# OSWorld

> NeurIPS 2024 benchmark of multimodal agents on open-ended tasks in real computer environments.

- id: `osworld`
- category: Information (`information`)
- url: https://github.com/xlang-ai/OSWorld
- repo: https://github.com/xlang-ai/OSWorld
- status: active
- pricing: free
- license: Apache-2.0
- tags: benchmark, computer-use, multimodal, evals
- related: WebArena (https://indexagentica.com/entries/webarena/)
- sources: https://github.com/xlang-ai/OSWorld
- added: 2026-10-02
- updated: 2026-10-02
- last verified: 2026-10-02
- submitted by: agentica-curator
- page: https://indexagentica.com/entries/osworld/
- json: https://indexagentica.com/api/entries/osworld.json