WebDev Arena (HTML): leaderboard
Voters submit a prompt for a web app, two anonymous models build it, and both builds run in sandboxes the voter can click through before choosing one. This board is the HTML technology slice, covering builds delivered as HTML, CSS and JavaScript rather than as a React project. Votes are fitted with a Bradley-Terry model and higher is better.
Metric: Arena Score. Source: arena.ai. 141 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-6.1 Sol (Max) | 1797 | #7 (GPT-6.1 Sol) |
| 2 | GPT-6 Astra (Max) | 1784 | #6 (GPT-6 Astra) |
| 3 | Claude Opus 5.5 (Max) | 1761 | #3 (Claude Opus 5.5) |
| 4 | Claude Sonnet 5.5 (xHigh) | 1739 | #11 (Claude Sonnet 5.5) |
| 5 | Claude Sonnet 5.5 (High) | 1709 | #11 (Claude Sonnet 5.5) |
| 6 | GPT-6 Sol (Max) | 1686 | #14 (GPT-6 Sol) |
| 7 | Claude Fable 5.1 (Max) | 1686 | #9 (Claude Fable 5.1) |
| 8 | Claude Opus 5 (Max) | 1681 | #12 (Claude Opus 5) |
| 9 | Muse Spark 1.3 (Max) | 1657 | #24 (Muse Spark 1.3) |
| 10 | Claude Opus 5 (High) | 1653 | #12 (Claude Opus 5) |
| 11 | Claude Fable 5 (High) | 1651 | #16 (Claude Fable 5) |
| 12 | Qwen 3.8 Max (0902) | 1649 | #29 |
| 13 | Kimi K3 (Max) | 1646 | #30 (Kimi K3) |
| 14 | MiMo-V2.6-Flash | 1643 | #70 |
| 15 | Gemini 4 Argon (High) | 1642 | #8 (Gemini 4 Argon) |
Interactive version: theaggregate.ai/benchmark?slug=webdev-arena-html · How It Works · Data refreshed daily, snapshot 2026-10-20.