Vision · Style Control · Homework
Arena · 50 models
| Rank | Model | Score |
|---|---|---|
| 1 | GPT-6.1 Sol (Max) | 1,358.3144 |
| 2 | Claude Fable 5 (High) | 1,351.8626 |
| 3 | Claude Opus 5.5 (High) | 1,351.4877 |
| 4 | GPT-6 Astra (Max) | 1,342.3681 |
| 5 | Gemini 3.8 Flash (High) | 1,338.4024 |
| 6 | GPT-5.5 (High) | 1,335.0524 |
| 7 | Claude Fable 5.1 (Max) | 1,334.3547 |
| 8 | Qwen3.8-Max | 1,334.2886 |
| 9 | Claude Opus 4.8 (High) | 1,331.8262 |
| 10 | Claude Opus 4.7 (High) | 1,330.9046 |
| 11 | GPT-5.5 | 1,329.9829 |
| 12 | GPT-5.4 (High) | 1,329.8132 |
| 13 | Claude Opus 4.7 | 1,325.8156 |
| 14 | Claude Sonnet 5.5 (xHigh) | 1,325.5434 |
| 15 | Claude Opus 4.6 (High) | 1,324.8731 |
| 16 | Grok 4.7 (xHigh) | 1,323.6326 |
| 17 | Claude Opus 5 (High) | 1,323.2579 |
| 18 | GPT-5.6 Terra (xHigh) | 1,321.0882 |
| 19 | Claude Opus 4.8 | 1,320.8187 |
| 20 | Gemini 3.5 Flash (Medium) | 1,316.2491 |
| 21 | GPT-5.6 Sol (xHigh) | 1,313.8757 |
| 22 | Claude Opus 4.6 | 1,312.2179 |
| 23 | Gemini 3.1 Pro Preview | 1,310.2359 |
| 24 | Gemini 3.7 Flash (High) | 1,308.9002 |
| 25 | Gemini 3 Pro | 1,308.5314 |
| 26 | Gemini 3 Flash | 1,308.2082 |
| 27 | DeepSeek-V4.1-Flash-20260910 (Max) | 1,307.4987 |
| 28 | GLM-5.3-Flash | 1,306.4453 |
| 29 | GPT-6 Sol (Max) | 1,306.1805 |
| 30 | Gemini 3.5 Flash (High) | 1,305.7489 |
| 31 | Claude Sonnet 5 (High) | 1,304.5725 |
| 32 | Gemma 4 31B | 1,303.8158 |
| 33 | Gemini 3.6 Flash (High) | 1,303.7486 |
| 34 | GPT-5.4 | 1,303.1815 |
| 35 | Kimi K2.6 | 1,302.2991 |
| 36 | Claude Sonnet 4.6 | 1,302.2958 |
| 37 | Grok 4.5 | 1,299.4681 |
| 38 | Muse Spark | 1,298.5206 |
| 39 | Muse Spark 1.3 (xHigh) | 1,297.0551 |
| 40 | Grok 4.6 (High) | 1,296.9951 |
| 41 | Gemini 3 Flash (Minimal) | 1,296.6975 |
| 42 | Muse Spark 1.3 (Max) | 1,293.7375 |
| 43 | GPT-5.2 Chat (20260210) | 1,293.3687 |
| 44 | GPT-5.4 mini (High) | 1,290.8696 |
| 45 | Gemini 3.5 Flash-Lite | 1,290.3199 |
| 46 | Kimi K2.5 (Thinking) | 1,290.0079 |
| 47 | GPT-5.6 Luna (xHigh) | 1,289.8025 |
| 48 | Qwen3.7-Plus | 1,288.6792 |
| 49 | Muse Spark 1.1 | 1,287.7657 |
| 50 | Qwen3.5-397B-A17B | 1,287.2396 |