{"url":"/dataset/metabench-paper-data","name":"metabench - Paper Data","full_name":null,"description_markdown":"Item-wise accuracies in six benchmarks from Open LLM Leaderboard 1 scraped from huggingface.co and used for metabench analyses and construction. Datasets with RMSE's for random benchmark subsets are used as reference in the paper and are included here. \r\n\r\nPlease find the data uploaded on zenodo by clicking on \"Homepage\".","description_withheld":null,"homepage":"https://zenodo.org/records/12819251","introduced_date":null,"introduced_date_note":null,"introduced_by":null,"license":{"name":"Creative Commons Attribution","url":null},"modalities":[{"name":"Tables","url":"/datasets/modality/tables"}],"tasks":[],"languages":[],"variants":["metabench - Paper Data"],"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."}