← all datasets
◆ Evals & benchmarks
OSWorld
Apache-2.0Open-ended computer-use tasks in real Ubuntu and Windows desktops, each with an execution-based check (NeurIPS 2024).
Summary
- Formats
json- License
- Apache-2.0
- Added
- 2026-09-10
Get it
From the project’s own instructions where it documents any; otherwise a plain clone.
-
$ git clone https://github.com/xlang-ai/OSWorld
-
$ cd OSWorld && pip install desktop-env
Tasks run in a full VM (VMware, VirtualBox, Docker with KVM, or a cloud provider).
Contents
1,190 files 121.9 MB repository
-
.py619 -
.json440 -
.md38 -
.png33 -
.txt22 -
(no ext)10 -
.sh8 -
.css3
Use it with
Commands are curated, not yet run by us.
jq — Stream the records one per line to see their shape.
$ jq -c . sample.json
DuckDB — Query the file in place with SQL — DuckDB detects CSV, JSON and JSONL by extension.
$ duckdb -c 'SELECT * FROM '\''sample.json'\'' LIMIT 10'