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 | 1499 |
| Opus 4.6 | 1495 |
| Opus 4.7 | 1494 |
| Claude Fable 5.1 | 1493 |
| Claude Opus 5 | 1490 |
| GPT-5.6 Sol | 1489 |
| Opus 4.8 | 1486 |
| GPT-5.5 | 1483 |
| Muse Spark 1.1 | 1479 |
| Sonnet 4.6 | 1478 |
| GPT-5.6 Terra | 1477 |
| Sonnet 5 | 1476 |
| GPT-6 Astra | 1473 |
| GPT-5.4 | 1470 |
| Muse Spark 1.3 | 1468 |
| Muse Spark | 1467 |
| Opus 4.5 | 1465 |
| Grok 4.5 | 1464 |
| GPT-5.6 Luna | 1462 |
| Grok 4.6 | 1461 |
| Gemini 3.5 Flash | 1461 |
| Gemini 3.1 Pro Preview | 1459 |
| Gemini 3.6 Flash | 1453 |
| Qwen3.7-Plus (source unspecified) | 1453 |
| Gemini 3 Pro Preview | 1451 |
| Kimi K2.6 | 1450 |
| Sonnet 4.5 | 1449 |
| Gemma 4 31B IT | 1445 |
| Gemini 3 Flash Preview | 1439 |
| Kimi K2.5 | 1436 |
| MiniMax M3 | 1433 |
| Gemini 2.5 Pro | 1431 |
| GPT-5.2 | 1425 |
| Haiku 4.5 | 1419 |
| GPT-5.1 | 1416 |
| GLM 5V Turbo | 1400 |