| Rank | Model | Score |
|---|---|---|
| 1 | gpt-6-astra | 96 |
| 2 | fugu | 95.5 |
| 3 | fugu-ultra | 95.5 |
| 4 | gpt-5-6-sol | 94.6 |
| 5 | gemini-3-1-pro | 94.3 |
| 6 | claude-opus-4-7 | 94.2 |
| 7 | claude-opus-4-8 | 93.6 |
| 8 | gpt-5-5 | 93.6 |
| 9 | kimi-k3 | 93.5 |
| 10 | gpt-5-2-pro-2025-12-11 | 93.2 |
| 11 | grok-4-5 | 93 |
| 12 | gpt-5-6-terra | 92.9 |
| 13 | gpt-5-4 | 92.8 |
| 14 | ornith-1-5-397b | 92.8 |
| 15 | qwen3-8-max | 92.6 |
| 16 | gpt-5-2 | 92.4 |
| 17 | qwen3-7-max | 92.4 |
| 18 | gpt-5-6-luna | 92.3 |
| 19 | hy4-preview | 92.3 |
| 20 | grok-4-20 | 92 |
| 21 | gemini-3-pro | 91.9 |
| 22 | qwen3-8-flash-next | 91.7 |
| 23 | claude-opus-4-6 | 91.3 |
| 24 | glm-5-2 | 91.2 |
| 25 | deepseek-v4-1-flash | 90.9 |
1 phaseActive