| Rank | Model | Score |
|---|---|---|
| 1 | longcat-flash-thinking | 0.992 |
| 2 | glm-4-5 | 0.982 |
| 3 | glm-4-5-air | 0.981 |
| 4 | kimi-k2-instruct-0905 | 0.974 |
| 5 | kimi-k2-instruct | 0.974 |
| 6 | llama-3-1-nemotron-ultra-253b-v1 | 0.97 |
| 7 | longcat-flash-lite | 0.968 |
| 8 | llama-3-3-nemotron-super-49b-v1 | 0.966 |
| 9 | longcat-flash-chat | 0.964 |
| 10 | kimi-k1-5 | 0.962 |
| 11 | deepseek-r1-0528 | 0.959 |
| 12 | deepseek-v3-0324 | 0.94 |
| 13 | qwq-32b | 0.906 |
| 14 | deepseek-v3 | 0.902 |
1 phaseActive
No evaluations yet for this benchmark.