Text · Style Control · Hard Prompts (English)
Arena · 50 models
| Rank | Model | Score |
|---|---|---|
| 1 | Gemini 4 Carbon (High) | 1,543.6893 |
| 2 | Gemini 4 Argon (High) | 1,542.8419 |
| 3 | Claude Opus 5.5 (High) | 1,537.9693 |
| 4 | Claude Opus 4.6 (High) | 1,535.0089 |
| 5 | Claude Fable 5 (High) | 1,531.2315 |
| 6 | Claude Opus 4.6 | 1,529.4997 |
| 7 | Claude Opus 4.7 (High) | 1,528.4372 |
| 8 | Muse Wonder (Max) | 1,527.3113 |
| 9 | Claude Fable 5.1 (Max) | 1,521.1385 |
| 10 | Claude Opus 4.7 | 1,520.2354 |
| 11 | Kimi K3 (Max) | 1,517.1258 |
| 12 | Claude Opus 4.8 (High) | 1,516.9894 |
| 13 | Muse Spark 1.3 (Max) | 1,515.1101 |
| 14 | Gemini 3.8 Flash (High) | 1,513.7371 |
| 15 | MiMo-V2.6-Pro | 1,513.4961 |
| 16 | Claude Opus 5 (High) | 1,513.4911 |
| 17 | GPT-6.1 Sol (Max) | 1,512.9217 |
| 18 | Claude Sonnet 5.5 (xHigh) | 1,512.9194 |
| 19 | Claude Opus 5 (Max) | 1,512.7746 |
| 20 | GLM-5.3 (Max) | 1,511.2597 |
| 21 | Muse Spark 1.2 (xHigh) | 1,510.5942 |
| 22 | Qwen3.8-Max | 1,510.0992 |
| 23 | GPT-5.6 Sol (xHigh) | 1,509.3371 |
| 24 | Muse Spark | 1,508.3771 |
| 25 | GPT-6 Astra (Max) | 1,507.0809 |
| 26 | Gemini 3.1 Pro Preview | 1,506.6718 |
| 27 | Claude Sonnet 4.6 | 1,506.1679 |
| 28 | Claude Opus 4.8 | 1,506.1547 |
| 29 | Muse Spark 1.1 | 1,505.3065 |
| 30 | DeepSeek-V4.1-Flash-20260910 (Max) | 1,504.2133 |
| 31 | Claude Opus 4.5 (High, 32K, 20251101) | 1,503.2128 |
| 32 | MiMo-V2.5-Pro | 1,500.2263 |
| 33 | Gemini 3.6 Flash (High) | 1,500.0117 |
| 34 | GPT-5.5 | 1,499.8518 |
| 35 | GPT-5.2 Chat (20260210) | 1,499.7416 |
| 36 | Gemini 3 Pro | 1,499.6714 |
| 37 | GLM-5.3-Flash | 1,499.517 |
| 38 | Gemini 3.7 Flash (High) | 1,499.3826 |
| 39 | GLM-5.1 | 1,499.3553 |
| 40 | Claude Opus 4.5 (20251101) | 1,499.1244 |
| 41 | GPT-5.5 (High) | 1,498.8537 |
| 42 | GLM-5.2 (Max) | 1,498.6565 |
| 43 | Claude Sonnet 4.5 (High, 32K, 20250929) | 1,494.6794 |
| 44 | Claude Sonnet 5 (High) | 1,493.9648 |
| 45 | Qwen3.5-Max-Preview | 1,493.792 |
| 46 | GPT-5.4 (High) | 1,493.059 |
| 47 | Grok 4.5 | 1,492.7707 |
| 48 | ERNIE 5.1 | 1,491.7127 |
| 49 | Gemini 3 Flash | 1,491.0142 |
| 50 | Gemini 3.5 Flash (Medium) | 1,490.9814 |