{"url":"/dataset/bongard-openworld","name":"Bongard-OpenWorld","full_name":null,"description_markdown":"Bongard-OpenWorld is a new benchmark for evaluating real-world few-shot reasoning for machine vision. We hope it can help us better understand the limitations of current visual intelligence and facilitate future research on visual agents with stronger few-shot visual reasoning capabilities.","description_withheld":null,"homepage":"https://joyjayng.github.io/Bongard-OpenWorld.github.io/","introduced_date":"2023-10-16","introduced_date_note":null,"introduced_by":{"paper":"/paper/bongard-openworld-few-shot-reasoning-for-free","title":"Bongard-OpenWorld: Few-Shot Reasoning for Free-form Visual Concepts in the Real World","first_author":"Rujie Wu","url":null},"license":{"name":"CC BY-NC-SA 4.0","url":"https://creativecommons.org/licenses/by-nc-sa/4.0/deed.en"},"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Few-Shot Learning","url":"/task/few-shot-learning","datasets_with_task":"/datasets/task/few-shot-learning"},{"name":"Visual Reasoning","url":"/task/visual-reasoning","datasets_with_task":"/datasets/task/visual-reasoning"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["Bongard-OpenWorld"],"data_loaders":[{"repo":"https://github.com/joyjayng/Bongard-OpenWorld","url":"https://github.com/joyjayng/Bongard-OpenWorld","frameworks":["pytorch"]}],"num_papers_in_archive":3,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/visual-reasoning-on-bongard-openworld","task":"Visual Reasoning","dataset_variant":"Bongard-OpenWorld","rows":9,"metrics":["2-Class Accuracy"],"first_row_in_archive_order":{"model":"Gemini-2.0 + CA","paper":"/paper/cognitive-paradigms-for-evaluating-vlms-on","metrics":{"2-Class Accuracy":"93.6"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/cognitive-paradigms-for-evaluating-vlms-on","title":"A Cognitive Paradigm Approach to Probe the Perception-Reasoning Interface in VLMs","date":"2025-01-23","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/bongard-openworld-few-shot-reasoning-for-free","title":"Bongard-OpenWorld: Few-Shot Reasoning for Free-form Visual Concepts in the Real World","date":"2023-10-16","rows_on_this_dataset":7,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":10,"samples_ran":7,"samples_unverified":3,"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":10,"samples_ran":7,"samples_unverified":3,"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."}