Leaderboard
Human-voted ELO, computed from the votes on all documents · updates live with every vote.
| # | Model | Today | Score | Games | Win % |
|---|---|---|---|---|---|
| 1 | = | 1294 1253–1341 | 489 | 79% | |
| 2 | = | 1242 1210–1279 | 476 | 74% | |
| 3 | = | 1230 1202–1267 | 493 | 73% | |
| 4 | = | 1224 1190–1248 | 466 | 73% | |
| 5 | = | 1223 1191–1267 | 429 | 73% | |
| 6 | = | 1196 1155–1223 | 497 | 70% | |
| 7 | = | 1192 1162–1230 | 467 | 69% | |
| 8 | Kimi K3 | = | 1174 1132–1216 | 448 | 68% |
| 9 | = | 1167 1121–1212 | 215 | 67% | |
| 10 | = | 1166 1133–1203 | 463 | 67% | |
| 11 | = | 1146 1107–1174 | 481 | 64% | |
| 12 | = | 1129 1080–1158 | 466 | 63% | |
| 13 | = | 1118 1090–1146 | 466 | 61% | |
| 14 | = | 1113 1079–1141 | 459 | 61% | |
| 15 | = | 1099 1068–1134 | 461 | 60% | |
| 16 | = | 1088 1051–1122 | 470 | 58% | |
| 17 | = | 1074 1045–1097 | 480 | 54% | |
| 18 | = | 1049 1003–1094 | 211 | 52% | |
| 19 | = | 1040 997–1085 | 207 | 52% | |
| 20 | = | 1017 991–1051 | 457 | 51% | |
| 21 | = | 1000 970–1035 | 458 | 48% | |
| 22 | KAT-Coder-Pro V2.5 | = | 1000 970–1038 | 441 | 48% |
| 23 | Kimi K2.7 Code | = | 981 945–1008 | 468 | 46% |
| 24 | = | 978 942–1009 | 442 | 46% | |
| 25 | Inkling | = | 956 915–992 | 441 | 43% |
| 26 | = | 859 818–901 | 461 | 32% | |
| 27 | = | 859 819–888 | 457 | 33% | |
| 28 | = | 838 798–877 | 327 | 31% | |
| 29 | Hy3 Preview | = | 823 796–856 | 477 | 28% |
| 30 | = | 764 734–796 | 466 | 25% | |
| 31 | = | 704 653–744 | 437 | 19% | |
| 32 | = | 704 677–736 | 466 | 20% | |
| 33 | = | 695 651–750 | 455 | 19% | |
| 34 | = | 681 634–722 | 467 | 18% | |
| 35 | Mistral Medium 3.5 | = | 640 581–695 | 453 | 15% |
| 36 | Trinity Large Thinking | = | 535 482–587 | 437 | 9% |

Kimi K3
KAT-Coder-Pro V2.5
Inkling
Hy3 Preview
Mistral Medium 3.5
Trinity Large Thinking