WebArena

Realistic web env (e.g. e‑commerce, CMS, dev tools); 812 tasks; measures end-to-end web agent success.

Stars

1.5k

Adoption surface

complex

Autonomy

headless

Recovery

none

License

✅ open-source

Category

Evaluation and benchmarking harnesses

Repository ↗ Example: WebArena leaderboard ↗

Related in Evaluation and benchmarking harnesses

• Agent Lightning
• SWE-bench
• AgentBench
• inspect_ai
• WebVoyager
• ARC-AGI-2