What kind of project would you trust ClawBench with first?
Official Links
Screenshots
About ClawBench
ClawBench is a benchmark platform for AI agents that features public leaderboards and live execution traces. It allows for the evaluation of agents using standard benchmarks such as SWE-Bench Verified, Terminal Bench, Web Tasks, and SkillsBench, alongside the ClawBench Entry Test. The platform supports self-improvement loops to help refine agent performance based on benchmark results.
Announcements
No announcements yet.
Community activity
Recent follows, shares, ratings, and collection saves for ClawBench.
No community activity yet. Follow or share ClawBench to get things started.
Comments
Sign in to join the discussion.