Text · Factuality · Hard Prompts (English)
Arena · 50 models
| Rank | Model | Score |
|---|---|---|
| 1 | Claude Opus 5.5 (High) | 1,549.1006 |
| 2 | Gemini 4 Carbon (High) | 1,544.5752 |
| 3 | Gemini 4 Argon (High) | 1,535.9274 |
| 4 | Claude Opus 4.6 (High) | 1,533.4883 |
| 5 | Claude Fable 5.1 (Max) | 1,532.0243 |
| 6 | Claude Opus 4.6 | 1,530.0235 |
| 7 | Muse Wonder (Max) | 1,529.1779 |
| 8 | Claude Opus 5 (Max) | 1,525.9131 |
| 9 | MiMo-V2.6-Pro | 1,522.6883 |
| 10 | Claude Sonnet 5.5 (xHigh) | 1,521.3585 |
| 11 | Claude Fable 5 (High) | 1,520.1939 |
| 12 | Claude Opus 5 (High) | 1,518.3737 |
| 13 | Qwen3.8-Max | 1,515.3144 |
| 14 | GPT-5.5 | 1,514.973 |
| 15 | GPT-5.5 (High) | 1,513.121 |
| 16 | Muse Spark 1.3 (Max) | 1,513.1056 |
| 17 | Kimi K3 (Max) | 1,512.9322 |
| 18 | GPT-5.4 (High) | 1,511.6147 |
| 19 | Muse Spark 1.2 (xHigh) | 1,511.4223 |
| 20 | Claude Opus 4.7 (High) | 1,511.2544 |
| 21 | GPT-6.1 Sol (Max) | 1,510.115 |
| 22 | Claude Opus 4.8 (High) | 1,510.0125 |
| 23 | MiMo-V2.5-Pro | 1,509.315 |
| 24 | Claude Opus 4.7 | 1,509.1007 |
| 25 | Qwen3.5-Max-Preview | 1,508.9363 |
| 26 | GPT-5.6 Sol (xHigh) | 1,508.3273 |
| 27 | Claude Sonnet 4.6 | 1,507.5317 |
| 28 | DeepSeek-V4.1-Flash-20260910 (Max) | 1,506.4824 |
| 29 | GLM-5.3 (Max) | 1,506.0607 |
| 30 | GPT-5.4 | 1,503.4066 |
| 31 | MiMo-V2.6-Flash | 1,503.2102 |
| 32 | Claude Opus 4.5 (20251101) | 1,502.7341 |
| 33 | Gemini 3.8 Flash (High) | 1,501.83 |
| 34 | Gemini 3.7 Flash (High) | 1,501.7137 |
| 35 | GPT-5.6 Terra (xHigh) | 1,500.8676 |
| 36 | Gemini 3.5 Flash (High) | 1,500.7595 |
| 37 | GPT-6 Astra (Max) | 1,500.5942 |
| 38 | Claude Opus 4.8 | 1,500.4359 |
| 39 | Gemini 3.6 Flash (High) | 1,500.3797 |
| 40 | GLM-5.3-Flash | 1,500.239 |
| 41 | Claude Opus 4.5 (High, 32K, 20251101) | 1,499.9094 |
| 42 | Gemini 3 Pro | 1,498.7878 |
| 43 | GPT-5.6 Luna (xHigh) | 1,498.1779 |
| 44 | GLM-5.1 | 1,497.9631 |
| 45 | Claude Sonnet 4.5 (High, 32K, 20250929) | 1,497.8884 |
| 46 | Grok 4.5 | 1,497.1012 |
| 47 | GLM-5.2 (Max) | 1,496.2514 |
| 48 | Gemini 3.1 Pro Preview | 1,495.7637 |
| 49 | Claude Sonnet 4.5 (20250929) | 1,495.4375 |
| 50 | MiMo-V2-Pro | 1,494.4353 |