Arena Code WebDev — Simulations
Code
Arena Code WebDev rating for interactive simulations. Anonymous generated simulations are compared through blind pairwise user votes.
Top models (higher is better)
| Model | Score |
|---|---|
| Claude Opus 5.5 | 1922 |
| GPT-6 Astra | 1883 |
| Claude Sonnet 5.5 | 1841 |
| GPT-6.1 Sol | 1829 |
| Claude Fable 5.1 | 1818 |
| Muse Wonder Full | 1782 |
| Claude Opus 5 | 1751 |
| Kimi K3.1 Pro | 1745 |
| Gemini 4 Argon | 1742 |
| GPT-6 Sol | 1741 |
| Hy4 Preview | 1703 |
| DeepSeek V4.1 Flash 1017 | 1701 |
| Qwen3.8 Max (0902) | 1698 |
| MiMo-V2.6-Pro | 1691 |
| Grok 4.7 | 1690 |
| Muse Spark 1.3 | 1690 |
| Muse Wonder | 1688 |
| Kimi K3 | 1684 |
| Qwen3.8-Max | 1676 |
| Claude Fable 5 | 1673 |
| MiMo-V2.6-Flash | 1660 |
| GLM-5.3 | 1656 |
| Grok 4.6 | 1648 |
| Qwen3.8-Flash-Next | 1644 |
| GLM-5.2 | 1635 |
| DeepSeek V4.1 Flash | 1633 |
| Claude Haiku 5.5 | 1632 |
| GPT-5.6 Sol | 1626 |
| GLM-5.3 Flash | 1620 |
| DeepSeek V4 Pro 0813 | 1619 |
| Gemini 3.7 Flash | 1618 |
| GPT-6 Luna | 1610 |
| Gemini 3.8 Flash | 1607 |
| Qwen3.8 27B | 1598 |
| MiniMax M3.1 Flash | 1590 |
| Opus 4.8 | 1576 |
| Grok 4.5 | 1575 |
| Opus 4.7 | 1573 |
| DeepSeek-V4-Flash | 1568 |
| Opus 4.6 | 1563 |