WebDev · HTML
Arena · 50 models
| Rank | Model | Score |
|---|---|---|
| 1 | GPT-6.1 Sol (Max) | 1,795.8032 |
| 2 | GPT-6 Astra (Max) | 1,784.8782 |
| 3 | Gemini 4 Carbon (High) | 1,779.8253 |
| 4 | Claude Opus 5.5 (Max) | 1,753.389 |
| 5 | Claude Sonnet 5.5 (xHigh) | 1,738.6281 |
| 6 | Muse Wonder Full (Max) | 1,730.9552 |
| 7 | GPT-6.1 Terra (Max) | 1,718.763 |
| 8 | Kimi K3.1 Pro (Max) | 1,706.1363 |
| 9 | DeepSeek-V4.1-Flash-20261017 (Max) | 1,700.8664 |
| 10 | Claude Sonnet 5.5 (High) | 1,699.8566 |
| 11 | Claude Fable 5.1 (Max) | 1,682.8046 |
| 12 | GPT-6 Sol (Max) | 1,679.628 |
| 13 | Claude Opus 5 (Max) | 1,677.0826 |
| 14 | Muse Wonder (Max) | 1,669.637 |
| 15 | Gemini 4 Argon (High) | 1,667.0403 |
| 16 | Qwen3.8-Max (0902) | 1,657.3836 |
| 17 | Muse Spark 1.3 (Max) | 1,654.4242 |
| 18 | Claude Fable 5 (High) | 1,650.6759 |
| 19 | Claude Opus 5 (High) | 1,649.0753 |
| 20 | Kimi K3 (Max) | 1,640.9694 |
| 21 | MiMo-V2.6-Flash | 1,638.4337 |
| 22 | Grok 4.7 (xHigh) | 1,628.5726 |
| 23 | Qwen3.8-Max | 1,625.924 |
| 24 | MiMo-V2.6-Pro | 1,624.2985 |
| 25 | Hy4 preview | 1,620.0388 |
| 26 | Muse Spark 1.3 (xHigh) | 1,619.8695 |
| 27 | GPT-5.6 Sol (xHigh, Codex Harness) | 1,617.0472 |
| 28 | DeepSeek-V4.1-Flash-20260910 (Max) | 1,613.0479 |
| 29 | Gemini 3.8 Flash (High) | 1,612.4468 |
| 30 | Grok 4.6 (High) | 1,597.0297 |
| 31 | GLM-5.3 (Max) | 1,596.9038 |
| 32 | Qwen3.8-Flash-Next | 1,594.8998 |
| 33 | GPT-6 Luna (Max) | 1,594.8985 |
| 34 | Gemini 3.7 Flash (High) | 1,590.6633 |
| 35 | GLM-5.3-Flash | 1,577.1371 |
| 36 | Claude Haiku 5.5 (High) | 1,567.9554 |
| 37 | GLM-5.2 (Max) | 1,567.6147 |
| 38 | Grok 4.5 | 1,567.5525 |
| 39 | DeepSeek-V4-Pro (High, 20260813) | 1,565.4488 |
| 40 | Qwen3.8-27B | 1,565.0953 |
| 41 | Claude Opus 4.6 (High) | 1,558.6412 |
| 42 | DeepSeek-V4-Flash (High) | 1,557.5726 |
| 43 | Step 5 Preview (High) | 1,555.0615 |
| 44 | Claude Opus 4.7 | 1,554.3731 |
| 45 | Gemini 3.6 Flash (High) | 1,546.5416 |
| 46 | Claude Opus 4.6 | 1,546.2211 |
| 47 | Claude Opus 4.7 (High) | 1,546.0919 |
| 48 | Muse Spark 1.2 (xHigh) | 1,543.0411 |
| 49 | Claude Opus 4.8 (High) | 1,542.7204 |
| 50 | GPT-5.5 (xHigh, Codex Harness) | 1,542.6578 |