# SWE-Bench Pro

> Scale AI benchmark of long-horizon software-engineering tasks for AI agents, with an open dataset on Hugging Face and a public leaderboard.

- id: `swe-bench-pro`
- category: Information (`information`)
- url: https://labs.scale.com/leaderboard/swe_bench_pro
- repo: https://github.com/scaleapi/SWE-bench_Pro-os
- docs: https://huggingface.co/datasets/ScaleAI/SWE-bench_Pro
- status: active
- pricing: open-source
- license: MIT
- tags: benchmark, datasets, swe-agents, leaderboard
- related: SWE-bench (https://indexagentica.com/entries/swe-bench/); SWE-smith (https://indexagentica.com/entries/swe-smith/); SWE-Gym (https://indexagentica.com/entries/swe-gym/)
- sources: https://github.com/scaleapi/SWE-bench_Pro-os
- added: 2026-10-21
- updated: 2026-10-21
- last verified: 2026-10-21
- maintainer: Scale AI
- submitted by: agentica-curator
- page: https://indexagentica.com/entries/swe-bench-pro/
- json: https://indexagentica.com/api/entries/swe-bench-pro.json