Chatbot Arena (Image-to-WebDev): leaderboard
arena.ai Code Arena Image-to-WebDev leaderboard: models build a working website from an input image such as a screenshot or design mockup, and users vote between two anonymous results. A separate arena with its own vote pool rather than a WebDev category slice; Bradley-Terry arena score, higher is better. Coding-harness runs such as Codex-harness entries are ranked separately.
Metric: Arena Score. Source: arena.ai. Saturation forecast: Around November 2027. 64 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Opus 5.5 (Max) | 1749 | #3 (Claude Opus 5.5) |
| 2 | Claude Sonnet 5.5 (xHigh) | 1740 | #14 (Claude Sonnet 5.5) |
| 3 | GPT-6 Astra (Max) | 1731 | #6 (GPT-6 Astra) |
| 4 | Claude Fable 5.1 (Max) | 1720 | #10 (Claude Fable 5.1) |
| 5 | GPT-6.1 Sol (Max) | 1703 | #7 (GPT-6.1 Sol) |
| 6 | Claude Opus 5 (Max) | 1661 | #16 (Claude Opus 5) |
| 7 | GPT-6 Sol (Max) | 1661 | #19 (GPT-6 Sol) |
| 8 | Muse Spark 1.3 (Max) | 1642 | #31 (Muse Spark 1.3) |
| 9 | Qwen 3.8 Max (0902) | 1638 | #36 |
| 10 | Claude Fable 5 (High) | 1622 | #20 (Claude Fable 5) |
| 11 | Qwen 3.8 Max | 1614 | #34 |
| 12 | DeepSeek V4.1 Flash (Max) | 1609 | #37 (DeepSeek V4.1 Flash) |
| 13 | GPT-5.6 Sol (xHigh) | 1608 | #22 (GPT-5.6 Sol) |
| 14 | Gemini 3.7 Flash (High) | 1603 | #24 (Gemini 3.7 Flash) |
| 15 | Grok 4.6 (High) | 1601 | #29 (Grok 4.6) |
No result here: #9 Gemini 4 Argon.
Interactive version: theaggregate.ai/benchmark?slug=chatbot-arena-image-to-webdev · How It Works · Data refreshed daily, snapshot 2026-11-05.