II.
TestSet overview
Reference · livetest-set:webarena-v1
WebArena v1 task suite overview
Canonical WebArena task artifact for autonomous web-agent evaluation.
Attributes
displayName
WebArena v1 task suite
benchmarkId
caseCount
812
releasedAt
2023-07-26
composition
WebArena's original long-horizon web task suite over realistic
self-hosted sites for shopping, forum, GitLab-style collaboration,
and content management workflows.
homepageUrl
description
Canonical WebArena task artifact for autonomous web-agent evaluation.
Outgoing edges
belongs_to_benchmark1
- benchmark:webarena·BenchmarkWebArena
Incoming edges
None.