{"url":"/dataset/bluex","name":"BLUEX","full_name":null,"description_markdown":"BLUEX is a valuable benchmark dataset designed to evaluate language models in Portuguese. Despite Portuguese being the fifth most widely spoken language, there is a scarcity of freely available resources for assessing language models in this language. The BLUEX dataset addresses this gap by providing a multimodal collection of questions from the two leading university entrance exams conducted in Brazil: Convest (Unicamp) and Fuvest (USP). These exams span from 2018 to 2024 and cover a total of 1260 questions. Notably, 724 of these questions do not have accompanying images.","description_withheld":null,"homepage":"https://github.com/portuguese-benchmark-datasets/bluex","introduced_date":"2023-07-11","introduced_date_note":null,"introduced_by":{"paper":"/paper/bluex-a-benchmark-based-on-brazilian-leading","title":"BLUEX: A benchmark based on Brazilian Leading Universities Entrance eXams","first_author":"Thales Sales Almeida","url":null},"license":null,"modalities":[],"tasks":[],"languages":[],"variants":["BLUEX"],"data_loaders":[],"num_papers_in_archive":5,"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."}