| Rank | Model | Score |
|---|---|---|
| 1 | claude-fable-5 | 40 |
| 2 | gemini-3-1-pro | 33 |
| 3 | muse-spark-open-816b-a42b | 25 |
| 4 | gpt-5-6-sol | 22 |
| 5 | nemotron-3-5-lightning-30b-a3b | 16.6 |
| 6 | nvidia-nemotron-labs-dory1-0-4b | 10.03 |
| 7 | kimi-k2-6 | 6 |
| 8 | glm-5-2 | 4 |
| 9 | raon-1-mini-preview | 3.5 |
| 10 | inkling | 2.1 |
| 11 | lfm3-1-7b | 0.5 |
| 12 | nemotron-3-ultra-550b-a55b | -1 |
| 13 | kimi-k2-5 | -8 |
| 14 | deepseek-v4-pro | -10 |
| 15 | lfm2-5-24b-a2b | -24.9 |
| 16 | lfm2-5-2-6b | -29.5 |
1 phaseActive