protologue

OSWorld

OSWorld is a benchmark of open-ended tasks that computer-use agents must complete in real operating systems and applications, graded by scripts that check the resulting state of the computer.

Description

Tasks span office software, web browsers, file management, and multi-application workflows. It is the standard benchmark for computer-use agents and showed a large gap between early agents and people.

Sources

  1. Xie et al. (2024). OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments.

Cite this entry

Protologue. (2026). OSWorld. In Protologue: A Taxonomy of Prompting and LLM Techniques (v1.4.0, PTL-0205). https://protologue.com/t/osworld/

BibTeX
@misc{protologue_osworld,
  title = {OSWorld},
  author = {{Protologue}},
  year = {2026},
  howpublished = {Protologue: A Taxonomy of Prompting and LLM Techniques, v1.4.0},
  note = {Entry PTL-0205},
  url = {https://protologue.com/t/osworld/}
}

Markdown JSON