Text · Style Control · Software & It Services
Arena · 50 models
| Rank | Model | Score |
|---|---|---|
| 1 | Gemini 4 Carbon (High) | 1,552.3163 |
| 2 | Gemini 4 Argon (High) | 1,550.2789 |
| 3 | Claude Opus 4.7 (High) | 1,540.4759 |
| 4 | Claude Fable 5 (High) | 1,538.0366 |
| 5 | Claude Opus 5.5 (High) | 1,537.762 |
| 6 | Claude Opus 4.6 (High) | 1,537.3005 |
| 7 | Muse Wonder (Max) | 1,535.1263 |
| 8 | Claude Opus 4.6 | 1,534.5733 |
| 9 | Muse Spark 1.2 (xHigh) | 1,533.9402 |
| 10 | GPT-6.1 Sol (Max) | 1,530.3576 |
| 11 | Claude Opus 4.7 | 1,530.3562 |
| 12 | Claude Fable 5.1 (Max) | 1,529.4359 |
| 13 | MiMo-V2.6-Pro | 1,528.371 |
| 14 | Muse Spark 1.3 (Max) | 1,525.3794 |
| 15 | Muse Spark 1.1 | 1,525.224 |
| 16 | Claude Opus 5 (High) | 1,524.0421 |
| 17 | Kimi K3 (Max) | 1,523.4969 |
| 18 | Claude Opus 4.8 (High) | 1,523.3676 |
| 19 | Muse Spark | 1,522.4548 |
| 20 | GPT-6 Astra (Max) | 1,522.1546 |
| 21 | GPT-5.6 Sol (xHigh) | 1,521.955 |
| 22 | Claude Sonnet 5.5 (xHigh) | 1,518.5387 |
| 23 | Gemini 3.8 Flash (High) | 1,518.0119 |
| 24 | Claude Opus 5 (Max) | 1,517.8571 |
| 25 | Claude Opus 4.8 | 1,517.1837 |
| 26 | GLM-5.3-Flash | 1,515.4807 |
| 27 | DeepSeek-V4.1-Flash-20260910 (Max) | 1,514.2331 |
| 28 | Claude Sonnet 4.6 | 1,514.1262 |
| 29 | GLM-5.3 (Max) | 1,513.0227 |
| 30 | Gemini 3.1 Pro Preview | 1,512.6215 |
| 31 | Qwen3.8-Max | 1,512.2057 |
| 32 | Claude Opus 4.5 (High, 32K, 20251101) | 1,511.8456 |
| 33 | Gemini 3.7 Flash (High) | 1,511.7525 |
| 34 | GPT-5.5 (High) | 1,510.6938 |
| 35 | Gemini 3.6 Flash (High) | 1,510.4654 |
| 36 | GPT-5.2 Chat (20260210) | 1,509.5129 |
| 37 | Gemini 3 Pro | 1,509.3009 |
| 38 | Qwen3.7-Max-Preview | 1,509.167 |
| 39 | MiMo-V2.5-Pro | 1,508.8522 |
| 40 | ERNIE 5.1 | 1,507.5872 |
| 41 | GPT-5.6 Terra (xHigh) | 1,507.2853 |
| 42 | Claude Opus 4.5 (20251101) | 1,507.2822 |
| 43 | GLM-5.2 (Max) | 1,507.0819 |
| 44 | GPT-5.4 (High) | 1,506.5644 |
| 45 | GPT-5.5 | 1,505.7187 |
| 46 | Claude Sonnet 5 (High) | 1,505.1389 |
| 47 | GPT-6 Sol (Max) | 1,504.2185 |
| 48 | Grok 4.20 Beta 1 | 1,503.4049 |
| 49 | Kimi K2.6 | 1,503.2723 |
| 50 | Grok 4.20 Beta (Reasoning, 0309) | 1,502.725 |