II.
TestSet overview
Reference · livetest-set:osworld-369-computer-tasks
OSWorld 369 real-computer tasks overview
Canonical OSWorld artifact for multimodal desktop-computer control agent evaluation.
Attributes
displayName
OSWorld 369 real-computer tasks
benchmarkId
caseCount
369
composition
Source-backed OSWorld task suite of real-world desktop and web
computer-use tasks with reproducible setup and execution-based
evaluation across operating-system and productivity workflows.
homepageUrl
description
Canonical OSWorld artifact for multimodal desktop-computer control
agent evaluation.
Outgoing edges
belongs_to_benchmark1
- benchmark:os-world·BenchmarkOSWorld
Incoming edges
None.