OSWorld 2.0: Benchmarking Computer Use Agents on Long-Horizon Real-World Tasks
Catalog snapshot
Repository health snapshot: 44 forks and 13 open issues at review time. Platform support is inferred conservatively from repository topics.
OSWorld 2.0: Benchmarking Computer Use Agents on Long-Horizon Real-World Tasks Fossfits includes OSWorld-V2 as an actively maintained coding agents option: its public repository was updated on 2026-09-11, uses the APACHE-2.0 license, and had 303 stars when reviewed. Check its documentation and release notes before production adoption.
agent · artificial intelligence · benchmark · computer use agent · cua