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: leaderboard.steel.dev. Status: saturation imminent. 19 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GLM-5V Turbo | 88.5 |
| 2 | GPT-4 | 30.8 |
Interactive version: theaggregate.ai/benchmark?slug=webvoyager · How the rankings work · Data refreshed daily, snapshot 2026-07-22.