{"url":"/sota/instruction-following-on-ifeval","task":{"name":"Instruction Following","url":"/task/instruction-following","note":null},"dataset":{"name":"IFEval","url":"/dataset/ifeval"},"category":"Computer Vision","categories":["Computer Vision","Natural Language Processing"],"category_note":null,"description":"Instruction following is the basic task of the model. This task is dedicated to evaluating the ability of the large model to follow human instructions. It is hoped that the model can generate controllable and safe answers.","description_from":"task","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["Inst-level loose-accuracy","Inst-level strict-accuracy","Prompt-level loose-accuracy","Prompt-level strict-accuracy"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"Inst-level loose-accuracy":"higher","Inst-level strict-accuracy":"higher","Prompt-level loose-accuracy":"higher","Prompt-level strict-accuracy":"higher"}},"counts":{"rows":4,"rows_with_code":4,"rows_with_paper_page":4,"rows_dated":4,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"AutoIF (Llama3 70B)","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"},"uses_additional_data":false,"paper_date":"2024-06-19","paper":"/paper/self-play-with-execution-feedback-improving","paper_url":"https://arxiv.org/abs/2406.13542v3","paper_title":"Self-play with Execution Feedback: Improving Instruction-following Capabilities of Large Language Models","code":"https://github.com/QwenLM/AutoIF","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":2,"model":"AutoIF (Qwen2 72B)","metrics":{"Inst-level loose-accuracy":"88","Inst-level strict-accuracy":"86.1","Prompt-level loose-accuracy":"82.3","Prompt-level strict-accuracy":"80.2"},"uses_additional_data":false,"paper_date":"2024-06-19","paper":"/paper/self-play-with-execution-feedback-improving","paper_url":"https://arxiv.org/abs/2406.13542v3","paper_title":"Self-play with Execution Feedback: Improving Instruction-following Capabilities of Large Language Models","code":"https://github.com/QwenLM/AutoIF","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":3,"model":"GPT-4","metrics":{"Inst-level loose-accuracy":"85.37","Inst-level strict-accuracy":"83.57","Prompt-level loose-accuracy":"79.3","Prompt-level strict-accuracy":"76.89"},"uses_additional_data":false,"paper_date":"2023-11-14","paper":"/paper/instruction-following-evaluation-for-large","paper_url":"https://arxiv.org/abs/2311.07911v1","paper_title":"Instruction-Following Evaluation for Large Language Models","code":"https://github.com/google-research/google-research/tree/master/instruction_following_eval","n_code_links":4,"syntology":{"n_ran":2,"n_unverified":5,"n_samples":7,"n_pointer_only_licence":0}},{"rank_in_archive_order":4,"model":"PaLM 2 S","metrics":{"Inst-level loose-accuracy":"59.11","Inst-level strict-accuracy":"55.76","Prompt-level loose-accuracy":"46.95","Prompt-level strict-accuracy":"43.07"},"uses_additional_data":false,"paper_date":"2023-11-14","paper":"/paper/instruction-following-evaluation-for-large","paper_url":"https://arxiv.org/abs/2311.07911v1","paper_title":"Instruction-Following Evaluation for Large Language Models","code":"https://github.com/google-research/google-research/tree/master/instruction_following_eval","n_code_links":4,"syntology":{"n_ran":2,"n_unverified":5,"n_samples":7,"n_pointer_only_licence":0}}],"since_archive":{"claim":"Results that newer papers report for their own method, placed here by Syntology. A model pointed at the cell in the paper's own table; the number was read from that cell and checked against this leaderboard's metric, dataset, split and scale; an independent check that saw this leaderboard's other rows and every other leaderboard on the same dataset accepted it. Not reviewed by the paper's authors or by the archive's editors, and not ranked against the archive rows.","extraction_file_present":true,"measurement":{"test_papers":883,"papers_with_output":881,"judged_true":108,"judged":110,"wilson95_lower":0.9361,"measured_on":"2026-09-24","frozen_commit":"0e3de0df94"},"measurement_note":"blind adjudication of accepted entries on a held-out split of archive papers, rules frozen before the test","coverage":{"sentence":"Syntology has checked 6,795 of the 9,581 papers on this site that are newer than the archive; results from the others appear after they are checked.","complete":false,"papers_newer_than_archive":9581,"papers_checked":6795,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"papers_not_yet_extracted":2785},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","rows_with_graph_line":4,"rows_with_any_sample_ran":4,"distinct_papers_with_graph_line":2,"distinct_papers_with_any_sample_ran":2,"samples_over_distinct_papers":{"n_ran":3,"n_unverified":5,"n_samples":8,"n_pointer_only_licence":0,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":6,"n_unverified":10,"n_samples":16,"n_pointer_only_licence":0,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}}}