Text · Style Control · Life & Physical & Social Science
Arena · 50 models
| Rank | Model | Score |
|---|---|---|
| 1 | Gemini 4 Argon (High) | 1,536.3095 |
| 2 | Gemini 4 Carbon (High) | 1,530.1969 |
| 3 | Claude Opus 4.6 (High) | 1,526.8875 |
| 4 | Claude Fable 5 (High) | 1,526.5527 |
| 5 | Claude Opus 4.7 (High) | 1,525.0926 |
| 6 | Kimi K3 (Max) | 1,523.7742 |
| 7 | Claude Fable 5.1 (Max) | 1,522.9507 |
| 8 | Muse Wonder (Max) | 1,519.9002 |
| 9 | Gemini 3.8 Flash (High) | 1,519.4363 |
| 10 | Claude Opus 4.6 | 1,518.6692 |
| 11 | Qwen3.8-Max | 1,515.3131 |
| 12 | Claude Opus 5.5 (High) | 1,515.1587 |
| 13 | Claude Opus 5 (Max) | 1,514.7284 |
| 14 | Claude Opus 4.7 | 1,513.7216 |
| 15 | Gemini 3.7 Flash (High) | 1,512.8953 |
| 16 | Muse Spark 1.3 (Max) | 1,511.7716 |
| 17 | Muse Spark 1.2 (xHigh) | 1,510.1007 |
| 18 | Gemini 3.1 Pro Preview | 1,509.9619 |
| 19 | Claude Opus 5 (High) | 1,509.8956 |
| 20 | GLM-5.3 (Max) | 1,507.2569 |
| 21 | Claude Opus 4.8 (High) | 1,504.0575 |
| 22 | Muse Spark 1.1 | 1,501.3094 |
| 23 | Claude Opus 4.8 | 1,500.2422 |
| 24 | Claude Sonnet 4.6 | 1,499.5754 |
| 25 | Claude Sonnet 5.5 (xHigh) | 1,498.7925 |
| 26 | MiMo-V2.6-Pro | 1,498.7901 |
| 27 | GPT-5.5 (High) | 1,497.9711 |
| 28 | Gemini 3 Pro | 1,497.4934 |
| 29 | GLM-5.2 (Max) | 1,497.3676 |
| 30 | GPT-5.5 | 1,496.4947 |
| 31 | Gemini 3.5 Flash (Medium) | 1,496.1706 |
| 32 | Muse Spark | 1,495.4869 |
| 33 | Gemini 3.6 Flash (High) | 1,493.5919 |
| 34 | GPT-5.5 Instant | 1,491.9749 |
| 35 | Claude Opus 4.5 (High, 32K, 20251101) | 1,491.4778 |
| 36 | GPT-6 Astra (Max) | 1,490.7008 |
| 37 | GPT-6.1 Sol (Max) | 1,490.6421 |
| 38 | DeepSeek-V4.1-Flash-20260910 (Max) | 1,490.4787 |
| 39 | GLM-5.3-Flash | 1,490.2522 |
| 40 | Qwen3.5-Max-Preview | 1,490.079 |
| 41 | Gemini 3.5 Flash (High) | 1,490.0092 |
| 42 | MiMo-V2.5-Pro | 1,489.9926 |
| 43 | GPT-5.6 Sol (xHigh) | 1,489.911 |
| 44 | Grok 4.20 Beta (Reasoning, 0309) | 1,489.2671 |
| 45 | Claude Sonnet 5 (High) | 1,488.1131 |
| 46 | GPT-5.4 (High) | 1,487.7862 |
| 47 | DeepSeek-V4-Pro (High, 20260813) | 1,487.7389 |
| 48 | GLM-5.1 | 1,487.5271 |
| 49 | Claude Opus 4.5 (20251101) | 1,487.1886 |
| 50 | Gemini 3 Flash | 1,486.7469 |