Skip to main content
Evaluation sources/OSWorld-Verified
ObservingProfessional work

OSWorld-Verified

XLANG Lab · Public model evaluation results from OSWorld-Verified.

Official evaluation
Source description

This source measures concrete delivery performance in Professional work; raw scores are shown separately from the normalized capability score.

Limitation: Different versions, reasoning settings, and test sets may change scores; read them with the data date.

How it is used

Participating sources affect capability scores; reference, cross-reference, and observing sources are for comparison and verification only.

Model results from this source

Claude Fable 58585.02026-06-09
Claude Opus 4.883.483.42026-06-09
Claude Sonnet 581.281.22026-06-30
Muse Spark 1.180.880.82026-07-09
GPT-5.578.778.72026-04-23
Claude Sonnet 4.678.578.52026-06-30
Claude Opus 4.77878.02026-04-23
Gemini 3.1 Pro Preview76.276.22026-05-19
GPT-5.47575.02026-04-23
MiniMax-M370.0670.12026-06-01

Frequently asked questions