Text · Factuality
Arena · 50 models
| Rank | Model | Score |
|---|---|---|
| 1 | Gemini 4 Carbon (High) | 1,521.5854 |
| 2 | Claude Opus 5.5 (High) | 1,508.6769 |
| 3 | Claude Fable 5.1 (Max) | 1,499.6873 |
| 4 | Gemini 4 Argon (High) | 1,499.5393 |
| 5 | Muse Wonder (Max) | 1,494.3282 |
| 6 | Claude Opus 4.6 (High) | 1,492.6206 |
| 7 | Claude Opus 5 (Max) | 1,488.3899 |
| 8 | Claude Opus 4.6 | 1,487.3636 |
| 9 | GPT-5.5 (High) | 1,485.6947 |
| 10 | MiMo-V2.6-Pro | 1,484.5005 |
| 11 | GPT-5.4 (High) | 1,484.2553 |
| 12 | Claude Fable 5 (High) | 1,482.7252 |
| 13 | GPT-5.5 | 1,481.8294 |
| 14 | Gemini 3 Pro | 1,481.2424 |
| 15 | Qwen3.7-Max-Preview | 1,479.6415 |
| 16 | Muse Spark 1.3 (Max) | 1,479.0976 |
| 17 | Muse Spark 1.2 (xHigh) | 1,479.0311 |
| 18 | Claude Opus 5 (High) | 1,478.2464 |
| 19 | Claude Opus 4.7 (High) | 1,477.3836 |
| 20 | Gemini 3.5 Flash (High) | 1,477.1554 |
| 21 | GPT-5.6 Sol (xHigh) | 1,476.3987 |
| 22 | Gemini 3.7 Flash (High) | 1,475.7613 |
| 23 | Claude Sonnet 5.5 (xHigh) | 1,475.5673 |
| 24 | Claude Opus 4.7 | 1,475.5438 |
| 25 | GPT-5.4 | 1,474.8512 |
| 26 | Qwen3.5-Max-Preview | 1,474.5884 |
| 27 | Gemini 3.8 Flash (High) | 1,471.9997 |
| 28 | Gemini 3.6 Flash (High) | 1,471.8834 |
| 29 | Gemini 3.1 Pro Preview | 1,471.6811 |
| 30 | Kimi K3 (Max) | 1,471.5128 |
| 31 | Qwen3.8-Max | 1,471.1131 |
| 32 | Claude Opus 4.8 (High) | 1,469.8135 |
| 33 | DeepSeek-V4.1-Flash-20260910 (Max) | 1,468.9852 |
| 34 | GPT-6 Luna (Max) | 1,468.7055 |
| 35 | GPT-5.6 Terra (xHigh) | 1,468.6812 |
| 36 | Muse Spark | 1,467.6315 |
| 37 | Gemini 3 Flash | 1,467.499 |
| 38 | Gemini 3.5 Flash (Medium) | 1,467.4855 |
| 39 | GPT-6 Astra (Max) | 1,466.5224 |
| 40 | GLM-5.3 (Max) | 1,466.112 |
| 41 | GPT-6.1 Sol (Max) | 1,465.5567 |
| 42 | Grok 4.5 | 1,465.1935 |
| 43 | Claude Opus 4.8 | 1,464.7281 |
| 44 | MiMo-V2.5-Pro | 1,464.3257 |
| 45 | GLM-5.3-Flash | 1,463.7881 |
| 46 | GLM-5.2 (Max) | 1,462.5993 |
| 47 | Muse Spark 1.1 | 1,462.4391 |
| 48 | Gemini 2.5 Pro | 1,461.7427 |
| 49 | Claude Sonnet 4.6 | 1,460.4823 |
| 50 | GPT-5.6 Luna (xHigh) | 1,460.4697 |