{"url":"/dataset/blimp","name":"BLiMP","full_name":"Benchmark of Linguistic Minimal Pairs","description_markdown":"BLiMP is a challenge set for evaluating what language models (LMs) know about major grammatical phenomena in English. BLiMP consists of 67 sub-datasets, each containing 1000 minimal pairs isolating specific contrasts in syntax, morphology, or semantics. The data is automatically generated according to expert-crafted grammars. Aggregate human agreement with the labels is 96.4%.\r\n\r\nSource: [BLiMP ](https://github.com/alexwarstadt/blimp)\r\nImage Source: [https://arxiv.org/pdf/1912.00582v3.pdf](https://arxiv.org/pdf/1912.00582v3.pdf)","description_withheld":null,"homepage":"https://github.com/alexwarstadt/blimp","introduced_date":"2019-12-02","introduced_date_note":null,"introduced_by":{"paper":"/paper/blimp-a-benchmark-of-linguistic-minimal-pairs","title":"BLiMP: The Benchmark of Linguistic Minimal Pairs for English","first_author":"Alex Warstadt","url":null},"license":{"name":"Unknown","url":null},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Language Modelling","url":"/task/language-modelling","datasets_with_task":"/datasets/task/language-modelling"},{"name":"Language Acquisition","url":"/task/language-acquisition","datasets_with_task":"/datasets/task/language-acquisition"}],"languages":[],"variants":["BLiMP"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/nyu-mll/blimp","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/blimp","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/tensorflow/datasets","url":"https://www.tensorflow.org/datasets/catalog/blimp","frameworks":["tf","jax"]},{"repo":"https://github.com/alexwarstadt/blimp","url":"https://github.com/alexwarstadt/blimp","frameworks":[]}],"num_papers_in_archive":126,"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."}