Arena Code WebDev — HTML
Code
Arena Code WebDev rating for websites generated as HTML. Anonymous outputs are compared through blind pairwise user votes.
Top models (higher is better)
| Model | Score |
|---|---|
| GPT-6.1 Sol | 1794 |
| GPT-6 Astra | 1777 |
| Claude Opus 5.5 | 1746 |
| Claude Sonnet 5.5 | 1739 |
| Muse Wonder Full | 1727 |
| Kimi K3.1 Pro | 1702 |
| DeepSeek V4.1 Flash 1017 | 1688 |
| Muse Wonder | 1684 |
| GPT-6 Sol | 1684 |
| Claude Fable 5.1 | 1683 |
| Claude Opus 5 | 1681 |
| Muse Spark 1.3 | 1653 |
| Qwen3.8 Max (0902) | 1652 |
| Claude Fable 5 | 1650 |
| Kimi K3 | 1642 |
| Gemini 4 Argon | 1642 |
| MiMo-V2.6-Flash | 1639 |
| MiMo-V2.6-Pro | 1626 |
| Qwen3.8-Max | 1625 |
| Grok 4.7 | 1625 |
| Hy4 Preview | 1620 |
| GPT-5.6 Sol | 1616 |
| Gemini 3.8 Flash | 1615 |
| DeepSeek V4.1 Flash | 1613 |
| Qwen3.8-Flash-Next | 1598 |
| Grok 4.6 | 1597 |
| GPT-6 Luna | 1596 |
| GLM-5.3 | 1595 |
| Gemini 3.7 Flash | 1592 |
| GLM-5.3 Flash | 1577 |
| Qwen3.8 27B | 1569 |
| Grok 4.5 | 1567 |
| GLM-5.2 | 1567 |
| Claude Haiku 5.5 | 1566 |
| DeepSeek V4 Pro 0813 | 1565 |
| Opus 4.6 | 1559 |
| DeepSeek-V4-Flash | 1558 |
| Opus 4.7 | 1554 |
| Gemini 3.5 Flash | 1554 |
| Gemini 3.6 Flash | 1547 |