Document · Style Control
Arena · 44 models
| Rank | Model | Score |
|---|---|---|
| 1 | claude-fable-5 | 1,498.8779 |
| 2 | claude-opus-4-6-high | 1,495.2565 |
| 3 | claude-opus-4-7 | 1,494.1884 |
| 4 | claude-opus-4-6 | 1,493.9382 |
| 5 | claude-opus-4-7-high | 1,493.0357 |
| 6 | claude-fable-5.1-max | 1,492.8291 |
| 7 | claude-opus-5-high | 1,489.747 |
| 8 | gpt-5.6-sol-xhigh | 1,488.6696 |
| 9 | claude-opus-4-8-high | 1,485.9343 |
| 10 | gpt-5.5 | 1,482.8112 |
| 11 | gpt-5.5-high | 1,480.2432 |
| 12 | muse-spark-1.1 | 1,479.4577 |
| 13 | claude-sonnet-4-6 | 1,477.7264 |
| 14 | gpt-5.6-terra-xhigh | 1,476.6531 |
| 15 | claude-sonnet-5-high | 1,475.6993 |
| 16 | claude-opus-4-8 | 1,475.3797 |
| 17 | gpt-6-astra-max | 1,472.5575 |
| 18 | gpt-5.4 | 1,470.09 |
| 19 | muse-spark-1.3-max | 1,467.8863 |
| 20 | muse-spark | 1,467.2929 |
| 21 | claude-opus-4-5-20251101 | 1,464.6127 |
| 22 | grok-4.5 | 1,464.3456 |
| 23 | gpt-5.6-luna-xhigh | 1,461.9842 |
| 24 | grok-4.6-high | 1,461.0739 |
| 25 | gemini-3.5-flash-medium | 1,460.5611 |
| 26 | gpt-5.5-instant | 1,460.3197 |
| 27 | gemini-3.1-pro-preview | 1,458.8644 |
| 28 | gemini-3.6-flash-high | 1,453.4194 |
| 29 | gemini-3.5-flash-high | 1,453.3953 |
| 30 | qwen3.7-plus | 1,452.5438 |
| 31 | gemini-3-pro | 1,451.0895 |
| 32 | kimi-k2.6 | 1,449.8008 |
| 33 | claude-sonnet-4-5-20250929 | 1,449.0763 |
| 34 | gemma-4-31b | 1,444.5076 |
| 35 | grok-4.20-beta-0309-reasoning | 1,439.4304 |
| 36 | gemini-3-flash | 1,439.1503 |
| 37 | kimi-k2.5-thinking | 1,435.963 |
| 38 | minimax-m3 | 1,432.9648 |
| 39 | gemini-2.5-pro | 1,430.5781 |
| 40 | gpt-5.2 | 1,425.3654 |
| 41 | gpt-5.2-high | 1,423.1641 |
| 42 | claude-haiku-4-5-20251001 | 1,418.7268 |
| 43 | gpt-5.1 | 1,415.8397 |
| 44 | glm-5v-turbo | 1,400.0664 |