OSWorld 2.1 (all 108 tasks)

OSWorld 2.1 is the current release of OSWorld 2.0: the same 108 long-horizon computer-use workflows with the maintainers' later fixes to task files, assets, mocked websites, and evaluators. This page stores partial scores on the full task set.

ModelsModels with a result.11
Top resultBest result on this benchmark.81.8%Claude Opus 5.5
Top-3 spreadPoints from first to third.1.7 pts
YearYear of release.2026

Result and price

10 of 11 results

Results

11 results
#ModelResultThe score from the source.
05Hy478.9%
10Muse Ember69.5%