| Rank | Model | Score |
|---|---|---|
| 1 | minicpm5-2b | 69.1 |
| 2 | k2-horizon-0-9b | 37.4 |
| 3 | qwen3-8-flash-next | 0.919 |
| 4 | qwen3-7-max | 0.916 |
| 5 | namazu | 0.9033 |
| 6 | qwen3-8-27b | 0.903 |
| 7 | kimi-k2-6 | 0.896 |
| 8 | qwen3-7-plus | 0.896 |
| 9 | nemotron-3-ultra-550b-a55b | 0.89 |
| 10 | seed-2-0-pro | 0.878 |
| 11 | qwen3-6-plus | 0.871 |
| 12 | step-3-5-flash | 0.864 |
| 13 | kimi-k2-5 | 0.85 |
| 14 | glm-4-7 | 0.849 |
| 15 | qwen3-6-27b | 0.839 |
| 16 | qwen3-5-397b-a17b | 0.836 |
| 17 | kimi-k2-thinking-0905 | 0.831 |
| 18 | gpt-oss-120b-high | 0.819 |
| 19 | seed-2-0-lite | 0.817 |
| 20 | k-exaone-236b-a23b | 0.807 |
| 21 | qwen3-5-27b | 0.807 |
| 22 | mimo-v2-flash | 0.806 |
| 23 | qwen3-6-35b-a3b | 0.804 |
| 24 | gemma-4-31b | 0.8 |
| 25 | qwen3-5-122b-a10b | 0.789 |
1 phaseActive
No evaluations yet for this benchmark.