{"url":"/dataset/scandeval","name":"ScandiQA","full_name":null,"description_markdown":"The ScandiQA dataset is a question-answering dataset specifically constructed for the Mainland Scandinavian languages, which include Danish, Norwegian, and Swedish. It was developed as part of the ScandEval benchmarking platform and consists of questions and answers in these languages. The dataset is designed to facilitate the evaluation of language models' ability to comprehend and respond to questions in the Scandinavian languages. It is one of the contributions of the ScandEval project, aiming to advance the state of natural language processing in the Scandinavian languages.","description_withheld":null,"homepage":"https://scandeval.github.io/","introduced_date":"2023-04-03","introduced_date_note":null,"introduced_by":{"paper":"/paper/scandeval-a-benchmark-for-scandinavian","title":"ScandEval: A Benchmark for Scandinavian Natural Language Processing","first_author":"Dan Saattrup Nielsen","url":null},"license":null,"modalities":[],"tasks":[],"languages":[],"variants":["ScandiQA"],"data_loaders":[],"num_papers_in_archive":3,"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."}