Browser automation
Web agents given one-line human requests, each needing one UI mechanic (52 distinct: sliders, native date and time fields, iframes, shadow DOM, hover and context menus, blocking dialogs, virtualised lists, drag and drop, typeahead, canvas controls, sign-in …); the server checks the state the agent submitted.
Browser automation
1 recorded configuration · 52 source tasks
First-time pass (score), tasks passed (final submission equals the target state), rejected submissions, steps, wall time. No judge.
Each task isolates one mechanic; long multi-application workflows are the WebBench suite itself.
One page per challenge served through a throw-away public tunnel to the vendor's hosted agent; one attempt per task, provider defaults, 300 s budget.
