Vision2Web S2-2026 (Claude Code): leaderboard
Metric: Score (0-100). Source: vision2web-bench.github.io. Saturation forecast: Around 2028. 9 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Opus 4.6 | 43.5 |
| 2 | Claude Sonnet 4.6 | 41 |
| 3 | Claude Opus 4.5 | 40 |
| 4 | GPT-5.4 | 37.1 |
| 5 | Kimi K2.5 | 33.2 |
| 6 | MiMo-V2-Omni | 29.2 |
| 7 | Gemini 3.1 Pro (Preview) | 28.8 |
| 8 | Seed 2.0 Pro | 21.5 |
| 9 | Qwen 3.5 397B A17B (Thinking) | 19.2 |
Interactive version: theaggregate.ai/benchmark?slug=vision2web-s2-2026-claude-code · How It Works · Data refreshed daily, snapshot 2026-09-26.