{"url":"/dataset/mm-eval","name":"MM-Eval","full_name":"Modern Mongolian Evaluation","description_markdown":"Large language models (LLMs) excel in high-resource languages but face notable challenges in low-resource languages like Mongolian. \r\nThe release of MM-Eval, comprising 569 syntax, 677 semantics, 344 knowledge, and 250 reasoning tasks, offers valuable insights for advancing NLP and LLMs in low-resource languages like Mongolian.","description_withheld":null,"homepage":"https://github.com/joenahm/MM-Eval","introduced_date":"2024-11-15","introduced_date_note":null,"introduced_by":{"paper":"/paper/mm-eval-a-hierarchical-benchmark-for-modern","title":"MM-Eval: A Hierarchical Benchmark for Modern Mongolian Evaluation in LLMs","first_author":"Mengyuan Zhang","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"World Knowledge","url":"/task/world-knowledge","datasets_with_task":"/datasets/task/world-knowledge"},{"name":"Math","url":"/task/math","datasets_with_task":"/datasets/task/math"}],"languages":[{"name":"Halh Mongolian","url":"/datasets/language/halh-mongolian"},{"name":"Mongolian","url":"/datasets/language/mongolian"}],"variants":["MM-Eval"],"data_loaders":[],"num_papers_in_archive":1,"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."}