{"url":"/dataset/muchomusic","name":"MuChoMusic","full_name":null,"description_markdown":"MuChoMusic is a benchmark designed to evaluate music understanding in multimodal language models focused on audio. It includes 1,187 multiple-choice questions validated by human annotators, based on 644 music tracks from two publicly available music datasets. These questions cover a wide variety of genres and assess knowledge and reasoning across several musical concepts and their cultural and functional contexts. The benchmark provides a holistic evaluation of five open-source models, revealing challenges such as over-reliance on the language modality and highlighting the need for better multimodal integration.","description_withheld":null,"homepage":"https://mulab-mir.github.io/muchomusic/","introduced_date":"2024-08-02","introduced_date_note":null,"introduced_by":{"paper":"/paper/2408-01337","title":"MuChoMusic: Evaluating Music Understanding in Multimodal Audio-Language Models","first_author":"Benno Weck","url":null},"license":{"name":"Creative Commons Attribution Share Alike 4.0 International","url":"https://zenodo.org/records/12709974"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"},{"name":"Audio","url":"/datasets/modality/audio"},{"name":"Music","url":"/datasets/modality/music"}],"tasks":[{"name":"Music Question Answering","url":"/task/music-question-answering","datasets_with_task":"/datasets/task/music-question-answering"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["MuChoMusic"],"data_loaders":[{"repo":"https://github.com/mulab-mir/muchomusic","url":"https://github.com/mulab-mir/muchomusic","frameworks":[]}],"num_papers_in_archive":6,"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."}