{"url":"/dataset/lingoly","name":"LingOly","full_name":null,"description_markdown":"This dataset is a benchmark for complex reasoning abilities in large language models, drawing on United Kingdom Linguistics Olympiad problems which cover a wide range of languages.","description_withheld":null,"homepage":"https://huggingface.co/datasets/ambean/lingOly","introduced_date":"2024-06-10","introduced_date_note":null,"introduced_by":{"paper":"/paper/lingoly-a-benchmark-of-olympiad-level","title":"LINGOLY: A Benchmark of Olympiad-Level Linguistic Reasoning Puzzles in Low-Resource and Extinct Languages","first_author":"Andrew M. Bean","url":null},"license":{"name":"CC-BY-NC-ND","url":"https://spdx.org/licenses/CC-BY-NC-ND-4.0"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Logical Reasoning","url":"/task/logical-reasoning","datasets_with_task":"/datasets/task/logical-reasoning"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["LingOly"],"data_loaders":[{"repo":"https://github.com/am-bean/lingOly","url":"https://github.com/am-bean/lingOly","frameworks":[]}],"num_papers_in_archive":4,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/logical-reasoning-on-lingoly","task":"Logical Reasoning","dataset_variant":"LingOly","rows":11,"metrics":["Delta_NoContext","Exact Match Accuracy"],"first_row_in_archive_order":{"model":"Claude Opus","paper":"/paper/lingoly-a-benchmark-of-olympiad-level","metrics":{"Delta_NoContext":"28.8%","Exact Match Accuracy":"46.3%"},"code_links":[{"title":"am-bean/lingOly","url":"https://github.com/am-bean/lingOly"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/lingoly-a-benchmark-of-olympiad-level","title":"LINGOLY: A Benchmark of Olympiad-Level Linguistic Reasoning Puzzles in Low-Resource and Extinct Languages","date":"2024-06-10","rows_on_this_dataset":11,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":2,"samples_ran":2,"samples_unverified":0,"pointer_only_for_licence":2,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":1,"samples_harvested":2,"samples_ran":2,"samples_unverified":0,"pointer_only_for_licence":2,"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."}