{"url":"/sota/visual-question-answering-on-vqa-v2-test-dev-1","task":{"name":"Visual Question Answering","url":"/task/visual-question-answering-1","note":null},"dataset":{"name":"VQA v2 test-dev","url":"/dataset/visual-question-answering-v2-0"},"category":"Computer Vision","categories":["Computer Vision","Natural Language Processing"],"category_note":null,"description":"MLLM Leaderboard","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":11,"rows_with_code":10,"rows_with_paper_page":10,"rows_dated":10,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"BLIP-2 ViT-G OPT 6.7B (fine-tuned)","metrics":{"Accuracy":"82.30"},"uses_additional_data":false,"paper_date":"2023-01-30","paper":"/paper/blip-2-bootstrapping-language-image-pre","paper_url":"https://arxiv.org/abs/2301.12597v3","paper_title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","code":"https://github.com/huggingface/transformers","n_code_links":17,"syntology":{"n_ran":4,"n_unverified":4,"n_samples":8,"n_pointer_only_licence":1}},{"rank_in_archive_order":2,"model":"CoCa","metrics":{"Accuracy":"82.3"},"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":3,"model":"OFA","metrics":{"Accuracy":"82.0"},"uses_additional_data":false,"paper_date":"2022-02-07","paper":"/paper/unifying-architectures-tasks-and-modalities","paper_url":"https://arxiv.org/abs/2202.03052v2","paper_title":"OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework","code":"https://github.com/modelscope/modelscope","n_code_links":4,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":4,"model":"BLIP-2 ViT-G OPT 2.7B (fine-tuned)","metrics":{"Accuracy":"81.74"},"uses_additional_data":false,"paper_date":"2023-01-30","paper":"/paper/blip-2-bootstrapping-language-image-pre","paper_url":"https://arxiv.org/abs/2301.12597v3","paper_title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","code":"https://github.com/huggingface/transformers","n_code_links":17,"syntology":{"n_ran":4,"n_unverified":4,"n_samples":8,"n_pointer_only_licence":1}},{"rank_in_archive_order":5,"model":"BLIP-2 ViT-G FlanT5 XL (fine-tuned)","metrics":{"Accuracy":"81.66"},"uses_additional_data":false,"paper_date":"2023-01-30","paper":"/paper/blip-2-bootstrapping-language-image-pre","paper_url":"https://arxiv.org/abs/2301.12597v3","paper_title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","code":"https://github.com/huggingface/transformers","n_code_links":17,"syntology":{"n_ran":4,"n_unverified":4,"n_samples":8,"n_pointer_only_licence":1}},{"rank_in_archive_order":6,"model":"mPLUG-2","metrics":{"Accuracy":"81.11"},"uses_additional_data":false,"paper_date":"2023-02-01","paper":"/paper/mplug-2-a-modularized-multi-modal-foundation","paper_url":"https://arxiv.org/abs/2302.00402v1","paper_title":"mPLUG-2: A Modularized Multi-modal Foundation Model Across Text, Image and Video","code":"https://github.com/modelscope/modelscope","n_code_links":4,"syntology":{"n_ran":9,"n_unverified":10,"n_samples":19,"n_pointer_only_licence":0}},{"rank_in_archive_order":7,"model":"Florence","metrics":{"Accuracy":"80.16"},"uses_additional_data":false,"paper_date":"2021-11-22","paper":"/paper/florence-a-new-foundation-model-for-computer","paper_url":"https://arxiv.org/abs/2111.11432v1","paper_title":"Florence: A New Foundation Model for Computer Vision","code":"https://github.com/microsoft/unicl","n_code_links":2,"syntology":null},{"rank_in_archive_order":8,"model":"Aurora (ours, r=64)","metrics":{"Accuracy":"77.69"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":9,"model":"VK-OOD","metrics":{"Accuracy":"76.8"},"uses_additional_data":false,"paper_date":"2023-02-11","paper":"/paper/differentiable-outlier-detection-enable","paper_url":"https://arxiv.org/abs/2302.05608v1","paper_title":"Differentiable Outlier Detection Enable Robust Deep Multimodal Analysis","code":"https://github.com/ellenzhuwang/VK_OOD","n_code_links":1,"syntology":null},{"rank_in_archive_order":10,"model":"LXMERT (low-magnitude pruning)","metrics":{"Accuracy":"70.72"},"uses_additional_data":false,"paper_date":"2023-10-23","paper":"/paper/lxmert-model-compression-for-visual-question","paper_url":"https://arxiv.org/abs/2310.15325v1","paper_title":"LXMERT Model Compression for Visual Question Answering","code":"https://github.com/ghazaleh-mahmoodi/lxmert_compression","n_code_links":2,"syntology":null},{"rank_in_archive_order":11,"model":"LocVLM-L","metrics":{"Accuracy":"56.2"},"uses_additional_data":false,"paper_date":"2024-04-11","paper":"/paper/learning-to-localize-objects-improves-spatial","paper_url":"https://arxiv.org/abs/2404.07449v1","paper_title":"Learning to Localize Objects Improves Spatial Reasoning in Visual-LLMs","code":"https://github.com/kahnchana/locvlm","n_code_links":1,"syntology":null}],"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":6,"rows_with_any_sample_ran":6,"distinct_papers_with_graph_line":4,"distinct_papers_with_any_sample_ran":4,"samples_over_distinct_papers":{"n_ran":23,"n_unverified":22,"n_samples":45,"n_pointer_only_licence":1,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":31,"n_unverified":30,"n_samples":61,"n_pointer_only_licence":3,"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"}}}