{"url":"/sota/visual-question-answering-vqa-on-core-mm","task":{"name":"Visual Question Answering (VQA)","url":"/task/visual-question-answering","note":null},"dataset":{"name":"InfiMM-Eval","url":"/dataset/core-mm"},"category":"Computer Vision","categories":["Computer Vision","Natural Language Processing"],"category_note":null,"description":"**Visual Question Answering (VQA)** is a task in computer vision that involves answering questions about an image. The goal of VQA is to teach machines to understand the content of an image and answer questions about it in natural language.\r\n\r\nImage Source: [visualqa.org](https://visualqa.org/)","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":["Overall score","Deductive","Abductive","Analogical","Params"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"Overall score":"higher","Deductive":null,"Abductive":null,"Analogical":null,"Params":"lower"}},"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":"GPT-4V","metrics":{"Abductive":"77.88","Analogical":"69.86","Deductive":"74.86","Overall score":"74.44"},"uses_additional_data":false,"paper_date":"2023-03-15","paper":"/paper/gpt-4-technical-report-1","paper_url":"https://arxiv.org/abs/2303.08774v5","paper_title":"GPT-4 Technical Report","code":"https://github.com/openai/evals","n_code_links":11,"syntology":{"n_ran":5,"n_unverified":0,"n_samples":5,"n_pointer_only_licence":1}},{"rank_in_archive_order":2,"model":"SPHINX v2","metrics":{"Abductive":"49.85","Analogical":"20.69","Deductive":"42.17","Overall score":"39.48","Params":"16B"},"uses_additional_data":false,"paper_date":"2023-11-13","paper":"/paper/sphinx-the-joint-mixing-of-weights-tasks-and","paper_url":"https://arxiv.org/abs/2311.07575v1","paper_title":"SPHINX: The Joint Mixing of Weights, Tasks, and Visual Embeddings for Multi-modal Large Language Models","code":"https://github.com/alpha-vllm/llama2-accessory","n_code_links":1,"syntology":{"n_ran":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":3}},{"rank_in_archive_order":3,"model":"Qwen-VL-Chat","metrics":{"Abductive":"44.39","Analogical":"30.42","Deductive":"37.55","Overall score":"37.39","Params":"16B"},"uses_additional_data":false,"paper_date":"2023-08-24","paper":"/paper/qwen-vl-a-frontier-large-vision-language","paper_url":"https://arxiv.org/abs/2308.12966v3","paper_title":"Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond","code":"https://github.com/qwenlm/qwen-vl","n_code_links":2,"syntology":{"n_ran":0,"n_unverified":2,"n_samples":2,"n_pointer_only_licence":2}},{"rank_in_archive_order":4,"model":"CogVLM-Chat","metrics":{"Abductive":"47.88","Analogical":"28.75","Deductive":"36.75","Overall score":"37.16","Params":"17B"},"uses_additional_data":false,"paper_date":"2023-11-06","paper":"/paper/cogvlm-visual-expert-for-pretrained-language","paper_url":"https://arxiv.org/abs/2311.03079v2","paper_title":"CogVLM: Visual Expert for Pretrained Language Models","code":"https://github.com/thudm/cogvlm","n_code_links":4,"syntology":null},{"rank_in_archive_order":5,"model":"LLaVA-1.5","metrics":{"Abductive":"47.91","Analogical":"24.31","Deductive":"30.94","Overall score":"32.62","Params":"13B"},"uses_additional_data":false,"paper_date":"2023-10-05","paper":"/paper/improved-baselines-with-visual-instruction","paper_url":"https://arxiv.org/abs/2310.03744v2","paper_title":"Improved Baselines with Visual Instruction Tuning","code":"https://github.com/huggingface/transformers","n_code_links":9,"syntology":{"n_ran":6,"n_unverified":3,"n_samples":9,"n_pointer_only_licence":8}},{"rank_in_archive_order":6,"model":"LLaMA-Adapter V2","metrics":{"Abductive":"46.12","Analogical":"22.08","Deductive":"28.7","Overall score":"30.46","Params":"7B"},"uses_additional_data":false,"paper_date":"2023-04-28","paper":"/paper/llama-adapter-v2-parameter-efficient-visual","paper_url":"https://arxiv.org/abs/2304.15010v1","paper_title":"LLaMA-Adapter V2: Parameter-Efficient Visual Instruction Model","code":"https://github.com/opengvlab/llama-adapter","n_code_links":3,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":1}},{"rank_in_archive_order":7,"model":"Emu","metrics":{"Abductive":"36.57","Analogical":"18.19","Deductive":"28.9","Overall score":"28.24","Params":"14B"},"uses_additional_data":false,"paper_date":"2023-07-11","paper":"/paper/generative-pretraining-in-multimodality","paper_url":"https://arxiv.org/abs/2307.05222v2","paper_title":"Emu: Generative Pretraining in Multimodality","code":"https://github.com/baaivision/emu","n_code_links":2,"syntology":{"n_ran":0,"n_unverified":2,"n_samples":2,"n_pointer_only_licence":0}},{"rank_in_archive_order":8,"model":"InstructBLIP","metrics":{"Abductive":"37.76","Analogical":"20.56","Deductive":"27.56","Overall score":"28.02","Params":"8B"},"uses_additional_data":false,"paper_date":"2023-05-11","paper":"/paper/instructblip-towards-general-purpose-vision","paper_url":"https://arxiv.org/abs/2305.06500v2","paper_title":"InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning","code":"https://github.com/salesforce/lavis","n_code_links":4,"syntology":null},{"rank_in_archive_order":9,"model":"InternLM-XComposer-VL","metrics":{"Abductive":"35.97","Analogical":"18.61","Deductive":"26.77","Overall score":"26.84","Params":"9B"},"uses_additional_data":false,"paper_date":"2023-09-26","paper":"/paper/internlm-xcomposer-a-vision-language-large","paper_url":"https://arxiv.org/abs/2309.15112v5","paper_title":"InternLM-XComposer: A Vision-Language Large Model for Advanced Text-image Comprehension and Composition","code":"https://github.com/internlm/internlm-xcomposer","n_code_links":3,"syntology":null},{"rank_in_archive_order":10,"model":"Otter","metrics":{"Abductive":"33.64","Analogical":"13.33","Deductive":"22.49","Overall score":"22.69","Params":"7B"},"uses_additional_data":false,"paper_date":"2023-05-05","paper":"/paper/otter-a-multi-modal-model-with-in-context","paper_url":"https://arxiv.org/abs/2305.03726v1","paper_title":"Otter: A Multi-Modal Model with In-Context Instruction Tuning","code":"https://github.com/luodian/otter","n_code_links":1,"syntology":null},{"rank_in_archive_order":11,"model":"mPLUG-Owl2","metrics":{"Abductive":"20.6","Analogical":"7.64","Deductive":"23.43","Overall score":"20.05","Params":"7B"},"uses_additional_data":false,"paper_date":"2023-11-07","paper":"/paper/mplug-owl2-revolutionizing-multi-modal-large","paper_url":"https://arxiv.org/abs/2311.04257v2","paper_title":"mPLUG-Owl2: Revolutionizing Multi-modal Large Language Model with Modality Collaboration","code":"https://github.com/x-plug/mplug-owl","n_code_links":2,"syntology":{"n_ran":1,"n_unverified":2,"n_samples":3,"n_pointer_only_licence":3}},{"rank_in_archive_order":12,"model":"BLIP-2-OPT2.7B","metrics":{"Abductive":"18.96","Analogical":"7.5","Deductive":"2.76","Overall score":"19.31","Params":"3B"},"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":13,"model":"MiniGPT-v2","metrics":{"Abductive":"13.28","Analogical":"5.69","Deductive":"11.02","Overall score":"10.43","Params":"8B"},"uses_additional_data":false,"paper_date":"2023-04-20","paper":"/paper/minigpt-4-enhancing-vision-language","paper_url":"https://arxiv.org/abs/2304.10592v2","paper_title":"MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models","code":"https://github.com/vision-cair/minigpt-4","n_code_links":6,"syntology":null},{"rank_in_archive_order":14,"model":"OpenFlamingo-v2","metrics":{"Abductive":"5.3","Analogical":"1.11","Deductive":"8.88","Overall score":"6.82","Params":"9B"},"uses_additional_data":false,"paper_date":"2023-08-02","paper":"/paper/openflamingo-an-open-source-framework-for","paper_url":"https://arxiv.org/abs/2308.01390v2","paper_title":"OpenFlamingo: An Open-Source Framework for Training Large Autoregressive Vision-Language Models","code":"https://github.com/mlfoundations/open_flamingo","n_code_links":2,"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 6,885 of the 9,623 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":9623,"papers_checked":6885,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"papers_not_yet_extracted":2737},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"syntology":{"read_at":"2026-09-25T09:33:49+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":5,"distinct_papers_with_graph_line":8,"distinct_papers_with_any_sample_ran":5,"samples_over_distinct_papers":{"n_ran":19,"n_unverified":14,"n_samples":33,"n_pointer_only_licence":19,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":19,"n_unverified":14,"n_samples":33,"n_pointer_only_licence":19,"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"}}}