Text · Factuality · Multi Turn
Arena · 50 models
| Rank | Model | Score |
|---|---|---|
| 1 | Gemini 4 Argon (High) | 1,524.8876 |
| 2 | Claude Opus 5.5 (High) | 1,509.4995 |
| 3 | Claude Opus 4.6 (High) | 1,507.6468 |
| 4 | Muse Wonder (Max) | 1,506.2068 |
| 5 | Claude Fable 5 (High) | 1,503.02 |
| 6 | Claude Opus 4.6 | 1,502.1629 |
| 7 | GPT-5.4 (High) | 1,499.9093 |
| 8 | Claude Opus 4.7 (High) | 1,497.9023 |
| 9 | Claude Opus 5 (Max) | 1,497.0234 |
| 10 | Claude Opus 4.7 | 1,495.9592 |
| 11 | Gemini 3.8 Flash (High) | 1,492.9413 |
| 12 | GPT-5.5 (High) | 1,492.5988 |
| 13 | Gemini 3 Pro | 1,492.3041 |
| 14 | Kimi K3 (Max) | 1,491.8829 |
| 15 | GPT-5.5 | 1,491.2113 |
| 16 | Claude Fable 5.1 (Max) | 1,490.9341 |
| 17 | Muse Spark 1.3 (Max) | 1,490.5609 |
| 18 | Muse Spark 1.2 (xHigh) | 1,490.3808 |
| 19 | Claude Opus 4.8 (High) | 1,490.0948 |
| 20 | Gemini 3.5 Flash (High) | 1,489.9025 |
| 21 | Qwen3.8-Max | 1,489.2756 |
| 22 | GPT-5.4 | 1,488.3842 |
| 23 | Claude Opus 5 (High) | 1,487.5397 |
| 24 | Qwen3.5-Max-Preview | 1,487.3353 |
| 25 | Gemini 3.7 Flash (High) | 1,484.8705 |
| 26 | Claude Opus 4.8 | 1,483.9767 |
| 27 | Gemini 3.1 Pro Preview | 1,482.9501 |
| 28 | Gemini 3.6 Flash (High) | 1,481.8923 |
| 29 | GPT-5.6 Sol (xHigh) | 1,481.7198 |
| 30 | GLM-5.3 (Max) | 1,481.1998 |
| 31 | MiMo-V2.5-Pro | 1,480.6189 |
| 32 | GPT-5.6 Terra (xHigh) | 1,480.2219 |
| 33 | Muse Spark 1.1 | 1,479.2158 |
| 34 | Claude Opus 4.5 (20251101) | 1,477.9144 |
| 35 | Muse Spark | 1,477.6192 |
| 36 | Gemini 3.5 Flash (Medium) | 1,476.9104 |
| 37 | GPT-6 Astra (Max) | 1,476.0225 |
| 38 | GLM-5.1 | 1,475.9008 |
| 39 | DeepSeek-V4-Pro | 1,475.8446 |
| 40 | Grok 4.5 | 1,475.5798 |
| 41 | Claude Opus 4.5 (High, 32K, 20251101) | 1,475.4519 |
| 42 | GLM-5.2 (Max) | 1,474.8979 |
| 43 | DeepSeek-V4.1-Flash-20260910 (Max) | 1,473.6836 |
| 44 | Claude Sonnet 5.5 (xHigh) | 1,472.5776 |
| 45 | Claude Sonnet 4.5 (20250929) | 1,471.9597 |
| 46 | Gemini 3 Flash | 1,471.5848 |
| 47 | MiMo-V2.6-Pro | 1,471.4913 |
| 48 | Claude Sonnet 4.6 | 1,470.0617 |
| 49 | GLM-5.3-Flash | 1,469.7268 |
| 50 | GPT-5.1 (High) | 1,469.049 |