SWE-bench-Live/repo-build-test-benchmark download history

SWE-bench-Live/repo-build-test-benchmark is a dataset on the Hugging Face Hub. In the last 30 days it was downloaded 934 times (200 in the last 7 days), and 1,510 times in total. It ranks #20,326 among datasets by monthly downloads.

The benchmark to evaluate the repo build and test ability of LM agents, used in the RepoLaunch paper (https://arxiv.org/abs/2603.05026).

Open SWE-bench-Live/repo-build-test-benchmark on Hugging Face

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