Text · Factuality · Writing & Literature & Language
Arena · 50 models
| Rank | Model | Score |
|---|---|---|
| 1 | Gemini 4 Carbon (High) | 1,521.5951 |
| 2 | Claude Opus 5.5 (High) | 1,513.2336 |
| 3 | Gemini 4 Argon (High) | 1,506.7576 |
| 4 | Claude Fable 5.1 (Max) | 1,500.8484 |
| 5 | Claude Fable 5 (High) | 1,489.1609 |
| 6 | Claude Opus 4.6 (High) | 1,488.751 |
| 7 | Muse Wonder (Max) | 1,485.2775 |
| 8 | Claude Opus 5 (Max) | 1,484.255 |
| 9 | Claude Opus 4.6 | 1,480.82 |
| 10 | Claude Opus 4.7 (High) | 1,480.1627 |
| 11 | Gemini 3.5 Flash (High) | 1,476.6973 |
| 12 | Gemini 3 Pro | 1,476.2114 |
| 13 | Gemini 3.7 Flash (High) | 1,475.7363 |
| 14 | Claude Opus 5 (High) | 1,475.0923 |
| 15 | Gemini 3.8 Flash (High) | 1,474.3796 |
| 16 | Claude Opus 4.7 | 1,471.9532 |
| 17 | Claude Sonnet 5.5 (xHigh) | 1,471.4881 |
| 18 | Qwen3.8-Max | 1,470.6459 |
| 19 | Gemini 3.1 Pro Preview | 1,470.5966 |
| 20 | GPT-5.5 (High) | 1,470.5276 |
| 21 | GPT-5.5 | 1,469.203 |
| 22 | GPT-5.6 Sol (xHigh) | 1,469.1291 |
| 23 | Qwen3.5-Max-Preview | 1,468.0825 |
| 24 | Kimi K3 (Max) | 1,466.7486 |
| 25 | Muse Spark 1.3 (Max) | 1,466.2857 |
| 26 | Claude Opus 4.8 (High) | 1,466.0372 |
| 27 | GPT-5.4 (High) | 1,464.1462 |
| 28 | Gemini 3.6 Flash (High) | 1,463.2419 |
| 29 | Gemini 3.5 Flash (Medium) | 1,463.2073 |
| 30 | Gemini 3 Flash | 1,462.7607 |
| 31 | GLM-5.3 (Max) | 1,462.6882 |
| 32 | Muse Spark | 1,462.3988 |
| 33 | GPT-5.4 | 1,459.4045 |
| 34 | GLM-5.2 (Max) | 1,458.9092 |
| 35 | MiMo-V2.6-Pro | 1,457.302 |
| 36 | Claude Opus 4.8 | 1,456.0327 |
| 37 | Grok 4.5 | 1,455.1043 |
| 38 | Claude Opus 4.5 (20251101) | 1,454.4876 |
| 39 | GPT-6.1 Sol (Max) | 1,454.284 |
| 40 | GPT-6 Astra (Max) | 1,453.9441 |
| 41 | DeepSeek-V4.1-Flash-20260910 (Max) | 1,453.6795 |
| 42 | Muse Spark 1.2 (xHigh) | 1,453.5068 |
| 43 | GLM-5.1 | 1,452.3079 |
| 44 | GLM-5.3-Flash | 1,452.2962 |
| 45 | MiMo-V2.5-Pro | 1,452.1435 |
| 46 | Claude Opus 4.5 (High, 32K, 20251101) | 1,451.7919 |
| 47 | Claude Sonnet 4.5 (20250929) | 1,450.7942 |
| 48 | Gemini 2.5 Pro | 1,450.0831 |
| 49 | Claude Sonnet 4.6 | 1,449.5897 |
| 50 | DeepSeek-V4-Pro | 1,449.0985 |