| Rank | Model | Score |
|---|---|---|
| 1 | deepseek-v4-1-flash | 88.1 |
| 2 | deepseek-v4-1-flash | 88.1 |
| 3 | gpt-5-5-cyber | 85.6 |
| 4 | gpt-5-6-sol | 84.5 |
| 5 | glm-5-3 | 84.5 |
| 6 | deepseek-v4-pro | 83.3 |
| 7 | claude-mythos-preview | 83.1 |
| 8 | gpt-5-5 | 81.8 |
| 9 | gpt-5-4 | 79 |
| 10 | hy4-preview | 78.4 |
| 11 | deepseek-v4-flash-vision-exp | 75.3 |
| 12 | claude-opus-4-7 | 73.1 |
| 13 | seed-2-1-pro | 68.7 |
| 14 | glm-5-1 | 68.7 |
| 15 | seed-2-1-turbo | 67 |
| 16 | claude-opus-4-6 | 66.6 |
| 17 | claude-sonnet-4-6 | 65.2 |
| 18 | claude-opus-4-5 | 50.6 |
| 19 | muse-spark | 43.5 |
| 20 | glm-5 | 43.2 |
| 21 | kimi-k2-5 | 41.3 |
| 22 | gpt-5 | 39.4 |
| 23 | gemini-3-1-pro | 38.8 |
| 24 | claude-sonnet-4-5 | 28.9 |
| 25 | claude-opus-4-1 | 25 |
1 phaseActive
No evaluations yet for this benchmark.