Leaderboard
Switch view: Combined pools all votes, Text/Image filter to that modality. BT Elo = Bradley-Terry MLE (refreshed every 30 min, with 95% bootstrap CI). K=4 / K=8 = live online Elo at two K-factor settings. Click headers to sort.
| # | Model | Released | BT Elo ▼ | online K=4 | online K=8 | games | code-runs |
|---|---|---|---|---|---|---|---|
| 1 | Fable 5 claude-fable-5 | 2026-06 | 1230 ±73 | 1092.7 | 1148.2 | 97 | – |
| 2 | GPT-5.5 gpt-5.5 | 2026-04 | 1135 ±27 | 1134.2 | 1142.4 | 651 | 91% |
| 3 | Gemini 3.1 Pro gemini-3.1-pro-preview | 2026-02 | 1116 ±23 | 1116.3 | 1114.6 | 760 | 70% |
| 4 | Gemini 3.5 Flash gemini-3.5-flash | 2026-05 | 1114 ±27 | 1125.8 | 1127.9 | 626 | 48% |
| 5 | Claude Opus 4.8 claude-opus-4-8 | 2026-05 | 1091 ±76 | 1025.0 | 1046.4 | 72 | – |
| 6 | GPT-5.4 gpt-5.4 | 2026-03 | 1042 ±27 | 1047.7 | 1044.8 | 565 | 87% |
| 7 | Gemini 3 Flash gemini-3-flash-preview | 2025-12 | 1010 ±25 | 1031.5 | 1036.8 | 632 | 55% |
| 8 | Claude Sonnet 4.6 claude-sonnet-4-6 | 2026-02 | 983 ±27 | 984.8 | 974.2 | 600 | 80% |
| 9 | Claude Opus 4.7 claude-opus-4-7 | 2026-04 | 977 ±26 | 979.6 | 967.3 | 659 | 91% |
| 10 | Gemma 4 31B gemma-4-31b-it | 2026-04 | 921 ±30 | 940.6 | 933.1 | 518 | 58% |
| 11 | GPT-5.4 Mini gpt-5.4-mini | 2026-03 | 920 ±26 | 931.1 | 927.2 | 591 | 73% |
| 12 | Gemini 3.1 Flash Lite gemini-3.1-flash-lite-preview | 2026-03 | 849 ±31 | 905.5 | 906.9 | 427 | 58% |
| 13 | Gemma 4 26B A4B gemma-4-26b-a4b-it | 2026-04 | 828 ±33 | 872.4 | 852.2 | 452 | 52% |
| 14 | Claude Haiku 4.5 claude-haiku-4-5 | 2025-10 | 771 ±33 | 826.0 | 802.3 | 446 | 50% |