.5-35b-a3b",
38479
+ "arena_name": "qwen3.5-35b-a3b",
38480
+ "arena_org": "Alibaba",
38481
+ "arena_elo": 1401,
38482
+ "arena_rank": 85,
38483
+ "arena_votes": 7278
38484
  },
38485
  {
38486
  "name": "longcat-flash-chat",
38487
  "arena_name": "longcat-flash-chat",
38488
  "arena_org": "Meituan",
38489
+ "arena_elo": 1400.43,
38490
+ "arena_rank": 86,
38491
+ "arena_votes": 11517
38492
  },
38493
  {
38494
  "name": "claude-sonnet-4-20250514-thinking-32k",
38495
  "arena_name": "claude-sonnet-4-20250514-thinking-32k",
38496
  "arena_org": "Anthropic",
38497
+ "arena_elo": 1399.02,
38498
+ "arena_rank": 88,
38499
+ "arena_votes": 35733
 
 
 
 
 
 
 
 
38500
  },
38501
  {
38502
+ "name": "hunyuan-vision-1.5-thinking",
38503
+ "arena_name": "hunyuan-vision-1.5-thinking",
38504
+ "arena_org": "Tencent",
38505
+ "arena_elo": 1396.03,
38506
+ "arena_rank": 90,
38507
+ "arena_votes": 2235
38508
  },
38509
  {
38510
  "name": "qwen3-vl-235b-a22b-thinking",
38511
  "arena_name": "qwen3-vl-235b-a22b-thinking",
38512
  "arena_org": "Alibaba",
38513
+ "arena_elo": 1395.82,
38514
+ "arena_rank": 91,
38515
+ "arena_votes": 8052
38516
  },
38517
  {
38518
  "name": "amazon-nova-experimental-chat-12-10",
38519
  "arena_name": "amazon-nova-experimental-chat-12-10",
38520
  "arena_org": "Amazon",
38521
+ "arena_elo": 1395.68,
38522
+ "arena_rank": 92,
38523
+ "arena_votes": 3720
38524
  },
38525
  {
38526
+ "name": "mai-1-preview",
38527
+ "arena_name": "mai-1-preview",
38528
+ "arena_org": "Microsoft AI",
38529
+ "arena_elo": 1392.99,
38530
+ "arena_rank": 94,
38531
+ "arena_votes": 18095
38532
  },
38533
  {
38534
  "name": "mimo-v2-flash (non-thinking)",
38535
  "arena_name": "mimo-v2-flash (non-thinking)",
38536
  "arena_org": "Xiaomi",
38537
+ "arena_elo": 1391.89,
38538
+ "arena_rank": 95,
38539
+ "arena_votes": 25427
 
 
 
 
 
 
 
 
38540
  },
38541
  {
38542
  "name": "o4-mini-2025-04-16",
38543
  "arena_name": "o4-mini-2025-04-16",
38544
  "arena_org": "OpenAI",
38545
+ "arena_elo": 1390,
38546
+ "arena_rank": 96,
38547
+ "arena_votes": 46166
38548
  },
38549
  {
38550
  "name": "claude-sonnet-4-20250514",
38551
  "arena_name": "claude-sonnet-4-20250514",
38552
  "arena_org": "Anthropic",
38553
+ "arena_elo": 1389.16,
38554
+ "arena_rank": 98,
38555
+ "arena_votes": 41021
38556
  },
38557
  {
38558
  "name": "step-3.5-flash",
38559
  "arena_name": "step-3.5-flash",
38560
  "arena_org": "StepFun",
38561
+ "arena_elo": 1388.71,
38562
+ "arena_rank": 99,
38563
+ "arena_votes": 13885
 
 
 
 
 
 
 
 
38564
  },
38565
  {
38566
  "name": "mimo-v2-flash (thinking)",
38567
  "arena_name": "mimo-v2-flash (thinking)",
38568
  "arena_org": "Xiaomi",
38569
+ "arena_elo": 1387.3,
38570
+ "arena_rank": 101,
38571
+ "arena_votes": 11053
38572
  },
38573
  {
38574
  "name": "hunyuan-t1-20250711",
38575
  "arena_name": "hunyuan-t1-20250711",
38576
  "arena_org": "Tencent",
38577
+ "arena_elo": 1387.06,
38578
+ "arena_rank": 103,
38579
+ "arena_votes": 4742
38580
+ },
38581
+ {
38582
+ "name": "claude-3-7-sonnet-20250219-thinking-32k",
38583
+ "arena_name": "claude-3-7-sonnet-20250219-thinking-32k",
38584
+ "arena_org": "Anthropic",
38585
+ "arena_elo": 1386.88,
38586
+ "arena_rank": 104,
38587
+ "arena_votes": 39307
38588
  },
38589
  {
38590
  "name": "minimax-m2.1-preview",
38591
  "arena_name": "minimax-m2.1-preview",
38592
  "arena_org": "MiniMax",
38593
+ "arena_elo": 1385.97,
38594
+ "arena_rank": 106,
38595
+ "arena_votes": 17271
 
 
 
 
 
 
 
 
38596
  },
38597
  {
38598
  "name": "hunyuan-turbos-20250416",
38599
  "arena_name": "hunyuan-turbos-20250416",
38600
  "arena_org": "Tencent",
38601
+ "arena_elo": 1383.18,
38602
+ "arena_rank": 107,
38603
+ "arena_votes": 10871
38604
  },
38605
  {
38606
+ "name": "qwen3-30b-a3b-instruct-2507",
38607
+ "arena_name": "qwen3-30b-a3b-instruct-2507",
38608
+ "arena_org": "Alibaba",
38609
+ "arena_elo": 1382.94,
38610
+ "arena_rank": 108,
38611
+ "arena_votes": 24086
38612
  },
38613
  {
38614
+ "name": "gemini-2.5-flash-lite-preview-09-2025-no-thinking",
38615
+ "arena_name": "gemini-2.5-flash-lite-preview-09-2025-no-thinking",
38616
  "arena_org": "Google",
38617
+ "arena_elo": 1379.96,
38618
+ "arena_rank": 110,
38619
+ "arena_votes": 47802
38620
  },
38621
  {
38622
  "name": "trinity-large",
38623
  "arena_name": "trinity-large",
38624
  "arena_org": "Arcee AI",
38625
+ "arena_elo": 1375.54,
38626
+ "arena_rank": 112,
38627
+ "arena_votes": 8033
38628
+ },
38629
+ {
38630
+ "name": "gemini-2.5-flash-lite-preview-06-17-thinking",
38631
+ "arena_name": "gemini-2.5-flash-lite-preview-06-17-thinking",
38632
+ "arena_org": "Google",
38633
+ "arena_elo": 1374.39,
38634
+ "arena_rank": 115,
38635
+ "arena_votes": 33445
38636
  },
38637
  {
38638
  "name": "glm-4.7-flash",
38639
  "arena_name": "glm-4.7-flash",
38640
  "arena_org": "Z.ai",
38641
+ "arena_elo": 1368.47,
38642
+ "arena_rank": 120,
38643
+ "arena_votes": 11857
38644
  },
38645
  {
38646
  "name": "amazon-nova-experimental-chat-11-10",
38647
  "arena_name": "amazon-nova-experimental-chat-11-10",
38648
  "arena_org": "Amazon",
38649
+ "arena_elo": 1367.75,
38650
+ "arena_rank": 121,
38651
+ "arena_votes": 24655
 
 
 
 
 
 
 
 
38652
  },
38653
  {
38654
  "name": "nvidia-nemotron-3-super-120b-a12b",
38655
  "arena_name": "nvidia-nemotron-3-super-120b-a12b",
38656
  "arena_org": "Nvidia",
38657
+ "arena_elo": 1364.56,
38658
+ "arena_rank": 123,
38659
+ "arena_votes": 3641
38660
+ },
38661
+ {
38662
+ "name": "minimax-m1",
38663
+ "arena_name": "minimax-m1",
38664
+ "arena_org": "MiniMax",
38665
+ "arena_elo": 1364.38,
38666
+ "arena_rank": 124,
38667
+ "arena_votes": 35951
38668
  },
38669
  {
38670
  "name": "o3-mini-high",
38671
  "arena_name": "o3-mini-high",
38672
  "arena_org": "OpenAI",
38673
+ "arena_elo": 1363.37,
38674
+ "arena_rank": 125,
38675
  "arena_votes": 18589
38676
  },
38677
  {
38678
  "name": "grok-3-mini-high",
38679
  "arena_name": "grok-3-mini-high",
38680
  "arena_org": "xAI",
38681
+ "arena_elo": 1362.93,
38682
+ "arena_rank": 126,
38683
+ "arena_votes": 17210
38684
  },
38685
  {
38686
  "name": "grok-3-mini-beta",
38687
  "arena_name": "grok-3-mini-beta",
38688
  "arena_org": "xAI",
38689
+ "arena_elo": 1357.6,
38690
+ "arena_rank": 129,
38691
+ "arena_votes": 23162
38692
  },
38693
  {
38694
  "name": "mistral-small-2506",
38695
  "arena_name": "mistral-small-2506",
38696
  "arena_org": "Mistral",
38697
+ "arena_elo": 1357.11,
38698
+ "arena_rank": 130,
38699
+ "arena_votes": 18015
38700
  },
38701
  {
38702
  "name": "intellect-3",
38703
  "arena_name": "intellect-3",
38704
  "arena_org": "Prime Intellect",
38705
+ "arena_elo": 1356.52,
38706
+ "arena_rank": 131,
38707
+ "arena_votes": 5387
38708
  },
38709
  {
38710
  "name": "glm-4.5v",
38711
  "arena_name": "glm-4.5v",
38712
  "arena_org": "Z.ai",
38713
+ "arena_elo": 1352.97,
38714
+ "arena_rank": 134,
38715
+ "arena_votes": 4989
38716
  },
38717
  {
38718
  "name": "amazon-nova-experimental-chat-10-20",
38719
  "arena_name": "amazon-nova-experimental-chat-10-20",
38720
  "arena_org": "Amazon",
38721
+ "arena_elo": 1350.6,
38722
+ "arena_rank": 137,
38723
+ "arena_votes": 11580
38724
  },
38725
  {
38726
  "name": "hunyuan-turbos-20250226",
38727
  "arena_name": "hunyuan-turbos-20250226",
38728
  "arena_org": "Tencent",
38729
+ "arena_elo": 1348.57,
38730
+ "arena_rank": 138,
38731
  "arena_votes": 2220
38732
  },
38733
  {
38734
  "name": "step-3",
38735
  "arena_name": "step-3",
38736
  "arena_org": "StepFun",
38737
+ "arena_elo": 1347.78,
38738
+ "arena_rank": 139,
38739
+ "arena_votes": 6600
38740
  },
38741
  {
38742
+ "name": "llama-3.1-nemotron-ultra-253b-v1",
38743
+ "arena_name": "llama-3.1-nemotron-ultra-253b-v1",
38744
+ "arena_org": "Nvidia",
38745
+ "arena_elo": 1346.91,
38746
+ "arena_rank": 143,
38747
+ "arena_votes": 2549
38748
  },
38749
  {
38750
  "name": "amazon-nova-experimental-chat-10-09",
38751
  "arena_name": "amazon-nova-experimental-chat-10-09",
38752
  "arena_org": "Amazon",
38753
+ "arena_elo": 1346.81,
38754
+ "arena_rank": 144,
38755
+ "arena_votes": 2872
38756
  },
38757
  {
38758
+ "name": "ling-flash-2.0",
38759
+ "arena_name": "ling-flash-2.0",
38760
+ "arena_org": "Ant Group",
38761
+ "arena_elo": 1346.03,
38762
+ "arena_rank": 145,
38763
+ "arena_votes": 7125
38764
  },
38765
  {
38766
  "name": "qwen-plus-0125",
38767
  "arena_name": "qwen-plus-0125",
38768
  "arena_org": "Alibaba",
38769
+ "arena_elo": 1346.01,
38770
+ "arena_rank": 146,
38771
  "arena_votes": 5819
38772
  },
38773
+ {
38774
+ "name": "nvidia-llama-3.3-nemotron-super-49b-v1.5",
38775
+ "arena_name": "nvidia-llama-3.3-nemotron-super-49b-v1.5",
38776
+ "arena_org": "Nvidia",
38777
+ "arena_elo": 1342.72,
38778
+ "arena_rank": 148,
38779
+ "arena_votes": 3392
38780
+ },
38781
  {
38782
  "name": "glm-4-plus-0111",
38783
  "arena_name": "glm-4-plus-0111",
38784
  "arena_org": "Zhipu",
38785
+ "arena_elo": 1342.68,
38786
+ "arena_rank": 149,
38787
  "arena_votes": 5760
38788
  },
 
 
 
 
 
 
 
 
38789
  {
38790
  "name": "hunyuan-turbo-0110",
38791
  "arena_name": "hunyuan-turbo-0110",
38792
  "arena_org": "Tencent",
38793
+ "arena_elo": 1340.33,
38794
+ "arena_rank": 152,
38795
  "arena_votes": 2290
38796
  },
38797
  {
38798
  "name": "nova-2-lite",
38799
  "arena_name": "nova-2-lite",
38800
  "arena_org": "Amazon",
38801
+ "arena_elo": 1337.59,
38802
+ "arena_rank": 153,
38803
+ "arena_votes": 12343
38804
  },
38805
  {
38806
  "name": "grok-2-2024-08-13",
38807
  "arena_name": "grok-2-2024-08-13",
38808
  "arena_org": "xAI",
38809
+ "arena_elo": 1334.9,
38810
+ "arena_rank": 157,
38811
  "arena_votes": 63498
38812
  },
38813
  {
38814
  "name": "llama-3.1-405b-instruct-bf16",
38815
  "arena_name": "llama-3.1-405b-instruct-bf16",
38816
  "arena_org": "Meta",
38817
+ "arena_elo": 1334.6,
38818
+ "arena_rank": 158,
38819
  "arena_votes": 41375
38820
  },
38821
  {
38822
  "name": "gemini-advanced-0514",
38823
  "arena_name": "gemini-advanced-0514",
38824
  "arena_org": "Google",
38825
+ "arena_elo": 1334.41,
38826
+ "arena_rank": 160,
38827
  "arena_votes": 50148
38828
  },
38829
  {
38830
  "name": "step-2-16k-exp-202412",
38831
  "arena_name": "step-2-16k-exp-202412",
38832
  "arena_org": "StepFun",
38833
+ "arena_elo": 1333.91,
38834
+ "arena_rank": 161,
38835
  "arena_votes": 4833
38836
  },
38837
  {
38838
  "name": "llama-3.1-405b-instruct-fp8",
38839
  "arena_name": "llama-3.1-405b-instruct-fp8",
38840
  "arena_org": "Meta",
38841
+ "arena_elo": 1332.78,
38842
+ "arena_rank": 162,
38843
  "arena_votes": 59656
38844
  },
38845
  {
38846
  "name": "olmo-3.1-32b-instruct",
38847
  "arena_name": "olmo-3.1-32b-instruct",
38848
  "arena_org": "Ai2",
38849
+ "arena_elo": 1330.82,
38850
+ "arena_rank": 163,
38851
+ "arena_votes": 12326
38852
  },
38853
  {
38854
  "name": "yi-lightning",
38855
  "arena_name": "yi-lightning",
38856
  "arena_org": "01 AI",
38857
+ "arena_elo": 1328.25,
38858
+ "arena_rank": 164,
38859
  "arena_votes": 27332,
38860
  "aider_pass_rate": 0.496
38861
  },
 
 
 
 
 
 
 
 
38862
  {
38863
  "name": "llama-3.3-nemotron-49b-super-v1",
38864
  "arena_name": "llama-3.3-nemotron-49b-super-v1",
38865
  "arena_org": "Nvidia",
38866
+ "arena_elo": 1327.41,
38867
+ "arena_rank": 166,
38868
  "arena_votes": 2218
38869
  },
38870
+ {
38871
+ "name": "molmo-2-8b",
38872
+ "arena_name": "molmo-2-8b",
38873
+ "arena_org": "Ai2",
38874
+ "arena_elo": 1326.21,
38875
+ "arena_rank": 168,
38876
+ "arena_votes": 811
38877
+ },
38878
  {
38879
  "name": "hunyuan-large-2025-02-10",
38880
  "arena_name": "hunyuan-large-2025-02-10",
38881
  "arena_org": "Tencent",
38882
+ "arena_elo": 1325.82,
38883
+ "arena_rank": 169,
38884
  "arena_votes": 3738
38885
  },
38886
  {
38887
  "name": "deepseek-v2.5-1210",
38888
  "arena_name": "deepseek-v2.5-1210",
38889
  "arena_org": "DeepSeek",
38890
+ "arena_elo": 1323.18,
38891
+ "arena_rank": 171,
38892
  "arena_votes": 6795,
38893
  "aider_pass_rate": 0.586
38894
  },
 
38896
  "name": "gemini-1.5-pro-001",
38897
  "arena_name": "gemini-1.5-pro-001",
38898
  "arena_org": "Google",
38899
+ "arena_elo": 1322.72,
38900
+ "arena_rank": 173,
38901
  "arena_votes": 79138,
38902
  "aider_pass_rate": 0.45899999999999996
38903
  },
 
38905
  "name": "llama-4-scout-17b-16e-instruct",
38906
  "arena_name": "llama-4-scout-17b-16e-instruct",
38907
  "arena_org": "Meta",
38908
+ "arena_elo": 1322.31,
38909
+ "arena_rank": 174,
38910
+ "arena_votes": 30740
38911
  },
38912
  {
38913
  "name": "step-1o-turbo-202506",
38914
  "arena_name": "step-1o-turbo-202506",
38915
  "arena_org": "StepFun",
38916
+ "arena_elo": 1321.45,
38917
+ "arena_rank": 176,
38918
+ "arena_votes": 9310
38919
  },
38920
  {
38921
  "name": "ring-flash-2.0",
38922
  "arena_name": "ring-flash-2.0",
38923
  "arena_org": "Ant Group",
38924
+ "arena_elo": 1321,
38925
+ "arena_rank": 178,
38926
+ "arena_votes": 7252
38927
  },
38928
  {
38929
  "name": "glm-4-plus",
38930
  "arena_name": "glm-4-plus",
38931
  "arena_org": "Zhipu AI",
38932
+ "arena_elo": 1319.04,
38933
+ "arena_rank": 179,
38934
  "arena_votes": 26126
38935
  },
38936
  {
38937
  "name": "gemma-3n-e4b-it",
38938
  "arena_name": "gemma-3n-e4b-it",
38939
  "arena_org": "Google",
38940
+ "arena_elo": 1318.46,
38941
+ "arena_rank": 180,
38942
+ "arena_votes": 22915
38943
+ },
38944
+ {
38945
+ "name": "gpt-oss-20b",
38946
+ "arena_name": "gpt-oss-20b",
38947
+ "arena_org": "OpenAI",
38948
+ "arena_elo": 1317.87,
38949
+ "arena_rank": 182,
38950
+ "arena_votes": 10750
38951
  },
38952
  {
38953
  "name": "nvidia-nemotron-3-nano-30b-a3b-bf16",
38954
  "arena_name": "nvidia-nemotron-3-nano-30b-a3b-bf16",
38955
  "arena_org": "Nvidia",
38956
+ "arena_elo": 1317.8,
38957
+ "arena_rank": 183,
38958
+ "arena_votes": 15650
38959
  },
38960
  {
38961
  "name": "qwen-max-0919",
38962
  "arena_name": "qwen-max-0919",
38963
  "arena_org": "Alibaba",
38964
+ "arena_elo": 1317.65,
38965
+ "arena_rank": 184,
38966
  "arena_votes": 16478
38967
  },
 
 
 
 
 
 
 
 
38968
  {
38969
  "name": "qwen2.5-plus-1127",
38970
  "arena_name": "qwen2.5-plus-1127",
38971
  "arena_org": "Alibaba",
38972
+ "arena_elo": 1315.02,
38973
+ "arena_rank": 186,
38974
  "arena_votes": 10187
38975
  },
38976
  {
38977
  "name": "athene-v2-chat",
38978
  "arena_name": "athene-v2-chat",
38979
  "arena_org": "NexusFlow",
38980
+ "arena_elo": 1314.18,
38981
+ "arena_rank": 187,
38982
  "arena_votes": 24739
38983
  },
38984
  {
38985
  "name": "gpt-4-1106-preview",
38986
  "arena_name": "gpt-4-1106-preview",
38987
  "arena_org": "OpenAI",
38988
+ "arena_elo": 1312.38,
38989
+ "arena_rank": 190,
38990
  "arena_votes": 100105,
38991
  "aider_pass_rate": 0.519
38992
  },
 
38994
  "name": "hunyuan-standard-2025-02-10",
38995
  "arena_name": "hunyuan-standard-2025-02-10",
38996
  "arena_org": "Tencent",
38997
+ "arena_elo": 1310.84,
38998
+ "arena_rank": 191,
38999
  "arena_votes": 3904
39000
  },
 
 
 
 
 
 
 
 
39001
  {
39002
  "name": "grok-2-mini-2024-08-13",
39003
  "arena_name": "grok-2-mini-2024-08-13",
39004
  "arena_org": "xAI",
39005
+ "arena_elo": 1307.79,
39006
+ "arena_rank": 193,
39007
  "arena_votes": 52567
39008
  },
39009
+ {
39010
+ "name": "mercury",
39011
+ "arena_name": "mercury",
39012
+ "arena_org": "Inception AI",
39013
+ "arena_elo": 1306.14,
39014
+ "arena_rank": 195,
39015
+ "arena_votes": 1988
39016
+ },
39017
  {
39018
  "name": "olmo-3-32b-think",
39019
  "arena_name": "olmo-3-32b-think",
39020
  "arena_org": "Ai2",
39021
+ "arena_elo": 1306.09,
39022
+ "arena_rank": 196,
39023
+ "arena_votes": 6023
39024
  },
39025
  {
39026
  "name": "athene-70b-0725",
39027
  "arena_name": "athene-70b-0725",
39028
  "arena_org": "NexusFlow",
39029
+ "arena_elo": 1305.67,
39030
+ "arena_rank": 197,
39031
  "arena_votes": 19621
39032
  },
39033
  {
39034
  "name": "magistral-medium-2506",
39035
  "arena_name": "magistral-medium-2506",
39036
  "arena_org": "Mistral",
39037
+ "arena_elo": 1303.88,
39038
+ "arena_rank": 199,
39039
+ "arena_votes": 11825
39040
  },
39041
  {
39042
  "name": "mistral-small-3.1-24b-instruct-2503",
39043
  "arena_name": "mistral-small-3.1-24b-instruct-2503",
39044
  "arena_org": "Mistral",
39045
+ "arena_elo": 1302.9,
39046
+ "arena_rank": 201,
39047
+ "arena_votes": 33731
39048
  },
39049
  {
39050
  "name": "hunyuan-large-vision",
39051
  "arena_name": "hunyuan-large-vision",
39052
  "arena_org": "Tencent",
39053
+ "arena_elo": 1294.12,
39054
+ "arena_rank": 204,
39055
+ "arena_votes": 5451
39056
  },
39057
  {
39058
  "name": "amazon-nova-pro-v1.0",
39059
  "arena_name": "amazon-nova-pro-v1.0",
39060
  "arena_org": "Amazon",
39061
+ "arena_elo": 1289.74,
39062
+ "arena_rank": 206,
39063
  "arena_votes": 24745
39064
  },
39065
  {
39066
  "name": "reka-core-20240904",
39067
  "arena_name": "reka-core-20240904",
39068
  "arena_org": "Reka AI",
39069
+ "arena_elo": 1287.45,
39070
+ "arena_rank": 209,
39071
  "arena_votes": 7312
39072
  },
39073
+ {
39074
+ "name": "ibm-granite-h-small",
39075
+ "arena_name": "ibm-granite-h-small",
39076
+ "arena_org": "IBM",
39077
+ "arena_elo": 1287.41,
39078
+ "arena_rank": 210,
39079
+ "arena_votes": 5783
39080
+ },
39081
  {
39082
  "name": "gpt-4-0314",
39083
  "arena_name": "gpt-4-0314",
39084
  "arena_org": "OpenAI",
39085
+ "arena_elo": 1286.22,
39086
+ "arena_rank": 211,
39087
  "arena_votes": 54173,
39088
  "aider_pass_rate": 0.504
39089
  },
39090
  {
39091
+ "name": "olmo-3.1-32b-think",
39092
+ "arena_name": "olmo-3.1-32b-think",
39093
+ "arena_org": "Ai2",
39094
+ "arena_elo": 1285.88,
39095
+ "arena_rank": 213,
39096
+ "arena_votes": 8575
39097
  },
39098
  {
39099
  "name": "llama-3.1-nemotron-51b-instruct",
39100
  "arena_name": "llama-3.1-nemotron-51b-instruct",
39101
  "arena_org": "Nvidia",
39102
+ "arena_elo": 1285.65,
39103
+ "arena_rank": 214,
39104
  "arena_votes": 3749
39105
  },
39106
  {
39107
  "name": "gemini-1.5-flash-001",
39108
  "arena_name": "gemini-1.5-flash-001",
39109
  "arena_org": "Google",
39110
+ "arena_elo": 1285.3,
39111
+ "arena_rank": 215,
39112
  "arena_votes": 62833
39113
  },
 
 
 
 
 
 
 
 
39114
  {
39115
  "name": "nemotron-4-340b-instruct",
39116
  "arena_name": "nemotron-4-340b-instruct",
39117
  "arena_org": "Nvidia",
39118
+ "arena_elo": 1276.65,
39119
+ "arena_rank": 218,
39120
  "arena_votes": 19659
39121
  },
39122
  {
39123
  "name": "llama-3-70b-instruct",
39124
  "arena_name": "llama-3-70b-instruct",
39125
  "arena_org": "Meta",
39126
+ "arena_elo": 1275.47,
39127
+ "arena_rank": 220,
39128
  "arena_votes": 156876
39129
  },
39130
  {
39131
  "name": "mistral-small-24b-instruct-2501",
39132
  "arena_name": "mistral-small-24b-instruct-2501",
39133
  "arena_org": "Mistral",
39134
+ "arena_elo": 1273.66,
39135
+ "arena_rank": 222,
39136
  "arena_votes": 14681
39137
  },
39138
  {
39139
  "name": "glm-4-0520",
39140
  "arena_name": "glm-4-0520",
39141
  "arena_org": "Zhipu AI",
39142
+ "arena_elo": 1272.83,
39143
+ "arena_rank": 223,
39144
  "arena_votes": 9788
39145
  },
39146
  {
39147
  "name": "reka-flash-20240904",
39148
  "arena_name": "reka-flash-20240904",
39149
  "arena_org": "Reka AI",
39150
+ "arena_elo": 1271.47,
39151
+ "arena_rank": 224,
39152
  "arena_votes": 7536
39153
  },
39154
  {
39155
  "name": "c4ai-aya-expanse-32b",
39156
  "arena_name": "c4ai-aya-expanse-32b",
39157
  "arena_org": "Cohere",
39158
+ "arena_elo": 1266.53,
39159
+ "arena_rank": 226,
39160
  "arena_votes": 27124
39161
  },
39162
  {
39163
  "name": "amazon-nova-lite-v1.0",
39164
  "arena_name": "amazon-nova-lite-v1.0",
39165
  "arena_org": "Amazon",
39166
+ "arena_elo": 1260.17,
39167
+ "arena_rank": 232,
39168
  "arena_votes": 19372
39169
  },
39170
  {
39171
  "name": "olmo-2-0325-32b-instruct",
39172
  "arena_name": "olmo-2-0325-32b-instruct",
39173
  "arena_org": "Ai2",
39174
+ "arena_elo": 1251.5,
39175
+ "arena_rank": 235,
39176
  "arena_votes": 3334
39177
  },
39178
  {
39179
  "name": "amazon-nova-micro-v1.0",
39180
  "arena_name": "amazon-nova-micro-v1.0",
39181
  "arena_org": "Amazon",
39182
+ "arena_elo": 1240.48,
39183
+ "arena_rank": 238,
39184
  "arena_votes": 19364
39185
  },
39186
  {
39187
  "name": "ministral-8b-2410",
39188
  "arena_name": "ministral-8b-2410",
39189
  "arena_org": "Mistral",
39190
+ "arena_elo": 1236.78,
39191
+ "arena_rank": 240,
39192
  "arena_votes": 4781
39193
  },
39194
  {
39195
  "name": "gemini-pro-dev-api",
39196
  "arena_name": "gemini-pro-dev-api",
39197
  "arena_org": "Google",
39198
+ "arena_elo": 1234.46,
39199
+ "arena_rank": 241,
39200
  "arena_votes": 18354
39201
  },
39202
  {
39203
  "name": "hunyuan-standard-256k",
39204
  "arena_name": "hunyuan-standard-256k",
39205
  "arena_org": "Tencent",
39206
+ "arena_elo": 1233.1,
39207
+ "arena_rank": 243,
39208
  "arena_votes": 2728
39209
  },
39210
  {
39211
  "name": "reka-flash-21b-20240226-online",
39212
  "arena_name": "reka-flash-21b-20240226-online",
39213
  "arena_org": "Reka AI",
39214
+ "arena_elo": 1232.54,
39215
+ "arena_rank": 244,
39216
  "arena_votes": 15450
39217
  },
39218
  {
39219
  "name": "reka-flash-21b-20240226",
39220
  "arena_name": "reka-flash-21b-20240226",
39221
  "arena_org": "Reka AI",
39222
+ "arena_elo": 1225.79,
39223
+ "arena_rank": 248,
39224
  "arena_votes": 24806
39225
  },
39226
  {
39227
  "name": "c4ai-aya-expanse-8b",
39228
  "arena_name": "c4ai-aya-expanse-8b",
39229
  "arena_org": "Cohere",
39230
+ "arena_elo": 1222.47,
39231
+ "arena_rank": 251,
39232
  "arena_votes": 9818
39233
  },
39234
  {
39235
  "name": "mistral-medium",
39236
  "arena_name": "mistral-medium",
39237
  "arena_org": "Mistral",
39238
+ "arena_elo": 1222.22,
39239
+ "arena_rank": 252,
39240
  "arena_votes": 34550
39241
  },
39242
  {
39243
  "name": "gemini-pro",
39244
  "arena_name": "gemini-pro",
39245
  "arena_org": "Google",
39246
+ "arena_elo": 1221.16,
39247
+ "arena_rank": 253,
39248
  "arena_votes": 6390
39249
  },
39250
  {
39251
  "name": "gpt-3.5-turbo-1106",
39252
  "arena_name": "gpt-3.5-turbo-1106",
39253
  "arena_org": "OpenAI",
39254
+ "arena_elo": 1201.68,
39255
+ "arena_rank": 260,
39256
  "arena_votes": 16619,
39257
  "aider_pass_rate": 0.455
39258
  },
 
39260
  "name": "dbrx-instruct-preview",
39261
  "arena_name": "dbrx-instruct-preview",
39262
  "arena_org": "Databricks",
39263
+ "arena_elo": 1194.28,
39264
+ "arena_rank": 264,
39265
  "arena_votes": 32191
39266
  },
39267
  {
39268
  "name": "wizardlm-70b",
39269
  "arena_name": "wizardlm-70b",
39270
  "arena_org": "Microsoft",
39271
+ "arena_elo": 1183.88,
39272
+ "arena_rank": 267,
39273
  "arena_votes": 8214
39274
  },
39275
  {
39276
  "name": "snowflake-arctic-instruct",
39277
  "arena_name": "snowflake-arctic-instruct",
39278
  "arena_org": "Snowflake",
39279
+ "arena_elo": 1178.69,
39280
+ "arena_rank": 274,
39281
  "arena_votes": 32832
39282
  },
39283
  {
39284
  "name": "tulu-2-dpo-70b",
39285
  "arena_name": "tulu-2-dpo-70b",
39286
  "arena_org": "AllenAI/UW",
39287
+ "arena_elo": 1177.23,
39288
+ "arena_rank": 276,
39289
  "arena_votes": 6535
39290
  },
39291
  {
39292
  "name": "vicuna-33b",
39293
  "arena_name": "vicuna-33b",
39294
  "arena_org": "LMSYS",
39295
+ "arena_elo": 1171.98,
39296
+ "arena_rank": 278,
39297
  "arena_votes": 22479
39298
  },
39299
  {
39300
  "name": "llama-2-70b-chat",
39301
  "arena_name": "llama-2-70b-chat",
39302
  "arena_org": "Meta",
39303
+ "arena_elo": 1170.02,
39304
+ "arena_rank": 281,
39305
  "arena_votes": 38492
39306
  },
39307
  {
39308
  "name": "llama2-70b-steerlm-chat",
39309
  "arena_name": "llama2-70b-steerlm-chat",
39310
  "arena_org": "Nvidia",
39311
+ "arena_elo": 1154.52,
39312
+ "arena_rank": 287,
39313
  "arena_votes": 3585
39314
  },
39315
  {
39316
  "name": "dolphin-2.2.1-mistral-7b",
39317
  "arena_name": "dolphin-2.2.1-mistral-7b",
39318
  "arena_org": "Cognitive Computations",
39319
+ "arena_elo": 1151.2,
39320
+ "arena_rank": 289,
39321
  "arena_votes": 1679
39322
  },
39323
  {
39324
  "name": "mpt-30b-chat",
39325
  "arena_name": "mpt-30b-chat",
39326
  "arena_org": "MosaicML",
39327
+ "arena_elo": 1149.28,
39328
+ "arena_rank": 290,
39329
  "arena_votes": 2572
39330
  },
39331
  {
39332
  "name": "wizardlm-13b",
39333
  "arena_name": "wizardlm-13b",
39334
  "arena_org": "Microsoft",
39335
+ "arena_elo": 1148.4,
39336
+ "arena_rank": 292,
39337
  "arena_votes": 7044
39338
  },
39339
  {
39340
  "name": "falcon-180b-chat",
39341
  "arena_name": "falcon-180b-chat",
39342
  "arena_org": "TII",
39343
+ "arena_elo": 1146.22,
39344
+ "arena_rank": 293,
39345
  "arena_votes": 1295
39346
  },
39347
  {
39348
  "name": "phi-3-mini-4k-instruct-june-2024",
39349
  "arena_name": "phi-3-mini-4k-instruct-june-2024",
39350
  "arena_org": "Microsoft",
39351
+ "arena_elo": 1142.33,
39352
+ "arena_rank": 295,
39353
  "arena_votes": 12297
39354
  },
39355
  {
39356
  "name": "llama-2-13b-chat",
39357
  "arena_name": "llama-2-13b-chat",
39358
  "arena_org": "Meta",
39359
+ "arena_elo": 1140.72,
39360
+ "arena_rank": 296,
39361
  "arena_votes": 19174
39362
  },
39363
  {
39364
  "name": "vicuna-13b",
39365
  "arena_name": "vicuna-13b",
39366
  "arena_org": "LMSYS",
39367
+ "arena_elo": 1140.1,
39368
+ "arena_rank": 297,
39369
  "arena_votes": 19367
39370
  },
39371
  {
39372
  "name": "qwen-14b-chat",
39373
  "arena_name": "qwen-14b-chat",
39374
  "arena_org": "Alibaba",
39375
+ "arena_elo": 1137.76,
39376
+ "arena_rank": 298,
39377
  "arena_votes": 4964
39378
  },
39379
  {
39380
  "name": "palm-2",
39381
  "arena_name": "palm-2",
39382
  "arena_org": "Google",
39383
+ "arena_elo": 1136.47,
39384
+ "arena_rank": 299,
39385
  "arena_votes": 8554
39386
  },
39387
  {
39388
  "name": "codellama-34b-instruct",
39389
  "arena_name": "codellama-34b-instruct",
39390
  "arena_org": "Meta",
39391
+ "arena_elo": 1135.76,
39392
+ "arena_rank": 300,
39393
  "arena_votes": 7366
39394
  },
39395
  {
39396
  "name": "guanaco-33b",
39397
  "arena_name": "guanaco-33b",
39398
  "arena_org": "UW",
39399
+ "arena_elo": 1126.49,
39400
+ "arena_rank": 305,
39401
  "arena_votes": 2921
39402
  },
39403
  {
39404
  "name": "stripedhyena-nous-7b",
39405
  "arena_name": "stripedhyena-nous-7b",
39406
  "arena_org": "Together AI",
39407
+ "arena_elo": 1120.16,
39408
+ "arena_rank": 307,
39409
  "arena_votes": 5182
39410
  },
39411
  {
39412
  "name": "codellama-70b-instruct",
39413
  "arena_name": "codellama-70b-instruct",
39414
  "arena_org": "Meta",
39415
+ "arena_elo": 1118.29,
39416
+ "arena_rank": 308,
39417
  "arena_votes": 1143
39418
  },
39419
  {
39420
  "name": "vicuna-7b",
39421
  "arena_name": "vicuna-7b",
39422
  "arena_org": "LMSYS",
39423
+ "arena_elo": 1113.81,
39424
+ "arena_rank": 309,
39425
  "arena_votes": 6923
39426
  },
39427
  {
39428
  "name": "mistral-7b-instruct",
39429
  "arena_name": "mistral-7b-instruct",
39430
  "arena_org": "Mistral",
39431
+ "arena_elo": 1108.79,
39432
+ "arena_rank": 313,
39433
  "arena_votes": 8977
39434
  },
39435
  {
39436
  "name": "llama-2-7b-chat",
39437
  "arena_name": "llama-2-7b-chat",
39438
  "arena_org": "Meta",
39439
+ "arena_elo": 1107.36,
39440
+ "arena_rank": 314,
39441
  "arena_votes": 14148
39442
  },
39443
  {
39444
  "name": "olmo-7b-instruct",
39445
  "arena_name": "olmo-7b-instruct",
39446
  "arena_org": "Ai2",
39447
+ "arena_elo": 1073.77,
39448
+ "arena_rank": 317,
39449
  "arena_votes": 6328
39450
  },
39451
  {
39452
  "name": "koala-13b",
39453
  "arena_name": "koala-13b",
39454
  "arena_org": "UC Berkeley",
39455
+ "arena_elo": 1069.58,
39456
+ "arena_rank": 318,
39457
  "arena_votes": 6965
39458
  },
39459
  {
39460
  "name": "alpaca-13b",
39461
  "arena_name": "alpaca-13b",
39462
  "arena_org": "Stanford",
39463
+ "arena_elo": 1066.61,
39464
+ "arena_rank": 319,
39465
  "arena_votes": 5745
39466
  },
39467
  {
39468
  "name": "gpt4all-13b-snoozy",
39469
  "arena_name": "gpt4all-13b-snoozy",
39470
  "arena_org": "Nomic AI",
39471
+ "arena_elo": 1065.14,
39472
+ "arena_rank": 320,
39473
  "arena_votes": 1743
39474
  },
39475
  {
39476
  "name": "mpt-7b-chat",
39477
  "arena_name": "mpt-7b-chat",
39478
  "arena_org": "MosaicML",
39479
+ "arena_elo": 1060.99,
39480
+ "arena_rank": 321,
39481
  "arena_votes": 3924
39482
  },
39483
  {
39484
  "name": "chatglm3-6b",
39485
  "arena_name": "chatglm3-6b",
39486
  "arena_org": "Tsinghua",
39487
+ "arena_elo": 1055.2,
39488
+ "arena_rank": 322,
39489
  "arena_votes": 4658
39490
  },
39491
  {
39492
  "name": "RWKV-4-Raven-14B",
39493
  "arena_name": "RWKV-4-Raven-14B",
39494
  "arena_org": "RWKV",
39495
+ "arena_elo": 1040.47,
39496
+ "arena_rank": 323,
39497
  "arena_votes": 4845
39498
  },
39499
  {
39500
  "name": "chatglm2-6b",
39501
  "arena_name": "chatglm2-6b",
39502
  "arena_org": "Tsinghua",
39503
+ "arena_elo": 1023.31,
39504
+ "arena_rank": 324,
39505
  "arena_votes": 2658
39506
  },
39507
  {
39508
  "name": "oasst-pythia-12b",
39509
  "arena_name": "oasst-pythia-12b",
39510
  "arena_org": "OpenAssistant",
39511
+ "arena_elo": 1021.21,
39512
+ "arena_rank": 325,
39513
  "arena_votes": 6310
39514
  },
39515
  {
39516
  "name": "chatglm-6b",
39517
  "arena_name": "chatglm-6b",
39518
  "arena_org": "Tsinghua",
39519
+ "arena_elo": 994.719,
39520
+ "arena_rank": 326,
39521
  "arena_votes": 4914
39522
  },
39523
  {
39524
  "name": "fastchat-t5-3b",
39525
  "arena_name": "fastchat-t5-3b",
39526
  "arena_org": "LMSYS",
39527
+ "arena_elo": 990.477,
39528
+ "arena_rank": 327,
39529
  "arena_votes": 4203
39530
  },
39531
  {
39532
  "name": "stablelm-tuned-alpha-7b",
39533
  "arena_name": "stablelm-tuned-alpha-7b",
39534
  "arena_org": "Stability AI",
39535
+ "arena_elo": 951.751,
39536
+ "arena_rank": 330,
39537
  "arena_votes": 3287
39538
  },
39539
  {