Model results
OSWorld
Choose a shared evaluation protocol to compare model scores. Versions, sources and configurations stay separate.
Atlas snapshot captured 10/19/2026, 10:20:28 AM UTC. This is an import timestamp, not the evaluation date. Coverage may be incomplete.
Reviewed recommendation and limits
Start with OSWorld for long desktop workflows. Select the task release and compare binary completion separately from partial credit.
Publisher-declared end-to-end results for June 24, August 8 and v2.1 task releases; binary completion and partial credit; full or offline datasets; exact step and tool settings. Imported groups below may use different protocols; this review does not certify each run. Full and offline datasets, task releases, step budgets, effort and tool settings stay separate. Provider effort labels do not imply equal compute. Exact execution backends and measurement dates are unreported; Muse Spark task denominators remain unresolved.
OSWorld binary completion
- Source
- OSWorld (reviewed publisher results)
- Version
- v2026.08.08
- Measurement date
- Not reported
- Metric
- % · Higher is better
- Evaluation scope
- Task release v2026.08.08; full dataset; 500 steps; reasoning high; tool setting batch tool; binary completion; end-to-end publisher protocol; provider-specific effort labels, not equal compute; exact execution backend, runtime revision, run count, decoding configuration and result date not supplied; publisher-reported evaluation, operator not separately attested; effective task denominator unverified
Fewer than two comparable models. No ranking is assigned. Missing metadata is shown as unreported; matching imported metadata is not independent verification of the protocol.
Claude Opus 5
anthropic/claude-opus-5
28.98%
View modelEvidence independent