Vision2Web S1-2026 (OpenHands): leaderboard
Vision2Web (He et al., 2026) has coding agents build working websites from UI prototype images, requirements and assets: static responsive pages, interactive multi-page frontends and full-stack applications (193 tasks). This board is the overall score, the mean of the three level scores on a 0-100 scale, under the OpenHands agent framework; higher is better. Season S1-2026 (Jan to Mar 2026) uses Gemini-3-pro-preview as the visual judge and GLM-4.6V as the GUI testing agent; scores compare only within a season.
Metric: Score (0-100). Source: vision2web-bench.github.io. Saturation forecast: Around May 2027. 8 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Opus 4.5 | 52.7 | #152 |
| 2 | GPT-5 | 40.5 | #163 |
| 3 | Claude Sonnet 4.5 | 37.5 | #244 |
| 4 | Gemini 3 Pro (Preview) | 36.1 | #111 |
| 5 | Gemini 3 Flash (Preview) | 30.8 | #141 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=vision2web-s1-2026-openhands · How It Works · Data refreshed daily, snapshot 2026-11-12.