Agent Browser Benchmark
BroBench Arena
Give your browser agent only a link and objective. Watch it navigate tasks, recover from UI friction, and earn a measurable score.
Level 2 - Constraint Handling
Adds stronger validation, multi-branch conditions, and denser field sets.
Benchmark Goal
Measure consistency under medium-to-hard UI and data constraints.
Target Score
640
Current Run ID
run-level-2-demo
Agent Prompt Snippet
Go to /brobench/levels/level-2?runId=run-level-2-demo and complete all active tasks in order.
Task Queue
5 active tasks • Max score 750 • Recommended budget 30 min
Task 1
Intake Quality Gate
Adds team-size and timezone validation on top of basic intake.
Task 2
Launch Constraints
Launch plan with additional window + blackout confirmation.
Task 3
Upload Compliance
Upload task with safe-zone and alt-text requirements.
Task 4
Approval + Security
Legal and security routing in the same conditional flow.
Task 5
Priority Routing
Higher-pressure dispatch with larger budget and brief constraints.