{"url":"/dataset/ifeval","name":"IFEval","full_name":"Instruction Following Evaluation Datset","description_markdown":"This dataset evaluates instruction following ability of large language models. There are 500+ prompts with instructions such as \"write an article with more than 800 words\", \"wrap your response with double quotation marks\", etc.","description_withheld":null,"homepage":"https://github.com/google-research/google-research/tree/master/instruction_following_eval","introduced_date":"2023-11-14","introduced_date_note":null,"introduced_by":{"paper":"/paper/instruction-following-evaluation-for-large","title":"Instruction-Following Evaluation for Large Language Models","first_author":"Jeffrey Zhou","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Large Language Model","url":"/task/large-language-model","datasets_with_task":"/datasets/task/large-language-model"},{"name":"Instruction Following","url":"/task/instruction-following","datasets_with_task":"/datasets/task/instruction-following"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["IFEval"],"data_loaders":[],"num_papers_in_archive":180,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/instruction-following-on-ifeval","task":"Instruction Following","dataset_variant":"IFEval","rows":4,"metrics":["Inst-level loose-accuracy","Inst-level strict-accuracy","Prompt-level loose-accuracy","Prompt-level strict-accuracy"],"first_row_in_archive_order":{"model":"AutoIF (Llama3 70B)","paper":"/paper/self-play-with-execution-feedback-improving","metrics":{"Inst-level loose-accuracy":"90.4","Inst-level strict-accuracy":"86.7","Prompt-level loose-accuracy":"85.6","Prompt-level strict-accuracy":"80.2"},"code_links":[{"title":"QwenLM/AutoIF","url":"https://github.com/QwenLM/AutoIF"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/self-play-with-execution-feedback-improving","title":"Self-play with Execution Feedback: Improving Instruction-following Capabilities of Large Language Models","date":"2024-06-19","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":1,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/instruction-following-evaluation-for-large","title":"Instruction-Following Evaluation for Large Language Models","date":"2023-11-14","rows_on_this_dataset":2,"code_links":4,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":7,"samples_ran":2,"samples_unverified":5,"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":2,"samples_harvested":8,"samples_ran":3,"samples_unverified":5,"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."}