| Rank | Model | Score |
|---|---|---|
| 1 | qwen3-8-max | 82.8 |
| 2 | nemotron-3-ultra-550b-a55b | 81.4 |
| 3 | hermes-3-70b | 81.2 |
| 4 | nova-2-pro | 80.2 |
| 5 | inkling | 79.8 |
| 6 | gemini-3-1-pro | 77.1 |
| 7 | muse-glimmer | 77 |
| 8 | deepseek-v4-pro | 76.5 |
| 9 | qwen3-5-27b | 76.5 |
| 10 | qwen3-5-397b-a17b | 76.5 |
| 11 | qwen3-5-122b-a10b | 76.1 |
| 12 | kimi-k2-6 | 76 |
| 13 | qwen3-6-plus | 74.2 |
| 14 | glm-5-2 | 73.3 |
| 15 | nemotron-3-5-lightning-30b-a3b | 72.9 |
| 16 | gpt-5-6-sol | 72.7 |
| 17 | nemotron-3-super-120b-a12b | 72.6 |
| 18 | kimi-k2-5 | 70.2 |
| 19 | qwen3-5-35b-a3b | 70.2 |
| 20 | qwen3-5-9b | 64.5 |
| 21 | claude-fable-5 | 63.5 |
| 22 | qwen3-5-4b | 59.2 |
| 23 | lfm2-5-2-6b | 59.17 |
| 24 | qwen3-5-2b | 41.3 |
| 25 | lfm2-5-vl-3b | 25.8 |
1 phaseActive