{
  "id": "osworld",
  "code": "PTL-0205",
  "term": "OSWorld",
  "aliases": [],
  "category": "benchmarks",
  "definition": "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.",
  "example": null,
  "broader": [
    "benchmark"
  ],
  "narrower": [],
  "related": [
    "computer-use-agent",
    "multimodal-prompting"
  ],
  "introduced": 2024,
  "added": "2026-10-10",
  "sources": [
    {
      "title": "OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments",
      "authors": "Xie et al.",
      "year": 2024,
      "url": "https://arxiv.org/abs/2404.07972"
    }
  ],
  "url": "https://protologue.com/t/osworld/",
  "citation": "Protologue. (2026). OSWorld. In Protologue: A Taxonomy of Prompting and LLM Techniques (v1.4.0, PTL-0205). https://protologue.com/t/osworld/"
}