multimodal benchmark
OSWorld
OSWorld: The first-of-its-kind scalable, real computer environment for multimodal agents, supporting task setup, execution-based evaluation, and interactive learning across Ubuntu, Windows, and macOS with 369 computer tasks involving real web and desktop applications, OS file I/O, and multi-application workflows
Updated Aug 7, 2026
Published models20
Registry coverage20
MetricScore
EvidenceB
OSWorld leaderboard
Sorted by the source-provided rank. Higher score is better according to the registry.
Score distribution
Top published rows on the benchmark's original scale.
OSWorld highlights
The top published results on this benchmark's own scale.
What is OSWorld?
Definition and scoring fields from the benchmark registry.
OSWorld: The first-of-its-kind scalable, real computer environment for multimodal agents, supporting task setup, execution-based evaluation, and interactive learning across Ubuntu, Windows, and macOS with 369 computer tasks involving real web and desktop applications, OS file I/O, and multi-application workflows
Scores are shown in ratio. The current registry marks this benchmark as not independently verified with evidence level B.
- Family
- OSWorld
- Modality
- multimodal
- Primary category
- multimodal
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- osworld|llm-stats-current
Source-native results are preserved. Eligibility for the overall LLMBoard score is a separate policy decision.
FAQ
Common questions about OSWorld.
Which model scores highest on OSWorld?
Seed 2.1 Pro is currently ranked first with 78.8%.
What does OSWorld measure?
OSWorld: The first-of-its-kind scalable, real computer environment for multimodal agents, supporting task setup, execution-based evaluation, and interactive learning across Ubuntu, Windows, and macOS with 369 computer tasks involving real web and desktop applications, OS file I/O, and multi-application workflows
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
20 unique published model results are currently shown.
Does this benchmark affect the overall score?
This benchmark is preserved as source-native evidence but is not eligible for the current overall score.