Vision2Web S1-2026 (OpenHands) - Level 3 Full-Stack: leaderboard
Vision2Web Level 3: the agent develops a full-stack web application from requirements and prototypes; the score is the mean of a VLM-judged visual score and a functional score from workflow-driven GUI tests, on a 0-100 scale under the OpenHands framework, higher is better (He et al., 2026). 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 October 2027. 8 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Opus 4.5 | 48 | #152 |
| 2 | GPT-5 | 34 | #163 |
| 3 | Claude Sonnet 4.5 | 19.8 | #244 |
| 4 | Gemini 3 Pro (Preview) | 17.2 | #111 |
| 5 | Gemini 3 Flash (Preview) | 12.5 | #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-level-3-full-stack · How It Works · Data refreshed daily, snapshot 2026-11-12.