| Rank | Model | Score |
|---|---|---|
| 1 | muse-spark-1-2 | 90.3 |
| 2 | muse-spark | 88.1 |
| 3 | kimi-k3 | 84.2 |
| 4 | claude-fable-5 | 83.3 |
| 5 | gpt-5-6-sol | 81.8 |
| 6 | gemini-3-1-pro | 78.2 |
| 7 | glm-5-2 | 77.8 |
| 8 | muse-glimmer | 75.5 |
| 9 | gpt-5-5 | 75.3 |
| 10 | inkling | 74.1 |
| 11 | qwen3-6-plus | 74.1 |
| 12 | deepseek-v4-pro | 73.2 |
| 13 | kimi-k2-6 | 68.1 |
| 14 | gpt-5-4 | 67.2 |
| 15 | kimi-k2-5 | 64 |
| 16 | qwen3-6-35b-a3b | 62.8 |
| 17 | claude-opus-4-6 | 62.7 |
| 18 | claude-opus-4-5 | 62.3 |
| 19 | solar-pro-4 | 61.4 |
| 20 | claude-sonnet-4-6 | 61.3 |
| 21 | gpt-5-2 | 60.6 |
| 22 | gemini-3-flash | 57.4 |
| 23 | nemotron-3-ultra-550b-a55b | 44.7 |
1 phaseActive
No evaluations yet for this benchmark.