{"url":"/dataset/include-base","name":"INCLUDE-base (44 languages)","full_name":null,"description_markdown":"## Dataset Summary\r\n\r\nINCLUDE is a comprehensive knowledge- and reasoning-centric benchmark across 44 languages that evaluates multilingual LLMs for performance in the actual language environments where they would be deployed. It contains 22,637 4-option multiple-choice-questions (MCQ) extracted from academic and professional exams, covering 57 topics, including regional knowledge.","description_withheld":null,"homepage":"https://huggingface.co/datasets/CohereForAI/include-base-44","introduced_date":"2024-11-29","introduced_date_note":null,"introduced_by":{"paper":"/paper/include-evaluating-multilingual-language","title":"INCLUDE: Evaluating Multilingual Language Understanding with Regional Knowledge","first_author":"Angelika Romanou","url":null},"license":{"name":"Apache License 2.0","url":"https://choosealicense.com/licenses/apache-2.0/"},"modalities":[],"tasks":[],"languages":[{"name":"French","url":"/datasets/language/french"},{"name":"Spanish","url":"/datasets/language/spanish"},{"name":"German","url":"/datasets/language/german"},{"name":"Italian","url":"/datasets/language/italian"},{"name":"Chinese","url":"/datasets/language/chinese"},{"name":"Bengali","url":"/datasets/language/bengali"},{"name":"Japanese","url":"/datasets/language/japanese"},{"name":"Russian","url":"/datasets/language/russian"},{"name":"Portuguese","url":"/datasets/language/portuguese"},{"name":"Albanian","url":"/datasets/language/albanian"},{"name":"Armenian","url":"/datasets/language/armenian"},{"name":"Basque","url":"/datasets/language/basque"},{"name":"Belarusian","url":"/datasets/language/belarusian"},{"name":"Bulgarian","url":"/datasets/language/bulgarian"},{"name":"Croatian","url":"/datasets/language/croatian"},{"name":"Dutch","url":"/datasets/language/dutch"},{"name":"Estonian","url":"/datasets/language/estonian"},{"name":"Finnish","url":"/datasets/language/finnish"},{"name":"Hebrew","url":"/datasets/language/hebrew"},{"name":"Hindi","url":"/datasets/language/hindi"},{"name":"Hungarian","url":"/datasets/language/hungarian"},{"name":"Indonesian","url":"/datasets/language/indonesian"},{"name":"Kazakh","url":"/datasets/language/kazakh"},{"name":"Korean","url":"/datasets/language/korean"},{"name":"Lithuanian","url":"/datasets/language/lithuanian"},{"name":"Persian","url":"/datasets/language/persian"},{"name":"Polish","url":"/datasets/language/polish"},{"name":"Serbian","url":"/datasets/language/serbian"},{"name":"Tagalog","url":"/datasets/language/tagalog"},{"name":"Tamil","url":"/datasets/language/tamil"},{"name":"Telugu","url":"/datasets/language/telugu"},{"name":"Turkish","url":"/datasets/language/turkish"},{"name":"Ukrainian","url":"/datasets/language/ukrainian"},{"name":"Urdu","url":"/datasets/language/urdu"},{"name":"Vietnamese","url":"/datasets/language/vietnamese"},{"name":"Greek","url":"/datasets/language/greek"},{"name":"Standard Arabic","url":"/datasets/language/standard-arabic"},{"name":"Azerbaijani","url":"/datasets/language/azerbaijani"},{"name":"Georgian","url":"/datasets/language/georgian"},{"name":"Malayalam","url":"/datasets/language/malayalam"},{"name":"Macedonian","url":"/datasets/language/macedonian"},{"name":"Nepali (individual language)","url":"/datasets/language/nepali-individual-language"},{"name":"Uzbek","url":"/datasets/language/uzbek"},{"name":"Malay (individual language)","url":"/datasets/language/malay-individual-language"}],"variants":["INCLUDE-base (44 languages)"],"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."}