{"url":"/dataset/alpacaeval","name":"AlpacaEval","full_name":null,"description_markdown":"The AlpacaEval set contains 805 instructions form self-instruct, open-assistant, vicuna, koala, hh-rlhf. Those were selected so that the AlpacaEval ranking of models on the AlpacaEval set would be similar to the ranking on the Alpaca demo data.","description_withheld":null,"homepage":"https://github.com/tatsu-lab/alpaca_eval","introduced_date":"2023-05-22","introduced_date_note":null,"introduced_by":{"paper":"/paper/alpacafarm-a-simulation-framework-for-methods-1","title":"AlpacaFarm: A Simulation Framework for Methods that Learn from Human Feedback","first_author":"Yann Dubois","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Text Generation","url":"/task/text-generation","datasets_with_task":"/datasets/task/text-generation"},{"name":"Chatbot","url":"/task/chatbot","datasets_with_task":"/datasets/task/chatbot"},{"name":"Human Judgment Correlation","url":"/task/human-judgment-correlation","datasets_with_task":"/datasets/task/human-judgment-correlation"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["AlpacaEval"],"data_loaders":[],"num_papers_in_archive":131,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/chatbot-on-alpacaeval","task":"Chatbot","dataset_variant":"AlpacaEval","rows":1,"metrics":["Average win rate"],"first_row_in_archive_order":{"model":"Yi 34B Chat","paper":"/paper/yi-open-foundation-models-by-01-ai","metrics":{"Average win rate":"27.2"},"code_links":[{"title":"01-ai/yi","url":"https://github.com/01-ai/yi"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/text-generation-on-alpacaeval","task":"Text Generation","dataset_variant":"AlpacaEval","rows":0,"metrics":["win rate"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/yi-open-foundation-models-by-01-ai","title":"Yi: Open Foundation Models by 01.AI","date":"2024-03-07","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":8,"samples_ran":2,"samples_unverified":6,"pointer_only_for_licence":0,"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":8,"samples_ran":2,"samples_unverified":6,"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."}