Text · Factuality · Exclude Ties
Arena · 50 models
| Rank | Model | Score |
|---|---|---|
| 1 | Gemini 4 Carbon (High) | 1,547.6963 |
| 2 | Claude Opus 5.5 (High) | 1,526.6662 |
| 3 | Gemini 4 Argon (High) | 1,520.0847 |
| 4 | Claude Fable 5.1 (Max) | 1,517.6969 |
| 5 | Muse Wonder (Max) | 1,507.7335 |
| 6 | Claude Opus 4.6 (High) | 1,505.4846 |
| 7 | Claude Opus 5 (Max) | 1,502.3177 |
| 8 | Claude Opus 4.6 | 1,500.4516 |
| 9 | MiMo-V2.6-Pro | 1,497.7763 |
| 10 | Gemini 3 Pro | 1,493.7423 |
| 11 | GPT-5.5 (High) | 1,491.3628 |
| 12 | Claude Fable 5 (High) | 1,491.1424 |
| 13 | GPT-5.4 (High) | 1,490.3532 |
| 14 | Muse Spark 1.3 (Max) | 1,489.956 |
| 15 | Muse Spark 1.2 (xHigh) | 1,488.9418 |
| 16 | Claude Opus 5 (High) | 1,488.7778 |
| 17 | Qwen3.7-Max-Preview | 1,488.134 |
| 18 | GPT-5.5 | 1,487.3223 |
| 19 | Claude Opus 4.7 (High) | 1,486.5006 |
| 20 | Gemini 3.5 Flash (High) | 1,486.2026 |
| 21 | Qwen3.5-Max-Preview | 1,485.5823 |
| 22 | Gemini 3.7 Flash (High) | 1,485.293 |
| 23 | Claude Opus 4.7 | 1,484.2243 |
| 24 | Gemini 3.8 Flash (High) | 1,483.1421 |
| 25 | Claude Sonnet 5.5 (xHigh) | 1,482.6415 |
| 26 | Qwen3.8-Max | 1,480.5607 |
| 27 | GPT-5.6 Sol (xHigh) | 1,480.0485 |
| 28 | Gemini 3.6 Flash (High) | 1,479.6734 |
| 29 | Gemini 3.1 Pro Preview | 1,479.5127 |
| 30 | Kimi K3 (Max) | 1,478.977 |
| 31 | Gemini 3 Flash | 1,477.3272 |
| 32 | Muse Spark | 1,477.0451 |
| 33 | GPT-5.4 | 1,475.8986 |
| 34 | Gemini 3.5 Flash (Medium) | 1,475.5729 |
| 35 | Claude Opus 4.8 (High) | 1,474.3548 |
| 36 | DeepSeek-V4.1-Flash-20260910 (Max) | 1,474.2609 |
| 37 | GLM-5.3 (Max) | 1,473.1858 |
| 38 | Muse Spark 1.1 | 1,471.9496 |
| 39 | GPT-5.6 Terra (xHigh) | 1,470.3346 |
| 40 | GLM-5.3-Flash | 1,470.1379 |
| 41 | GLM-5.2 (Max) | 1,469.8252 |
| 42 | MiMo-V2.5-Pro | 1,469.0281 |
| 43 | Claude Opus 4.8 | 1,467.9077 |
| 44 | Grok 4.5 | 1,467.6205 |
| 45 | GPT-6 Astra (Max) | 1,466.6436 |
| 46 | GPT-6 Luna (Max) | 1,466.6431 |
| 47 | GPT-6.1 Sol (Max) | 1,466.4816 |
| 48 | Gemini 2.5 Pro | 1,466.3998 |
| 49 | Claude Sonnet 4.6 | 1,464.2823 |
| 50 | Claude Opus 4.5 (High, 32K, 20251101) | 1,462.736 |