| Rank | Model | Score |
|---|---|---|
| 1 | claude-fable-5 | 84.2 |
| 2 | gpt-5-5 | 83.2 |
| 3 | gpt-5-6-sol | 83 |
| 4 | gpt-5-1 | 82.8 |
| 5 | seed-2-1-pro | 82.7 |
| 6 | claude-opus-4-7 | 82.5 |
| 7 | seed-2-1-turbo | 82.2 |
| 8 | gemini-3-1-pro | 82 |
| 9 | gemini-2-5-pro | 81.7 |
| 10 | kimi-k3 | 81.6 |
| 11 | gemini-3-flash | 81.2 |
| 12 | gpt-5-4 | 81.2 |
| 13 | qwen3-7-max | 81.2 |
| 14 | claude-opus-4-8 | 81 |
| 15 | gemini-3-pro | 81 |
| 16 | gpt-5-6-terra | 80.7 |
| 17 | muse-spark | 80.4 |
| 18 | gpt-5-2 | 79.5 |
| 19 | qwen3-5-397b-a17b | 79.5 |
| 20 | kimi-k2-6 | 79 |
| 21 | qwen3-7-plus | 79 |
| 22 | qwen3-6-plus | 78.8 |
| 23 | claude-opus-4-5 | 78.4 |
| 24 | gpt-5-6-luna | 78.4 |
| 25 | gpt-5 | 78.4 |
1 phaseActive