Text · Factuality · Creative Writing
Arena · 50 models
| Rank | Model | Score |
|---|---|---|
| 1 | Claude Opus 5.5 (High) | 1,509.3903 |
| 2 | Gemini 4 Argon (High) | 1,504.9417 |
| 3 | Gemini 4 Carbon (High) | 1,500.8657 |
| 4 | Claude Fable 5.1 (Max) | 1,495.2088 |
| 5 | Claude Opus 4.6 (High) | 1,490.3844 |
| 6 | Muse Wonder (Max) | 1,480.42 |
| 7 | Gemini 3 Pro | 1,478.7568 |
| 8 | Claude Opus 5 (Max) | 1,478.3028 |
| 9 | Claude Fable 5 (High) | 1,477.7146 |
| 10 | Claude Opus 4.7 (High) | 1,472.7427 |
| 11 | Gemini 3.7 Flash (High) | 1,471.5853 |
| 12 | Gemini 3.8 Flash (High) | 1,469.3496 |
| 13 | Claude Opus 5 (High) | 1,468.7682 |
| 14 | Claude Opus 4.6 | 1,468.5358 |
| 15 | Claude Opus 4.7 | 1,467.5873 |
| 16 | Gemini 3.5 Flash (High) | 1,467.0642 |
| 17 | Qwen3.8-Max | 1,466.229 |
| 18 | Gemini 3.1 Pro Preview | 1,465.5152 |
| 19 | Gemini 3 Flash | 1,461.9443 |
| 20 | Claude Sonnet 5.5 (xHigh) | 1,460.9625 |
| 21 | Gemini 3.5 Flash (Medium) | 1,460.8852 |
| 22 | Muse Spark 1.3 (Max) | 1,459.9251 |
| 23 | Qwen3.5-Max-Preview | 1,459.9176 |
| 24 | MiMo-V2.6-Pro | 1,457.4902 |
| 25 | GPT-5.5 (High) | 1,456.5245 |
| 26 | Gemini 3.6 Flash (High) | 1,455.9754 |
| 27 | GLM-5.3 (Max) | 1,455.5956 |
| 28 | GPT-5.5 | 1,454.7828 |
| 29 | Claude Opus 4.8 (High) | 1,454.7813 |
| 30 | GPT-5.6 Sol (xHigh) | 1,453.7274 |
| 31 | GLM-5.2 (Max) | 1,451.5432 |
| 32 | Kimi K3 (Max) | 1,451.4193 |
| 33 | Claude Opus 4.8 | 1,448.5168 |
| 34 | Claude Opus 4.5 (20251101) | 1,448.4715 |
| 35 | GPT-5.4 (High) | 1,447.9948 |
| 36 | Gemini 2.5 Pro | 1,447.9944 |
| 37 | GLM-5.1 | 1,447.9567 |
| 38 | Grok 4.5 | 1,447.5013 |
| 39 | Claude Sonnet 4.5 (20250929) | 1,446.4688 |
| 40 | DeepSeek-V4-Pro | 1,445.8136 |
| 41 | Claude Opus 4.5 (High, 32K, 20251101) | 1,445.4979 |
| 42 | ERNIE 5.1 | 1,443.301 |
| 43 | GLM-5 | 1,442.8215 |
| 44 | Grok 4.20 Multi-Agent Beta (0309) | 1,442.4674 |
| 45 | Claude Sonnet 4.6 | 1,442.173 |
| 46 | Grok 4.20 Beta 1 | 1,441.892 |
| 47 | MiMo-V2.5-Pro | 1,441.5375 |
| 48 | DeepSeek-V4-Pro Preview (High) | 1,439.8107 |
| 49 | GPT-5.4 | 1,439.0706 |
| 50 | DeepSeek-V4.1-Flash-20260910 (Max) | 1,438.44 |