Text
Arena · 50 models
| Rank | Model | Score |
|---|---|---|
| 1 | Gemini 4 Carbon (High) | 1,540.0421 |
| 2 | Gemini 4 Argon (High) | 1,528.577 |
| 3 | Claude Opus 5.5 (High) | 1,515.7998 |
| 4 | Claude Fable 5.1 (Max) | 1,513.8339 |
| 5 | Claude Opus 5 (Max) | 1,507.9091 |
| 6 | Claude Opus 5 (High) | 1,504.0843 |
| 7 | Claude Opus 4.6 (High) | 1,501.7236 |
| 8 | Muse Wonder (Max) | 1,499.1666 |
| 9 | Gemini 3.8 Flash (High) | 1,498.4923 |
| 10 | Claude Opus 4.6 | 1,496.2496 |
| 11 | Claude Fable 5 (High) | 1,491.5611 |
| 12 | MiMo-V2.6-Pro | 1,491.3511 |
| 13 | Muse Spark 1.3 (Max) | 1,490.6256 |
| 14 | Claude Opus 4.7 (High) | 1,489.7196 |
| 15 | Gemini 3.7 Flash (High) | 1,489.1174 |
| 16 | Qwen3.8-Max | 1,483.2906 |
| 17 | Claude Opus 4.7 | 1,482.9868 |
| 18 | Muse Spark 1.2 (xHigh) | 1,482.6648 |
| 19 | Gemini 3.5 Flash (High) | 1,482.1753 |
| 20 | Gemini 3.1 Pro Preview | 1,480.1062 |
| 21 | Gemini 3.6 Flash (High) | 1,479.7907 |
| 22 | Gemini 3 Pro | 1,479.4014 |
| 23 | Muse Spark 1.1 | 1,478.2816 |
| 24 | Gemini 3.5 Flash (Medium) | 1,478.1611 |
| 25 | Kimi K3 (Max) | 1,475.6886 |
| 26 | Qwen3.7-Max-Preview | 1,474.6659 |
| 27 | Muse Spark | 1,474.0352 |
| 28 | GLM-5.3 (Max) | 1,473.7757 |
| 29 | GLM-5.3-Flash | 1,473.0372 |
| 30 | Claude Sonnet 5.5 (xHigh) | 1,472.8511 |
| 31 | GPT-5.5 (High) | 1,471.5687 |
| 32 | Qwen3.5-Max-Preview | 1,470.3945 |
| 33 | GLM-5.2 (Max) | 1,469.6434 |
| 34 | GPT-5.4 (High) | 1,469.0796 |
| 35 | ERNIE 5.1 | 1,467.7697 |
| 36 | GPT-5.5 | 1,466.752 |
| 37 | Gemini 3 Flash | 1,465.6661 |
| 38 | DeepSeek-V4.1-Flash-20260910 (Max) | 1,464.507 |
| 39 | MiMo-V2.5-Pro | 1,464.2246 |
| 40 | GLM-5.1 | 1,462.8156 |
| 41 | Claude Opus 4.8 (High) | 1,461.2951 |
| 42 | Claude Sonnet 4.6 | 1,457.7072 |
| 43 | Gemini 2.5 Pro | 1,457.701 |
| 44 | GPT-5.6 Sol (xHigh) | 1,457.2397 |
| 45 | Kimi K2.6 | 1,455.557 |
| 46 | Qwen3.7-Plus | 1,454.5577 |
| 47 | Claude Opus 4.8 | 1,454.0343 |
| 48 | GPT-5.4 | 1,452.4698 |
| 49 | MiMo-V2.6-Flash | 1,451.2184 |
| 50 | DeepSeek-V4-Pro | 1,451.1279 |