{"url":"/sota/visual-reasoning-on-nlvr2-test","task":{"name":"Visual Reasoning","url":"/task/visual-reasoning","note":null},"dataset":{"name":"NLVR2 Test","url":"/dataset/nlvr"},"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":["Accuracy"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"Accuracy":"higher"}},"counts":{"rows":14,"rows_with_code":14,"rows_with_paper_page":14,"rows_dated":14,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"BEiT-3","metrics":{"Accuracy":"92.58"},"uses_additional_data":false,"paper_date":"2022-08-22","paper":"/paper/image-as-a-foreign-language-beit-pretraining","paper_url":"https://arxiv.org/abs/2208.10442v2","paper_title":"Image as a Foreign Language: BEiT Pretraining for All Vision and Vision-Language Tasks","code":"https://github.com/microsoft/unilm/tree/master/beit","n_code_links":2,"syntology":null},{"rank_in_archive_order":2,"model":"X2-VLM (large)","metrics":{"Accuracy":"89.4"},"uses_additional_data":false,"paper_date":"2022-11-22","paper":"/paper/x-2-vlm-all-in-one-pre-trained-model-for","paper_url":"https://arxiv.org/abs/2211.12402v2","paper_title":"X$^2$-VLM: All-In-One Pre-trained Model For Vision-Language Tasks","code":"https://github.com/zengyan-97/x-vlm","n_code_links":2,"syntology":{"n_ran":2,"n_unverified":4,"n_samples":6,"n_pointer_only_licence":6}},{"rank_in_archive_order":3,"model":"XFM (base)","metrics":{"Accuracy":"88.4"},"uses_additional_data":false,"paper_date":"2023-01-12","paper":"/paper/toward-building-general-foundation-models-for","paper_url":"https://arxiv.org/abs/2301.05065v2","paper_title":"Toward Building General Foundation Models for Language, Vision, and Vision-Language Understanding Tasks","code":"https://github.com/zhangxinsong-nlp/XFM","n_code_links":1,"syntology":null},{"rank_in_archive_order":4,"model":"CoCa","metrics":{"Accuracy":"87.0"},"uses_additional_data":false,"paper_date":"2022-05-04","paper":"/paper/coca-contrastive-captioners-are-image-text","paper_url":"https://arxiv.org/abs/2205.01917v2","paper_title":"CoCa: Contrastive Captioners are Image-Text Foundation Models","code":"https://github.com/mlfoundations/open_clip","n_code_links":6,"syntology":{"n_ran":9,"n_unverified":8,"n_samples":17,"n_pointer_only_licence":0}},{"rank_in_archive_order":5,"model":"X2-VLM (base)","metrics":{"Accuracy":"87.0"},"uses_additional_data":false,"paper_date":"2022-11-22","paper":"/paper/x-2-vlm-all-in-one-pre-trained-model-for","paper_url":"https://arxiv.org/abs/2211.12402v2","paper_title":"X$^2$-VLM: All-In-One Pre-trained Model For Vision-Language Tasks","code":"https://github.com/zengyan-97/x-vlm","n_code_links":2,"syntology":{"n_ran":2,"n_unverified":4,"n_samples":6,"n_pointer_only_licence":6}},{"rank_in_archive_order":6,"model":"VLMo","metrics":{"Accuracy":"86.86"},"uses_additional_data":false,"paper_date":"2021-11-03","paper":"/paper/vlmo-unified-vision-language-pre-training","paper_url":"https://arxiv.org/abs/2111.02358v2","paper_title":"VLMo: Unified Vision-Language Pre-Training with Mixture-of-Modality-Experts","code":"https://github.com/microsoft/unilm/tree/master/vlmo","n_code_links":2,"syntology":null},{"rank_in_archive_order":7,"model":"SimVLM","metrics":{"Accuracy":"85.15"},"uses_additional_data":false,"paper_date":"2021-08-24","paper":"/paper/simvlm-simple-visual-language-model","paper_url":"https://arxiv.org/abs/2108.10904v3","paper_title":"SimVLM: Simple Visual Language Model Pretraining with Weak Supervision","code":"https://github.com/yulong-XJTU/SimVLM","n_code_links":2,"syntology":{"n_ran":18,"n_unverified":19,"n_samples":37,"n_pointer_only_licence":28}},{"rank_in_archive_order":8,"model":"X-VLM (base)","metrics":{"Accuracy":"84.76"},"uses_additional_data":false,"paper_date":"2021-11-16","paper":"/paper/multi-grained-vision-language-pre-training","paper_url":"https://arxiv.org/abs/2111.08276v3","paper_title":"Multi-Grained Vision Language Pre-Training: Aligning Texts with Visual Concepts","code":"https://github.com/zengyan-97/x-vlm","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":9,"model":"BLIP-129M","metrics":{"Accuracy":"83.09"},"uses_additional_data":false,"paper_date":"2022-01-28","paper":"/paper/blip-bootstrapping-language-image-pre","paper_url":"https://arxiv.org/abs/2201.12086v2","paper_title":"BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation","code":"https://github.com/huggingface/transformers","n_code_links":9,"syntology":null},{"rank_in_archive_order":10,"model":"ALBEF (14M)","metrics":{"Accuracy":"82.55"},"uses_additional_data":false,"paper_date":"2021-07-16","paper":"/paper/align-before-fuse-vision-and-language","paper_url":"https://arxiv.org/abs/2107.07651v2","paper_title":"Align before Fuse: Vision and Language Representation Learning with Momentum Distillation","code":"https://github.com/salesforce/lavis","n_code_links":6,"syntology":{"n_ran":3,"n_unverified":2,"n_samples":5,"n_pointer_only_licence":3}},{"rank_in_archive_order":11,"model":"UNITER (Large)","metrics":{"Accuracy":"79.5"},"uses_additional_data":false,"paper_date":"2019-09-25","paper":"/paper/uniter-learning-universal-image-text-1","paper_url":"https://arxiv.org/abs/1909.11740v3","paper_title":"UNITER: UNiversal Image-TExt Representation Learning","code":"https://github.com/ChenRocks/UNITER","n_code_links":7,"syntology":{"n_ran":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":2}},{"rank_in_archive_order":12,"model":"SOHO","metrics":{"Accuracy":"77.32"},"uses_additional_data":false,"paper_date":"2021-04-07","paper":"/paper/seeing-out-of-the-box-end-to-end-pre-training","paper_url":"https://arxiv.org/abs/2104.03135v2","paper_title":"Seeing Out of tHe bOx: End-to-End Pre-training for Vision-Language Representation Learning","code":"https://github.com/researchmm/soho","n_code_links":3,"syntology":null},{"rank_in_archive_order":13,"model":"LXMERT","metrics":{"Accuracy":"76.2"},"uses_additional_data":false,"paper_date":"2019-08-20","paper":"/paper/lxmert-learning-cross-modality-encoder","paper_url":"https://arxiv.org/abs/1908.07490v3","paper_title":"LXMERT: Learning Cross-Modality Encoder Representations from Transformers","code":"https://github.com/huggingface/transformers","n_code_links":9,"syntology":{"n_ran":4,"n_unverified":11,"n_samples":15,"n_pointer_only_licence":3}},{"rank_in_archive_order":14,"model":"ViLT-B/32","metrics":{"Accuracy":"76.13"},"uses_additional_data":false,"paper_date":"2021-02-05","paper":"/paper/vilt-vision-and-language-transformer-without","paper_url":"https://arxiv.org/abs/2102.03334v2","paper_title":"ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision","code":"https://github.com/huggingface/transformers","n_code_links":6,"syntology":{"n_ran":1,"n_unverified":3,"n_samples":4,"n_pointer_only_licence":1}}],"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 6,264 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":6264,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"papers_not_yet_extracted":3316},"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":9,"rows_with_any_sample_ran":9,"distinct_papers_with_graph_line":8,"distinct_papers_with_any_sample_ran":8,"samples_over_distinct_papers":{"n_ran":41,"n_unverified":47,"n_samples":88,"n_pointer_only_licence":43,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":43,"n_unverified":51,"n_samples":94,"n_pointer_only_licence":49,"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"}}}