WebDev Arena (React): 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 React technology slice, covering builds delivered as React components rather than as plain HTML, CSS and JavaScript. Votes are fitted with a Bradley-Terry model and higher is better.
Metric: Arena Score. Source: arena.ai. 126 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Opus 5.5 (Max) | 1863 | #3 (Claude Opus 5.5) |
| 2 | Claude Sonnet 5.5 (xHigh) | 1824 | #11 (Claude Sonnet 5.5) |
| 3 | GPT-6 Astra (Max) | 1811 | #6 (GPT-6 Astra) |
| 4 | Claude Fable 5.1 (Max) | 1793 | #9 (Claude Fable 5.1) |
| 5 | GPT-6.1 Sol (Max) | 1758 | #7 (GPT-6.1 Sol) |
| 6 | Claude Sonnet 5.5 (High) | 1749 | #11 (Claude Sonnet 5.5) |
| 7 | Claude Opus 5 (Max) | 1714 | #12 (Claude Opus 5) |
| 8 | GPT-6 Sol (Max) | 1693 | #14 (GPT-6 Sol) |
| 9 | Qwen 3.8 Max (0902) | 1691 | #29 |
| 10 | Gemini 4 Argon (High) | 1690 | #8 (Gemini 4 Argon) |
| 11 | Qwen 3.8 Max | 1682 | #35 |
| 12 | Claude Opus 5 (High) | 1677 | #12 (Claude Opus 5) |
| 13 | Kimi K3 (Max) | 1669 | #30 (Kimi K3) |
| 14 | Muse Spark 1.3 (Max) | 1669 | #24 (Muse Spark 1.3) |
| 15 | Grok 4.7 (xHigh) | 1661 | #25 (Grok 4.7) |
Interactive version: theaggregate.ai/benchmark?slug=webdev-arena-react · How It Works · Data refreshed daily, snapshot 2026-10-20.