| Rank | Model | Score |
|---|---|---|
| 1 | kimi-k3 | 91.2 |
| 2 | gpt-5-6-sol | 90.4 |
| 3 | claude-fable-5 | 88 |
| 4 | gpt-5-6-terra | 87.5 |
| 5 | seed-2-1-pro | 86.2 |
| 6 | gemini-3-1-pro | 85.9 |
| 7 | seed-2-1-turbo | 84.9 |
| 8 | claude-sonnet-5 | 84.7 |
| 9 | gpt-5-5 | 84.4 |
| 10 | claude-opus-4-8 | 84.3 |
| 11 | hy3 | 84.2 |
| 12 | claude-opus-4-6 | 84 |
| 13 | minimax-m3 | 83.5 |
| 14 | deepseek-v4-pro | 83.4 |
| 15 | deepseek-v4-pro-max | 83.4 |
| 16 | gpt-5-6-luna | 83.3 |
| 17 | kimi-k2-6 | 83.2 |
| 18 | gpt-5-4 | 82.7 |
| 19 | claude-opus-4-7 | 79.3 |
| 20 | glm-5-1 | 79.3 |
| 21 | gpt-5-1-thinking | 78.4 |
| 22 | gpt-5-2-pro-2025-12-11 | 77.9 |
| 23 | seed-2-0-pro | 77.3 |
| 24 | inkling | 77.1 |
| 25 | gpt-5-1 | 76.5 |
1 phaseActive