Benchmarks

OSWorld 2.0

Agentsunit % · normalized over [0, 85]

OSWorld 2.0 — a harder, refreshed version of the OSWorld real-desktop-GUI computer-use benchmark, scored pass@1. Distinct from and not comparable to OSWorld-Verified (v1).

#ModelSourceScoreNormalized

Score distribution

4 tracked results across the normalization window

085

Score vs. parameters

Open-weights models, log-x params

No open-weights models with disclosed parameter counts have a score here yet.