{"url":"/dataset/mmstar","name":"MMStar","full_name":null,"description_markdown":"MMStar is an elite vision-indispensable multi-modal benchmark comprising 1,500 meticulously selected samples. These samples are carefully balanced and purified, ensuring they exhibit visual dependency, minimal data leakage, and require advanced multi-modal capabilities. MMStar evaluates LVLMs across 6 core capabilities and 18 detailed axes.","description_withheld":null,"homepage":"https://github.com/MMStar-Benchmark/MMStar","introduced_date":"2024-03-29","introduced_date_note":null,"introduced_by":{"paper":"/paper/are-we-on-the-right-way-for-evaluating-large","title":"Are We on the Right Way for Evaluating Large Vision-Language Models?","first_author":"Lin Chen","url":null},"license":null,"modalities":[],"tasks":[],"languages":[],"variants":["MMStar"],"data_loaders":[],"num_papers_in_archive":146,"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."}