princeton-nlp/SWE-bench_Lite download history

princeton-nlp/SWE-bench_Lite is a dataset on the Hugging Face Hub. In the last 30 days it was downloaded 56,452 times (9,988 in the last 7 days), and 2,468,042 times in total. It ranks #653 among datasets by monthly downloads.

Dataset Summary SWE-bench Lite is subset of SWE-bench, a dataset that tests systems’ ability to solve GitHub issues automatically. The dataset collects 300 test Issue-Pull Request pairs from 11 popular Python. Evaluation is performed by unit test verification using post-PR behavior as

Models trained on SWE-bench_Lite

4 models list it as training data.

Spaces using SWE-bench_Lite

Downloads by month

Downloads in the 30 days up to the end of each month, and the change from the month before.

MonthDownloadsChange
Up to 2026-11-1856,452-11%
October 202663,297-30%
September 202690,861-20%
August 2026113,294-25%
July 2026150,365+1%
June 2026148,961+48%
May 2026100,755+13%
April 202688,971+30%
March 202668,300-6%
February 202672,495+90%
January 202638,155+0%
December 202538,155+29%

Its busiest 30 days so far ended on 2024-07-29, with 415,384 downloads.

Open princeton-nlp/SWE-bench_Lite on Hugging Face

Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.