Text · Instruction Following
Arena · 50 models
| Rank | Model | Score |
|---|---|---|
| 1 | Gemini 4 Carbon (High) | 1,539.1879 |
| 2 | Claude Opus 5.5 (High) | 1,538.9173 |
| 3 | Gemini 4 Argon (High) | 1,532.5704 |
| 4 | Claude Opus 4.6 (High) | 1,520.8533 |
| 5 | Claude Fable 5.1 (Max) | 1,518.6833 |
| 6 | Claude Opus 5 (Max) | 1,518.0362 |
| 7 | Claude Opus 5 (High) | 1,515.3222 |
| 8 | Claude Opus 4.6 | 1,509.2018 |
| 9 | Claude Fable 5 (High) | 1,502.5171 |
| 10 | Claude Opus 4.7 (High) | 1,497.8677 |
| 11 | Muse Wonder (Max) | 1,493.6175 |
| 12 | Gemini 3.8 Flash (High) | 1,492.6746 |
| 13 | Claude Sonnet 5.5 (xHigh) | 1,491.8396 |
| 14 | MiMo-V2.6-Pro | 1,491.6718 |
| 15 | Claude Opus 4.7 | 1,488.4747 |
| 16 | Gemini 3.7 Flash (High) | 1,485.7854 |
| 17 | Kimi K3 (Max) | 1,485.2477 |
| 18 | GPT-5.6 Sol (xHigh) | 1,482.7621 |
| 19 | GLM-5.3 (Max) | 1,481.2641 |
| 20 | GLM-5.3-Flash | 1,480.6077 |
| 21 | Qwen3.8-Max | 1,480.4341 |
| 22 | GPT-5.5 (High) | 1,478.5634 |
| 23 | Claude Opus 4.5 (High, 32K, 20251101) | 1,478.0269 |
| 24 | Muse Spark 1.3 (Max) | 1,477.6078 |
| 25 | Claude Opus 4.8 (High) | 1,476.9736 |
| 26 | Claude Sonnet 4.6 | 1,475.7135 |
| 27 | MiMo-V2.5-Pro | 1,475.4406 |
| 28 | GPT-5.5 | 1,475.1328 |
| 29 | DeepSeek-V4.1-Flash-20260910 (Max) | 1,473.7945 |
| 30 | Claude Opus 4.5 (20251101) | 1,472.3706 |
| 31 | GPT-5.4 (High) | 1,469.3061 |
| 32 | GPT-6.1 Sol (Max) | 1,467.3614 |
| 33 | Gemini 3.5 Flash (High) | 1,467.1933 |
| 34 | Gemini 3.6 Flash (High) | 1,467.028 |
| 35 | Qwen3.5-Max-Preview | 1,466.813 |
| 36 | Gemini 3.1 Pro Preview | 1,466.0365 |
| 37 | GLM-5.2 (Max) | 1,465.6056 |
| 38 | Gemini 3.5 Flash (Medium) | 1,464.9186 |
| 39 | Muse Spark 1.2 (xHigh) | 1,464.8438 |
| 40 | Claude Opus 4.8 | 1,462.9957 |
| 41 | ERNIE 5.1 | 1,460.3263 |
| 42 | Qwen3.7-Max-Preview | 1,459.9896 |
| 43 | Claude Sonnet 4.5 (20250929) | 1,459.1552 |
| 44 | Claude Sonnet 4.5 (High, 32K, 20250929) | 1,458.0317 |
| 45 | Gemini 3 Pro | 1,457.8406 |
| 46 | Muse Spark 1.1 | 1,456.7262 |
| 47 | GPT-5.4 | 1,454.9351 |
| 48 | GPT-5.6 Terra (xHigh) | 1,454.5142 |
| 49 | GPT-6 Astra (Max) | 1,454.062 |
| 50 | Claude Sonnet 5 (High) | 1,452.6828 |