Arena Document (Style Controlled)
Professional Work
Style-controlled Document Arena rating for models analyzing document and long-content inputs. Higher ratings indicate stronger preference in blind pairwise user votes after adjusting for response style.
Top models (higher is better)
| Model | Score |
|---|---|
| Claude Fable 5 | 1507 |
| Opus 4.7 | 1497 |
| Opus 4.6 | 1495 |
| Claude Opus 5 | 1493 |
| Opus 4.8 | 1487 |
| Muse Spark 1.1 | 1483 |
| GPT-5.6 Terra | 1482 |
| GPT-5.6 Sol | 1481 |
| Sonnet 5 | 1479 |
| GPT-5.5 | 1478 |
| Sonnet 4.6 | 1478 |
| GPT-5.4 | 1469 |
| GPT-5.6 Luna | 1467 |
| Muse Spark | 1466 |
| Opus 4.5 | 1464 |
| Gemini 3.5 Flash | 1462 |
| Grok 4.5 | 1462 |
| Gemini 3.1 Pro Preview | 1460 |
| Gemini 3 Pro Preview | 1451 |
| Kimi K2.6 | 1450 |
| Qwen3.7-Plus | 1449 |
| Sonnet 4.5 | 1446 |
| Gemma 4 31B | 1445 |
| Gemini 3 Flash Preview | 1441 |
| Kimi K2.5 | 1435 |
| MiniMax M3 | 1434 |
| Gemini 2.5 Pro | 1430 |
| GPT-5.2 | 1426 |
| Haiku 4.5 | 1422 |
| GPT-5.1 | 1412 |
| GLM 5V Turbo | 1402 |