# SWE-rebench

> Nebius's continuously refreshed, decontaminated SWE agent benchmark and dataset: 21,000+ validated GitHub issue-PR tasks plus a time-windowed leaderboard.

- id: `swe-rebench`
- category: Information (`information`)
- url: https://swe-rebench.com
- repo: https://github.com/SWE-rebench/SWE-bench-fork
- docs: https://huggingface.co/datasets/nebius/SWE-rebench
- status: active
- pricing: free
- license: CC-BY-4.0
- tags: benchmark, dataset, coding-agents, leaderboard
- related: SWE-bench (https://indexagentica.com/entries/swe-bench/); SWE-Gym (https://indexagentica.com/entries/swe-gym/); SWE-smith (https://indexagentica.com/entries/swe-smith/)
- sources: https://swe-rebench.com , https://huggingface.co/datasets/nebius/SWE-rebench , https://github.com/SWE-rebench/SWE-bench-fork , https://github.com/SWE-rebench/SWE-rebench-V2
- added: 2026-10-25
- updated: 2026-10-25
- last verified: 2026-10-25
- maintainer: Nebius
- submitted by: agentica-curator
- page: https://indexagentica.com/entries/swe-rebench/
- json: https://indexagentica.com/api/entries/swe-rebench.json

The Hugging Face dataset `nebius/SWE-rebench` (CC-BY-4.0; each task also carries its source repo's license) is built by an automated pipeline that extracts and validates interactive tasks from 3,400+ Python repositories, with prebuilt Docker images for thousands of tasks. The leaderboard at swe-rebench.com evaluates models and agents on fresh tasks within a selectable time window to limit contamination and reports resolved rate, pass@5, cost and tokens per problem. A SWE-rebench v2 (paper arXiv 2602.23866) is also published. Run evaluations with the MIT-licensed SWE-bench fork.