Vision2Web S4-2026 (Claude Code): 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 Claude Code agent framework; higher is better. Season S4-2026 (Oct to Dec 2026) uses Gemini-3.5-flash as the visual judge and GLM-5V-Turbo (Claude Code) as the GUI testing agent; scores compare only within a season.
Metric: Score (0-100). Source: vision2web-bench.github.io. Saturation forecast: Around February 2027. 6 models tracked. Updated 4 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Fable 5 | 82.3 | #32 |
| 2 | Claude Opus 5 | 80.2 | #26 |
| 3 | Kimi K3 | 79 | #61 |
| 4 | GLM-5.3 Flash | 77.8 | #136 |
| 5 | Claude Opus 4.8 | 76.1 | #64 |
| 6 | DeepSeek-V4-Flash-Vision-Exp | 67.6 | #131 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=vision2web-s4-2026-claude-code · How It Works · Data refreshed daily, snapshot 2026-11-20.