{"url":"/dataset/mocha","name":"MOCHA","full_name":null,"description_markdown":"Contains 40K human judgement scores on model outputs from 6 diverse question answering datasets and an additional set of minimal pairs for evaluation. \r\n\r\nSource: [MOCHA: A Dataset for Training and Evaluating Generative Reading Comprehension Metrics](/paper/mocha-a-dataset-for-training-and-evaluating)","description_withheld":null,"homepage":"https://github.com/anthonywchen/MOCHA","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/mocha-a-dataset-for-training-and-evaluating","title":"MOCHA: A Dataset for Training and Evaluating Generative Reading Comprehension Metrics","first_author":"Anthony Chen","url":null},"license":null,"modalities":[],"tasks":[{"name":"Question Answering","url":"/task/question-answering","datasets_with_task":"/datasets/task/question-answering"},{"name":"Reading Comprehension","url":"/task/reading-comprehension","datasets_with_task":"/datasets/task/reading-comprehension"}],"languages":[],"variants":["MOCHA"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/anthonychen/mocha","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/mocha","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/anthonywchen/MOCHA","url":"https://github.com/anthonywchen/MOCHA","frameworks":[]}],"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."}