{"url":"/dataset/repobench","name":"RepoBench","full_name":null,"description_markdown":"RepoBench is a benchmark designed for evaluating repository-level code auto-completion systems, focusing on more complex, real-world programming scenarios involving multiple files. It comprises three tasks: RepoBench-R (Retrieval), measuring the system's ability to retrieve relevant code snippets; RepoBench-C (Code Completion), assessing the prediction of the next line of code with both in-file and cross-file context; and RepoBench-P (Pipeline), evaluating complex tasks requiring both retrieval and prediction. RepoBench aims to provide a comprehensive performance comparison to foster continuous improvement in auto-completion systems.","description_withheld":null,"homepage":"https://github.com/Leolty/repobench","introduced_date":"2023-06-05","introduced_date_note":null,"introduced_by":{"paper":"/paper/repobench-benchmarking-repository-level-code","title":"RepoBench: Benchmarking Repository-Level Code Auto-Completion Systems","first_author":"Tianyang Liu","url":null},"license":null,"modalities":[],"tasks":[],"languages":[],"variants":["RepoBench"],"data_loaders":[],"num_papers_in_archive":17,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[],"papers_with_a_benchmark_row":[],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}