Vision2Web S1-2026 (Claude Code) - Level 3 Full-Stack: leaderboard
Metric: Score (0-100). Source: vision2web-bench.github.io. Saturation forecast: Around July 2027. 8 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Opus 4.5 | 43.7 |
| 2 | Claude Sonnet 4.5 | 20.7 |
| 3 | GPT-5 | 16.5 |
| 4 | Gemini 3 Pro (Preview) | 9.3 |
| 5 | Gemini 3 Flash (Preview) | 3.5 |
| 6 | Qwen 3 VL 8B | 0 |
Interactive version: theaggregate.ai/benchmark?slug=vision2web-s1-2026-claude-code-level-3-full-stack · How It Works · Data refreshed daily, snapshot 2026-09-26.