Hugging Face dataset · #501

princeton-nlp/SWE-bench

princeton-nlp/SWE-bench is #501 among listed Hugging Face datasets, with 153 likes. SWE-bench is a dataset that tests systems’ ability to solve GitHub issues automatically. The dataset collects 2,294 Issue-Pull Request pairs from 12 popular Python repositories. Evaluation is performed by unit test verification using post-PR behavior as the reference solution…

Dataset
https://huggingface.co/datasets/princeton-nlp/SWE-bench
Author
princeton-nlp (user)
Likes
153
Downloads (30 days)
95,343
License
—
Size
10K<n<100K
Tasks
—
Modalities
text
Gated
No
Created
2023-10-10
Last modified
2025-03-03
Snapshot
2026-10-21

Back to Hugging Face datasets · Methodology