| Rank | Model | Score |
|---|---|---|
| 1 | gpt-5-1 | 98.8 |
| 2 | o3-mini | 97.9 |
| 3 | gemini-3-flash | 97.5 |
| 4 | gpt-5-2 | 97.5 |
| 5 | deepseek-r1-0528 | 97.3 |
| 6 | o3 | 96.7 |
| 7 | gpt-5-5 | 96.3 |
| 8 | gemini-2-5-pro | 96.2 |
| 9 | o1 | 94.8 |
| 10 | gemini-2-5-flash | 94.8 |
| 11 | phi-4-reasoning-plus | 93.3 |
| 12 | phi-4-reasoning | 92.7 |
| 13 | deepseek-v3-2 | 92.3 |
| 14 | qwq-32b | 90.6 |
| 15 | deepseek-v3-1 | 90.4 |
| 16 | ministral-3-14b-instruct-2512 | 90.4 |
| 17 | deepseek-v3 | 90.2 |
| 18 | gemini-2-0-flash | 89.7 |
| 19 | kimi-k2-0905 | 89.1 |
| 20 | gemma-3-27b | 89 |
| 21 | llama-3-3-70b-instruct | 87.8 |
| 22 | mistral-large-3 | 87.7 |
| 23 | ministral-3-8b-instruct-2512 | 87.6 |
| 24 | gemini-2-0-flash-lite | 86.8 |
| 25 | mimo-v2-5-pro | 86.2 |
1 phaseActive
No evaluations yet for this benchmark.