Arena Text — Multi-turn (No Style Control)
Chat & Writing
Raw Arena rating for multi-turn Text Arena conversations without style-control adjustment. Higher ratings indicate stronger preference in blind pairwise user votes.
Top models (higher is better)
| Model | Score |
|---|---|
| Gemini 4 Argon | 1547 |
| Opus 4.6 | 1512 |
| Muse Wonder | 1507 |
| Opus 4.7 | 1505 |
| Claude Fable 5 | 1504 |
| Claude Opus 5.5 | 1504 |
| Gemini 3.8 Flash | 1503 |
| Claude Opus 5 | 1500 |
| Muse Spark 1.2 | 1500 |
| Claude Fable 5.1 | 1495 |
| Qwen3.8-Max | 1490 |
| Kimi K3 | 1489 |
| Muse Spark 1.3 | 1489 |
| Gemini 3.1 Pro Preview | 1487 |
| Gemini 3.7 Flash | 1487 |
| Gemini 3 Pro Preview | 1484 |
| Muse Spark 1.1 | 1484 |
| GPT-5.4 | 1482 |
| Gemini 3.6 Flash | 1481 |
| Gemini 3.5 Flash | 1481 |
| Qwen3.7 Max Preview | 1480 |
| Muse Spark | 1477 |
| GPT-5.5 | 1476 |
| Opus 4.8 | 1476 |
| MiMo-V2.5-Pro | 1475 |
| GLM-5.1 | 1472 |
| Gemini 3 Flash Preview | 1471 |
| GLM-5.3 Flash | 1471 |
| ERNIE 5.1 | 1470 |
| GLM-5.3 | 1470 |
| GLM-5.2 | 1469 |
| DeepSeek-V4-Pro | 1468 |
| Opus 4.5 | 1466 |
| Claude Sonnet 5.5 | 1465 |
| MiMo-V2.6-Pro | 1465 |
| Sonnet 4.5 | 1465 |
| Sonnet 4.6 | 1464 |
| GPT-5.6 Sol | 1461 |
| DeepSeek V4.1 Flash | 1460 |
| Qwen3.7-Plus (source unspecified) | 1459 |