Text · Expert
Arena · 50 models
| Rank | Model | Score |
|---|---|---|
| 1 | Gemini 4 Carbon (High) | 1,596.3709 |
| 2 | Claude Opus 5 (High) | 1,552.9972 |
| 3 | Claude Opus 5 (Max) | 1,551.3281 |
| 4 | Gemini 4 Argon (High) | 1,548.9705 |
| 5 | Claude Opus 5.5 (High) | 1,547.7418 |
| 6 | Claude Fable 5.1 (Max) | 1,544.9062 |
| 7 | MiMo-V2.6-Pro | 1,542.9103 |
| 8 | Claude Opus 4.6 (High) | 1,542.8165 |
| 9 | Claude Opus 4.6 | 1,536.8914 |
| 10 | Claude Fable 5 (High) | 1,534.7478 |
| 11 | Claude Sonnet 5.5 (xHigh) | 1,527.2138 |
| 12 | Gemini 3.8 Flash (High) | 1,526.2404 |
| 13 | Kimi K3 (Max) | 1,519.8508 |
| 14 | Claude Opus 4.7 | 1,519.7391 |
| 15 | Claude Opus 4.7 (High) | 1,519.1661 |
| 16 | GLM-5.3 (Max) | 1,517.1908 |
| 17 | GPT-5.6 Sol (xHigh) | 1,515.7298 |
| 18 | Gemini 3.7 Flash (High) | 1,514.0169 |
| 19 | GLM-5.3-Flash | 1,513.5743 |
| 20 | Muse Spark 1.3 (Max) | 1,510.4867 |
| 21 | Qwen3.8-Max | 1,507.5386 |
| 22 | GPT-5.5 (High) | 1,507.2884 |
| 23 | GPT-5.4 (High) | 1,506.2501 |
| 24 | amazon-nova-experimental-chat (26-02-10) | 1,505.9483 |
| 25 | Muse Wonder (Max) | 1,505.6339 |
| 26 | GPT-5.5 | 1,503.3393 |
| 27 | Claude Opus 4.8 (High) | 1,503.17 |
| 28 | DeepSeek-V4.1-Flash-20260910 (Max) | 1,502.0179 |
| 29 | MiMo-V2.5-Pro | 1,500.9609 |
| 30 | Claude Sonnet 4.6 | 1,499.7936 |
| 31 | GPT-6.1 Sol (Max) | 1,499.2367 |
| 32 | MiMo-V2.6-Flash | 1,496.7879 |
| 33 | GPT-5.6 Terra (xHigh) | 1,495.1451 |
| 34 | Gemini 3.5 Flash (High) | 1,494.4622 |
| 35 | GPT-6 Astra (Max) | 1,493.2488 |
| 36 | Claude Opus 4.8 | 1,491.6342 |
| 37 | ERNIE 5.1 | 1,491.0392 |
| 38 | Kimi K2.6 | 1,490.9206 |
| 39 | Claude Sonnet 5 (High) | 1,490.0334 |
| 40 | Gemini 3.6 Flash (High) | 1,489.5401 |
| 41 | Qwen3.5-Max-Preview | 1,488.9271 |
| 42 | GLM-5.2 (Max) | 1,488.4734 |
| 43 | Qwen3.7-Max-Preview | 1,488.4458 |
| 44 | Claude Opus 4.5 (20251101) | 1,487.1276 |
| 45 | Gemini 3.5 Flash (Medium) | 1,484.8646 |
| 46 | Gemini 3.1 Pro Preview | 1,483.9222 |
| 47 | Claude Sonnet 4.5 (High, 32K, 20250929) | 1,482.3633 |
| 48 | GPT-5.4 | 1,481.7309 |
| 49 | Qwen3.8-27B | 1,481.5137 |
| 50 | Claude Opus 4.5 (High, 32K, 20251101) | 1,480.8421 |