| Rank | Model | Score |
|---|---|---|
| 1 | claude-fable-5 | 95 |
| 2 | claude-mythos-preview | 93.9 |
| 3 | claude-opus-4-8 | 88.6 |
| 4 | claude-opus-4-7 | 87.6 |
| 5 | ornith-1-5-397b | 86 |
| 6 | claude-sonnet-5 | 85.2 |
| 7 | beam-1-0-501b-a23b | 81.6 |
| 8 | claude-opus-4-6 | 81.42 |
| 9 | claude-opus-4-5 | 80.9 |
| 10 | deepseek-v4-pro-max | 80.6 |
| 11 | gemini-3-1-pro | 80.6 |
| 12 | minimax-m3 | 80.5 |
| 13 | qwen3-7-max | 80.4 |
| 14 | qwen3-7-max | 80.4 |
| 15 | kimi-k2-6 | 80.2 |
| 16 | minimax-m2-5 | 80.2 |
| 17 | kimi-k2-0905 | 80.2 |
| 18 | gpt-5-2 | 80 |
| 19 | claude-sonnet-4-6 | 79.6 |
| 20 | claude-sonnet-4-6 | 79.6 |
| 21 | deepseek-v4-flash-max | 79 |
| 22 | ornith-1-5-35b-a3b | 79 |
| 23 | mimo-v2-5-pro | 78.9 |
| 24 | qwen3-6-plus | 78.8 |
| 25 | dots3-note-preview | 78.4 |
1 phaseActive
No evaluations yet for this benchmark.