princeton-nlp/SWE-bench download history

princeton-nlp/SWE-bench is a dataset on the Hugging Face Hub. In the last 30 days it was downloaded 83,459 times (47,908 in the last 7 days), and 1,957,192 times in total. It ranks #306 among datasets by monthly downloads.

Dataset Summary 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 solut

Models trained on SWE-bench

6 models list it as training data.

Spaces using SWE-bench

Open princeton-nlp/SWE-bench on Hugging Face

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