About WebArena-Verified Browser Agent Benchmark
Definition and scoring
- Organisation
- Amine El Hattami, Megh Thakkar, Nicolas Chapados, Christopher Pal
- Category
- Agents
- Version
- 2025
- Direction
- higher is better
- Ranking use
- Reference
- Contamination risk
- Unknown
WebArena-Verified is an audited release of the WebArena browser-agent benchmark. It rechecks task descriptions, reference answers, and evaluators, and replaces nondeterministic judging with deterministic checks where possible. Results stay tied to the exact model variant and evaluation system. Multiple systems for the same model use the best published score on this page; overall Lumina scoring uses the median of ranking-eligible rows.
Open benchmark source ↗