| Rank | Model | Score |
|---|---|---|
| 1 | claude-sonnet-5 | 57.4 |
| 2 | ornith-1-5-397b | 56.1 |
| 3 | kimi-k3 | 56 |
| 4 | seed-2-1-pro | 55.7 |
| 5 | glm-5-3-flash | 55.3 |
| 6 | glm-5-2 | 54.7 |
| 7 | seed-2-1-turbo | 54.6 |
| 8 | kimi-k2-thinking-0905 | 51 |
| 9 | fugu-ultra | 50 |
| 10 | qwen3-5-27b | 48.5 |
| 11 | deepseek-v4-pro-max | 48.2 |
| 12 | qwen3-5-122b-a10b | 47.5 |
| 13 | qwen3-5-35b-a3b | 47.4 |
| 14 | fugu | 47.2 |
| 15 | gemini-3-1-pro | 46.44 |
| 16 | inkling | 46 |
| 17 | deepseek-v4-flash-max | 45.1 |
| 18 | gpt-5-4 | 44.32 |
| 19 | qwen3-8-max | 43.6 |
| 20 | gemini-3-flash | 43.5 |
| 21 | claude-sonnet-5 | 43.2 |
| 22 | glm-4-7 | 42.8 |
| 23 | deepseek-v4-pro | 42.7 |
| 24 | gpt-5-5 | 41.4 |
| 25 | qwen3-7-max | 41.4 |
1 phaseActive
No evaluations yet for this benchmark.