WebVoyager: leaderboard
Real-world multimodal web-agent benchmark for completing open-ended tasks on live websites through screenshot observation and browser actions.
Metric: Success Rate (%). Source: github.com. Source: leaderboard.steel.dev. Saturation forecast: Around January 2027. 22 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GLM-5V Turbo | 88.5 | #166 |
| 2 | GPT-4 | 30.8 | #438 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=webvoyager · How It Works · Data refreshed daily, snapshot 2026-10-20.