Vision2Web S1-2026 (Claude Code) - Level 2 Interactive: leaderboard
Vision2Web Level 2: the agent builds an interactive multi-page frontend from 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 Claude Code 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 2028. 8 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Opus 4.5 | 54.9 | #152 |
| 2 | GPT-5 | 44 | #163 |
| 3 | Claude Sonnet 4.5 | 36.8 | #244 |
| 4 | Gemini 3 Flash (Preview) | 20.5 | #141 |
| 5 | Gemini 3 Pro (Preview) | 14 | #111 |
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-claude-code-level-2-interactive · How It Works · Data refreshed daily, snapshot 2026-11-12.