Browser automation
WebVoyager
End-to-end navigation and task completion on live websites; original release has 643 tasks across 15 sites.
This supplemental, unranked audit examined 10 archived attempts: 7 received DeepSeek reviews and 3 lacked usable captured images.
About WebVoyager
What it measures
Task success; supplemented with cost per success and elapsed time.
Scope & limitations
Website drift, blocked pages and judge configuration affect comparability; distinguish the dataset from its reference agent.
Evaluation environment
Browser agent with live-web access and recorded trajectories.