multimodal benchmark
OSWorld Screenshot-only: A variant of the OSWorld benchmark that evaluates multimodal AI agents using only screenshot observations to complete open-ended computer tasks across real operating systems (Ubuntu, Windows, macOS). Tests agents' ability to perform complex workflows involving web apps, desktop applications, file I/O, and multi-application tasks through visual interface understanding and GUI grounding.
Updated Aug 11, 2026
Higher score ranks better on this benchmark.
| 01 | AN | 14.9% | 100.0% | 1 | C |
The leading models and scores on this benchmark.
What OSWorld Screenshot-only measures and how its scores work.
OSWorld Screenshot-only: A variant of the OSWorld benchmark that evaluates multimodal AI agents using only screenshot observations to complete open-ended computer tasks across real operating systems (Ubuntu, Windows, macOS). Tests agents' ability to perform complex workflows involving web apps, desktop applications, file I/O, and multi-application tasks through visual interface understanding and GUI grounding.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
Common questions about OSWorld Screenshot-only.
Claude 3.5 Sonnet is currently ranked first with 14.9%.
OSWorld Screenshot-only: A variant of the OSWorld benchmark that evaluates multimodal AI agents using only screenshot observations to complete open-ended computer tasks across real operating systems (Ubuntu, Windows, macOS). Tests agents' ability to perform complex workflows involving web apps, desktop applications, file I/O, and multi-application tasks through visual interface understanding and GUI grounding.
Yes. Higher values rank better for this benchmark.
1 model results are currently shown.
No. This benchmark is shown for reference but does not contribute to the overall score.