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 2.1
- Source
- Anthropic (reviewed publisher results)
- Version
- 2.1
- Measurement date
- Not reported
- Metric
- % · Higher is better
- Evaluation scope
- Vendor-reported in Anthropic's Claude Opus 5.5 launch table; adaptive thinking at max effort unless noted; evaluated with production safeguards on, and where they intervened, cybersecurity tasks fell back to Claude Opus 4.8 and biology/frontier-LLM tasks to Claude Opus 5 (Anthropic says this likely lowers scores); partial credit scoring as labelled in the table; announcement dated 2026-09-22; measurement date unreported
Positions are withheld because at least one result lacks explicit independent provenance or a documented evaluation scope. Missing metadata is shown as unreported; matching imported metadata is not independent verification of the protocol.
Claude Opus 5.5
anthropic/claude-opus-5-5
81.8%
View modelEvidence model-card-reported