# OSWorld-Verified

OSWorld-Verified is an AI benchmark; this page records what it measures and traces its data, grader, and scores to primary sources.

Measures multimodal agents on reproducible, open-ended tasks in real desktop applications; the verified release repairs the original task set.

## Details

- Address: Online, Global
- Website: [os-world.github.io/](<https://os-world.github.io/>)
- Tags: Helpful, Viral, Science
- Category: Agents
- Status: Active
- Data licence: Apache-2.0
- Data access: open
- Grader: simulation
- Organization: XLang Lab
- Released: 2024-04
- Paper: [arxiv.org/abs/2404.07972](<https://arxiv.org/abs/2404.07972>)
- Leaderboard: [os-world.github.io/\#benchmark](<https://os-world.github.io/#benchmark>)
- Repository: [github.com/xlang-ai/OSWorld](<https://github.com/xlang-ai/OSWorld>)
- Task count: 369
- Top-score provenance: unknown
- ABI family: No

## Questions

### Where is OSWorld-Verified?

OSWorld-Verified is at Online, Global.

### How do I contact OSWorld-Verified?

To contact OSWorld-Verified, visit https://os-world.github.io/.

## Source

From [Benchmark primary sources](https://aibenchmarkindex.com/about), license CC0-1.0, checked 2026-10-15.

Last updated October 15, 2026.

## Links

- This benchmark on the [web page](<https://aibenchmarkindex.com/global/online/osworld-verified>)
- [Agents in Online](<https://aibenchmarkindex.com/global/online/category/agents.md>)
- [More benchmarks in Online](<https://aibenchmarkindex.com/global/online.md>)

> **Check before you compare.** Benchmark methods and leaderboards change. Follow the cited primary source before using a result in a decision.
