Text · Factuality · Longer Query
Arena · 50 models
| Rank | Model | Score |
|---|---|---|
| 1 | Gemini 4 Carbon (High) | 1,538.9284 |
| 2 | Gemini 4 Argon (High) | 1,531.9889 |
| 3 | Claude Opus 5.5 (High) | 1,529.4837 |
| 4 | Claude Fable 5.1 (Max) | 1,518.7263 |
| 5 | Claude Opus 4.6 (High) | 1,512.9099 |
| 6 | Claude Opus 4.6 | 1,510.0541 |
| 7 | Claude Opus 5 (Max) | 1,506.7905 |
| 8 | Claude Fable 5 (High) | 1,504.5552 |
| 9 | Muse Wonder (Max) | 1,504.4414 |
| 10 | MiMo-V2.6-Pro | 1,502.4077 |
| 11 | GPT-5.5 (High) | 1,500.4176 |
| 12 | Claude Opus 5 (High) | 1,499.7098 |
| 13 | Claude Opus 4.7 (High) | 1,499.6172 |
| 14 | Claude Sonnet 5.5 (xHigh) | 1,498.7254 |
| 15 | GPT-5.5 | 1,498.0313 |
| 16 | Gemini 3.8 Flash (High) | 1,495.4141 |
| 17 | Qwen3.7-Max-Preview | 1,495.1444 |
| 18 | GPT-5.6 Sol (xHigh) | 1,494.5721 |
| 19 | Claude Opus 4.7 | 1,494.2579 |
| 20 | Kimi K3 (Max) | 1,493.9895 |
| 21 | Gemini 3.7 Flash (High) | 1,491.9528 |
| 22 | Claude Opus 4.8 (High) | 1,491.9428 |
| 23 | Qwen3.5-Max-Preview | 1,491.4024 |
| 24 | GPT-5.4 (High) | 1,491.3422 |
| 25 | Claude Opus 4.5 (20251101) | 1,490.9688 |
| 26 | Muse Spark 1.3 (Max) | 1,490.8474 |
| 27 | Gemini 3.5 Flash (High) | 1,490.32 |
| 28 | Claude Opus 4.5 (High, 32K, 20251101) | 1,488.8773 |
| 29 | Claude Opus 4.8 | 1,488.316 |
| 30 | Qwen3.8-Max | 1,487.7374 |
| 31 | Claude Sonnet 4.5 (High, 32K, 20250929) | 1,487.2254 |
| 32 | GPT-5.4 | 1,487.1053 |
| 33 | Claude Sonnet 4.5 (20250929) | 1,486.3203 |
| 34 | Muse Spark 1.2 (xHigh) | 1,486.1978 |
| 35 | MiMo-V2.5-Pro | 1,485.9803 |
| 36 | Gemini 3 Pro | 1,485.7868 |
| 37 | Claude Sonnet 4.6 | 1,485.0882 |
| 38 | DeepSeek-V4.1-Flash-20260910 (Max) | 1,484.4043 |
| 39 | GLM-5.2 (Max) | 1,484.2259 |
| 40 | GLM-5.3 (Max) | 1,483.9447 |
| 41 | Gemini 3.1 Pro Preview | 1,483.741 |
| 42 | GPT-6.1 Sol (Max) | 1,483.2906 |
| 43 | GLM-5.3-Flash | 1,482.9208 |
| 44 | Grok 4.5 | 1,481.8865 |
| 45 | GPT-6 Astra (Max) | 1,481.6912 |
| 46 | Gemini 3.6 Flash (High) | 1,480.8915 |
| 47 | Gemini 3.5 Flash (Medium) | 1,479.0412 |
| 48 | GPT-5.6 Terra (xHigh) | 1,476.7366 |
| 49 | Kimi K2.6 | 1,476.3795 |
| 50 | GLM-5.1 | 1,476.2468 |