Mengqi Yuan et al.
OSWorld 2.1 offline subset (82 tasks)
The official offline subset of OSWorld 2.1: 82 of the 108 long-horizon computer-use workflows, run with no internet access in the agent's virtual machine.
ModelsModels with a result.10
Top-3 spreadPoints from first to third.5.4 pts
YearYear of release.2026
Result and price
10 of 10 results
Results
10 results#ModelResultThe score from the source.