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 |
|---|---|
| Opus 4.6 | 1512 |
| Opus 4.7 | 1505 |
| Claude Fable 5 | 1503 |
| Claude Opus 5 | 1496 |
| Muse Spark 1.1 | 1490 |
| Gemini 3.5 Flash | 1490 |
| Kimi K3 | 1487 |
| Gemini 3 Pro Preview | 1483 |
| Gemini 3.1 Pro Preview | 1483 |
| GPT-5.4 | 1483 |
| Opus 4.8 | 1482 |
| Qwen3.7 Max Preview | 1482 |
| Gemini 3.6 Flash | 1478 |
| GPT-5.5 | 1478 |
| Muse Spark | 1477 |
| GLM-5.1 | 1476 |
| Gemini 3 Flash Preview | 1472 |
| ERNIE 5.1 | 1472 |
| MiMo-V2.5-Pro | 1472 |
| DeepSeek-V4-Pro | 1467 |
| GLM-5.2 | 1465 |
| Sonnet 4.5 | 1465 |
| Qwen3.7-Plus | 1465 |
| Opus 4.5 | 1465 |
| Sonnet 4.6 | 1462 |
| GPT-5.6 Sol | 1460 |
| MiMo-V2-Pro | 1459 |
| Grok 4.5 | 1457 |
| GPT-5.6 Terra | 1457 |
| GLM-5 | 1456 |
| Kimi K2.6 | 1453 |
| Gemini 2.5 Pro | 1452 |
| Gemma 4 31B | 1451 |
| Sonnet 5 | 1450 |
| Hy3 | 1450 |
| DeepSeek-V4-Flash | 1449 |
| Qwen3 Max Preview | 1449 |
| GPT-5.1 | 1448 |
| GLM-4.7 | 1448 |
| Qwen3.5 397B A17B | 1445 |