| Rank | Model | Score |
|---|---|---|
| 1 | deepseek-v4-pro-max | 93.5 |
| 2 | fugu-ultra | 93.2 |
| 3 | fugu | 92.9 |
| 4 | deepseek-v4-flash-max | 91.6 |
| 5 | gpt-5-1 | 90.1 |
| 6 | gemini-3-1-pro | 89.1 |
| 7 | gpt-5 | 88.3 |
| 8 | claude-opus-4-7 | 88 |
| 9 | gemini-3-pro | 87.8 |
| 10 | solar-pro-4 | 87.8 |
| 11 | claude-opus-4-8 | 85.6 |
| 12 | claude-sonnet-4-6 | 85.4 |
| 13 | grok-4-5 | 85 |
| 14 | claude-sonnet-5 | 84.5 |
| 15 | kimi-k2-thinking-0905 | 83.5 |
| 16 | deepseek-v3-2-thinking | 83.3 |
| 17 | deepseek-v3-2 | 83.3 |
| 18 | minimax-m2 | 83 |
| 19 | seed-2-1-pro | 82.5 |
| 20 | gemini-3-flash | 82.1 |
| 21 | nemotron-3-super-120b-a12b | 81.2 |
| 22 | claude-opus-4-5 | 80.3 |
| 23 | o4-mini-high | 80.2 |
| 24 | kimi-k2-instruct | 80 |
| 25 | longcat-flash-thinking | 79.4 |
1 phaseActive