{"url":"/dataset/mmarco","name":"mMARCO","full_name":null,"description_markdown":"**mMARCO** is a multilingual version of the MS MARCO passage ranking dataset comprising 8 languages that was created using machine translation.","description_withheld":null,"homepage":"https://github.com/unicamp-dl/mMARCO.git","introduced_date":"2021-08-31","introduced_date_note":null,"introduced_by":{"paper":"/paper/mmarco-a-multilingual-version-of-ms-marco","title":"mMARCO: A Multilingual Version of the MS MARCO Passage Ranking Dataset","first_author":"Luiz Bonifacio","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Passage Re-Ranking","url":"/task/passage-re-ranking","datasets_with_task":"/datasets/task/passage-re-ranking"}],"languages":[],"variants":["mMARCO"],"data_loaders":[],"num_papers_in_archive":23,"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."}