{"slug":"osworld","name":"OSWorld","category":"eval","categoryName":"Evaluation, red-teaming & guardrails","audience":["ai-era"],"primary":"ai-era","openClosed":"open","pricing":"open-source","license":"Apache-2.0","maintained":"yes","officialUrl":"https://os-world.github.io","repo":"https://github.com/xlang-ai/OSWorld","latestVersion":"v0.1.16","latestRelease":"2024-06-26","stars":3229,"starsAsOf":"2026-10-22","description":"[NeurIPS 2024] OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments","descriptionZh":"真实电脑环境多模态 agent 基准","callMethods":["CLI"],"platforms":[],"addedAt":"2026-10-10","updatedAt":"2026-10-22","topics":["agent","artificial-intelligence","benchmark","cli","code-generation","gui","language-model","large-action-model","llm","multimodal","natural-language-processing","reinforcement-learning","rpa","vlm"],"language":"Python","lastPush":"2026-10-21","formerly":null,"packages":[],"recentVersions":[{"version":"v0.1.16","date":"2024-06-26","prerelease":false,"url":"https://github.com/xlang-ai/OSWorld/releases/tag/v0.1.16","source":"GitHub Release"},{"version":"v0.1.0","date":"2024-04-11","prerelease":false,"url":"https://github.com/xlang-ai/OSWorld/releases/tag/v0.1.0","source":"GitHub Release"}],"alternatives":["lmms-eval","opencompass","swe-bench","tau2-bench","promptfoo","ragas","lm-evaluation-harness","giskard-oss"],"stacks":[],"scenarios":["evaluate-and-monitor"],"problems":[],"reasonZh":"电脑操作基准","sources":["priority","oss","github-pool"],"record":"https://aimap.page/api/v1/software/osworld.json","pages":{"en":"https://aimap.page/en/software/osworld/","zh-hans":"https://aimap.page/zh-hans/software/osworld/"}}