Text · Factuality · Hard Prompts
Arena · 50 models
| Rank | Model | Score |
|---|---|---|
| 1 | Gemini 4 Carbon (High) | 1,544.671 |
| 2 | Claude Opus 5.5 (High) | 1,537.2762 |
| 3 | Gemini 4 Argon (High) | 1,526.5921 |
| 4 | Claude Fable 5.1 (Max) | 1,524.3114 |
| 5 | Claude Opus 4.6 (High) | 1,522.2765 |
| 6 | Claude Opus 4.6 | 1,519.637 |
| 7 | Muse Wonder (Max) | 1,516.3637 |
| 8 | Claude Opus 5 (Max) | 1,515.2269 |
| 9 | GPT-5.5 (High) | 1,513.1526 |
| 10 | MiMo-V2.6-Pro | 1,512.5441 |
| 11 | GPT-5.5 | 1,510.8184 |
| 12 | GPT-5.4 (High) | 1,509.7355 |
| 13 | GPT-5.6 Sol (xHigh) | 1,509.1539 |
| 14 | Claude Fable 5 (High) | 1,508.1519 |
| 15 | Claude Opus 5 (High) | 1,506.0637 |
| 16 | Claude Sonnet 5.5 (xHigh) | 1,505.053 |
| 17 | Muse Spark 1.3 (Max) | 1,502.1106 |
| 18 | GPT-5.4 | 1,501.5466 |
| 19 | Claude Opus 4.7 (High) | 1,501.4462 |
| 20 | Muse Spark 1.2 (xHigh) | 1,500.7458 |
| 21 | Claude Opus 4.7 | 1,500.6483 |
| 22 | Qwen3.7-Max-Preview | 1,499.2231 |
| 23 | Claude Opus 4.8 (High) | 1,499.2124 |
| 24 | Kimi K3 (Max) | 1,499.1382 |
| 25 | Qwen3.5-Max-Preview | 1,499.0032 |
| 26 | GPT-6.1 Sol (Max) | 1,497.6975 |
| 27 | Gemini 3 Pro | 1,497.4149 |
| 28 | GPT-5.6 Terra (xHigh) | 1,497.3417 |
| 29 | GPT-6 Luna (Max) | 1,497.1429 |
| 30 | Gemini 3.7 Flash (High) | 1,496.938 |
| 31 | Gemini 3.5 Flash (High) | 1,496.4271 |
| 32 | DeepSeek-V4.1-Flash-20260910 (Max) | 1,495.9222 |
| 33 | GPT-6 Astra (Max) | 1,494.9112 |
| 34 | Qwen3.8-Max | 1,494.3828 |
| 35 | Gemini 3.8 Flash (High) | 1,493.3316 |
| 36 | MiMo-V2.5-Pro | 1,493.3169 |
| 37 | Claude Sonnet 4.6 | 1,492.7681 |
| 38 | Claude Opus 4.8 | 1,492.5423 |
| 39 | Claude Opus 4.5 (High, 32K, 20251101) | 1,492.1411 |
| 40 | Claude Opus 4.5 (20251101) | 1,491.7184 |
| 41 | Gemini 3.6 Flash (High) | 1,491.6479 |
| 42 | GLM-5.3-Flash | 1,491.4689 |
| 43 | Grok 4.5 | 1,491.0773 |
| 44 | GLM-5.3 (Max) | 1,490.7058 |
| 45 | Gemini 3.1 Pro Preview | 1,490.4085 |
| 46 | GPT-5.6 Luna (xHigh) | 1,488.6868 |
| 47 | Gemini 3.5 Flash (Medium) | 1,487.3713 |
| 48 | GLM-5.2 (Max) | 1,485.1437 |
| 49 | Muse Spark 1.1 | 1,483.8982 |
| 50 | GPT-5.1 (High) | 1,483.7034 |