Mahal Systems

Overview › Benchmark catalog

OSWorld-Verified

Fits general desktop agents on office and OS tasks; the current reference number for computer-use models. Borrow the parallel AWS runner that finishes a run within an hour.

What it asks the agent to do

  • the 369 OSWorld tasks with fixed evaluators, fuzzy matching and backup sites
  • office, daily and professional desktop tasks on Ubuntu

What to borrow from it

baselinegrading designsandbox design

Caveats

Top scores (85 to 90 percent in 2026 reports) are past the 72 percent human baseline, so it no longer separates strong agents; use OSWorld 2.0 for headroom.

Details

Workloadscomputer use, documents, spreadsheets, it ops
Interactionsingle turn
Environmentdesktop
End state checkedYes
Toolsmouse and keyboard on an Ubuntu VM (AWS or Docker), screenshots
Gradingstate diff, programmatic check
Size369
Datareal public
Personal datanone
LicenseApache-2.0
Harnessinspect_evals, own repo
Statussaturated

Links