feat(benchmarks): add 25-defect dataset, manifest loader, and Pass@k evaluation harness - #5

feat(benchmarks): add 25-defect dataset, manifest loader, and Pass@k evaluation harness#5

Abdurrafay19 merged 18 commits into

masterAbdurrafay19/patchwork:masterfrom

bench/defect-evaluationAbdurrafay19/patchwork:bench/defect-evaluationCopy head branch name to clipboard