{"url":"/sota/visual-reasoning-on-winogavil","task":{"name":"Visual Reasoning","url":"/task/visual-reasoning","note":null},"dataset":{"name":"WinoGAViL","url":"/dataset/winogavil"},"category":"Computer Vision","categories":["Computer Vision","Reasoning"],"category_note":null,"description":"Ability to understand  actions and reasoning  associated with any  visual images","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":["Jaccard Index"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"Jaccard Index":null}},"counts":{"rows":8,"rows_with_code":8,"rows_with_paper_page":8,"rows_dated":8,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"Humans","metrics":{"Jaccard Index":"90"},"uses_additional_data":false,"paper_date":"2022-07-25","paper":"/paper/winogavil-gamified-association-benchmark-to","paper_url":"https://arxiv.org/abs/2207.12576v2","paper_title":"WinoGAViL: Gamified Association Benchmark to Challenge Vision-and-Language Models","code":"https://github.com/winogavil/winogavil-experiments","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":1,"n_samples":2,"n_pointer_only_licence":0}},{"rank_in_archive_order":2,"model":"ViLT (Zero-Shot)","metrics":{"Jaccard Index":"52"},"uses_additional_data":false,"paper_date":"2022-07-25","paper":"/paper/winogavil-gamified-association-benchmark-to","paper_url":"https://arxiv.org/abs/2207.12576v2","paper_title":"WinoGAViL: Gamified Association Benchmark to Challenge Vision-and-Language Models","code":"https://github.com/winogavil/winogavil-experiments","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":1,"n_samples":2,"n_pointer_only_licence":0}},{"rank_in_archive_order":3,"model":"X-VLM (Zero-Shot)","metrics":{"Jaccard Index":"46"},"uses_additional_data":false,"paper_date":"2022-07-25","paper":"/paper/winogavil-gamified-association-benchmark-to","paper_url":"https://arxiv.org/abs/2207.12576v2","paper_title":"WinoGAViL: Gamified Association Benchmark to Challenge Vision-and-Language Models","code":"https://github.com/winogavil/winogavil-experiments","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":1,"n_samples":2,"n_pointer_only_licence":0}},{"rank_in_archive_order":4,"model":"CLIP-ViT-B/32 (Zero-Shot)","metrics":{"Jaccard Index":"41"},"uses_additional_data":false,"paper_date":"2022-07-25","paper":"/paper/winogavil-gamified-association-benchmark-to","paper_url":"https://arxiv.org/abs/2207.12576v2","paper_title":"WinoGAViL: Gamified Association Benchmark to Challenge Vision-and-Language Models","code":"https://github.com/winogavil/winogavil-experiments","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":1,"n_samples":2,"n_pointer_only_licence":0}},{"rank_in_archive_order":5,"model":"CLIP-ViT-L/14 (Zero-Shot)","metrics":{"Jaccard Index":"40"},"uses_additional_data":false,"paper_date":"2022-07-25","paper":"/paper/winogavil-gamified-association-benchmark-to","paper_url":"https://arxiv.org/abs/2207.12576v2","paper_title":"WinoGAViL: Gamified Association Benchmark to Challenge Vision-and-Language Models","code":"https://github.com/winogavil/winogavil-experiments","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":1,"n_samples":2,"n_pointer_only_licence":0}},{"rank_in_archive_order":6,"model":"CLIP-RN50x64/14 (Zero-Shot)","metrics":{"Jaccard Index":"38"},"uses_additional_data":false,"paper_date":"2022-07-25","paper":"/paper/winogavil-gamified-association-benchmark-to","paper_url":"https://arxiv.org/abs/2207.12576v2","paper_title":"WinoGAViL: Gamified Association Benchmark to Challenge Vision-and-Language Models","code":"https://github.com/winogavil/winogavil-experiments","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":1,"n_samples":2,"n_pointer_only_licence":0}},{"rank_in_archive_order":7,"model":"CLIP-RN50 (Zero-Shot)","metrics":{"Jaccard Index":"35"},"uses_additional_data":false,"paper_date":"2022-07-25","paper":"/paper/winogavil-gamified-association-benchmark-to","paper_url":"https://arxiv.org/abs/2207.12576v2","paper_title":"WinoGAViL: Gamified Association Benchmark to Challenge Vision-and-Language Models","code":"https://github.com/winogavil/winogavil-experiments","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":1,"n_samples":2,"n_pointer_only_licence":0}},{"rank_in_archive_order":8,"model":"CLIP-ViL (Zero-Shot)","metrics":{"Jaccard Index":"15"},"uses_additional_data":false,"paper_date":"2022-07-25","paper":"/paper/winogavil-gamified-association-benchmark-to","paper_url":"https://arxiv.org/abs/2207.12576v2","paper_title":"WinoGAViL: Gamified Association Benchmark to Challenge Vision-and-Language Models","code":"https://github.com/winogavil/winogavil-experiments","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":1,"n_samples":2,"n_pointer_only_licence":0}}],"since_archive":{"present":false,"note":"No Syntology-extracted rows are published in this build."},"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":8,"rows_with_any_sample_ran":8,"distinct_papers_with_graph_line":1,"distinct_papers_with_any_sample_ran":1,"samples_over_distinct_papers":{"n_ran":1,"n_unverified":1,"n_samples":2,"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":8,"n_unverified":8,"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"}}}