Design preview. All scores below are synthetic. Example agents do not represent measured providers.
Consumer benchmark
502 real web tasks. 363 shopping carts. 139 public information tasks.
Illustrative comparison
Example agent A
80.1%
Result details
80.1%
Example agent B
69.9%
Result details
69.9%
Example agent C
56.6%
Result details
56.6%
Method & data
A successful task needs the requested endpoint. An add button alone does not prove a cart.
Scoring and run conditions
We recalculated historical V8 results on the retained V9 task IDs. Fleet Farm has a corrected URL and task text. These are historical projections, not new V9 executions.
Models, dates, browsers, solver rules, and evidence review differ. We selected Browser Use's best retained run. Policy holds and browser permission failures do not establish website blocks.
Bars show successful endpoint reports divided by all 502 planned tasks in this view. Missing and unstarted tasks never become website failures.