{"url":"/dataset/coir","name":"CoIR","full_name":"Code Information Retrieval Benchmark","description_markdown":"CoIR (Code Information Retrieval) benchmark, is designed to evaluate code retrieval capabilities. CoIR includes 10 curated code datasets, covering 8 retrieval tasks across 7 domains. In total, it encompasses two million documents. It also provides a common and easy Python framework, installable via pip, and shares the same data schema as benchmarks like MTEB and BEIR for easy cross-benchmark evaluations.","description_withheld":null,"homepage":"https://github.com/CoIR-team/coir","introduced_date":"2024-07-03","introduced_date_note":null,"introduced_by":{"paper":"/paper/coir-a-comprehensive-benchmark-for-code","title":"CoIR: A Comprehensive Benchmark for Code Information Retrieval Models","first_author":"Xiangyang Li","url":null},"license":{"name":"Apache-2.0 license","url":"https://github.com/CoIR-team/coir?tab=Apache-2.0-1-ov-file"},"modalities":[],"tasks":[{"name":"2D Object Detection","url":"/task/2d-object-detection","datasets_with_task":"/datasets/task/2d-object-detection"},{"name":"Object Detection","url":"/task/object-detection","datasets_with_task":"/datasets/task/object-detection"},{"name":"task","url":null,"datasets_with_task":"/datasets/task/task"},{"name":"Lesion Segmentation","url":"/task/lesion-segmentation","datasets_with_task":"/datasets/task/lesion-segmentation"},{"name":"Code Search","url":"/task/code-search","datasets_with_task":"/datasets/task/code-search"},{"name":"COVID-19 Diagnosis","url":"/task/covid-19-detection","datasets_with_task":"/datasets/task/covid-19-detection"},{"name":"Open-Domain Subject-to-Video","url":"/task/open-domain-subject-to-video","datasets_with_task":"/datasets/task/open-domain-subject-to-video"}],"languages":[],"variants":["","CoIR"],"data_loaders":[],"num_papers_in_archive":18,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/code-search-on-coir","task":"Code Search","dataset_variant":"CoIR","rows":1,"metrics":["nDCG@10"],"first_row_in_archive_order":{"model":"Voyage-code-002","paper":"/paper/coir-a-comprehensive-benchmark-for-code","metrics":{"nDCG@10":"56.26"},"code_links":[{"title":"coir-team/coir","url":"https://github.com/coir-team/coir"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/coir-a-comprehensive-benchmark-for-code","title":"CoIR: A Comprehensive Benchmark for Code Information Retrieval Models","date":"2024-07-03","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":5,"samples_ran":2,"samples_unverified":3,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":1,"samples_harvested":5,"samples_ran":2,"samples_unverified":3,"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."}