| Rank | Model | Score |
|---|---|---|
| 1 | nex-n2-5-max | 92.6 |
| 2 | gpt-6-astra | 91.5 |
| 3 | kimi-k3 | 91.2 |
| 4 | gpt-5-6-sol | 90.4 |
| 5 | nex-n2-5-pro | 89.7 |
| 6 | claude-fable-5 | 88 |
| 7 | gpt-5-6-terra | 87.5 |
| 8 | ornith-1-5-397b | 86.6 |
| 9 | seed-2-1-pro | 86.2 |
| 10 | gemini-3-1-pro | 85.9 |
| 11 | seed-2-1-turbo | 84.9 |
| 12 | claude-sonnet-5 | 84.7 |
| 13 | gpt-5-5 | 84.4 |
| 14 | claude-opus-4-8 | 84.3 |
| 15 | hy3 | 84.2 |
| 16 | claude-opus-4-6 | 84 |
| 17 | minimax-m3 | 83.5 |
| 18 | deepseek-v4-pro | 83.4 |
| 19 | deepseek-v4-pro-max | 83.4 |
| 20 | gpt-5-6-luna | 83.3 |
| 21 | kimi-k2-6 | 83.2 |
| 22 | gpt-5-4 | 82.7 |
| 23 | claude-opus-4-7 | 79.3 |
| 24 | glm-5-1 | 79.3 |
| 25 | gpt-5-1-thinking | 78.4 |
1 phaseActive