{"url":"/sota/visual-question-answering-on-gqa-test-dev","task":{"name":"Visual Question Answering (VQA)","url":"/task/visual-question-answering","note":null},"dataset":{"name":"GQA test-dev","url":"/dataset/gqa"},"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":["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":17,"rows_with_code":15,"rows_with_paper_page":17,"rows_dated":17,"rows_using_additional_data":1},"rows":[{"rank_in_archive_order":1,"model":"CFR","metrics":{"Accuracy":"72.1"},"uses_additional_data":false,"paper_date":"2021-10-06","paper":"/paper/coarse-to-fine-reasoning-for-visual-question","paper_url":"https://arxiv.org/abs/2110.02526v2","paper_title":"Coarse-to-Fine Reasoning for Visual Question Answering","code":"https://github.com/aioz-ai/cfr_vqa","n_code_links":2,"syntology":{"n_ran":4,"n_unverified":5,"n_samples":9,"n_pointer_only_licence":0}},{"rank_in_archive_order":2,"model":"PaLI-X-VPD","metrics":{"Accuracy":"67.3"},"uses_additional_data":false,"paper_date":"2023-12-05","paper":"/paper/visual-program-distillation-distilling-tools","paper_url":"https://arxiv.org/abs/2312.03052v2","paper_title":"Visual Program Distillation: Distilling Tools and Programmatic Reasoning into Vision-Language Models","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":3,"model":"CuMo-7B","metrics":{"Accuracy":"64.9"},"uses_additional_data":true,"paper_date":"2024-05-09","paper":"/paper/cumo-scaling-multimodal-llm-with-co-upcycled","paper_url":"https://arxiv.org/abs/2405.05949v1","paper_title":"CuMo: Scaling Multimodal LLM with Co-Upcycled Mixture-of-Experts","code":"https://github.com/shi-labs/cumo","n_code_links":1,"syntology":{"n_ran":10,"n_unverified":2,"n_samples":12,"n_pointer_only_licence":0}},{"rank_in_archive_order":4,"model":"Video-LaVIT","metrics":{"Accuracy":"64.4"},"uses_additional_data":false,"paper_date":"2024-02-05","paper":"/paper/video-lavit-unified-video-language-pre","paper_url":"https://arxiv.org/abs/2402.03161v3","paper_title":"Video-LaVIT: Unified Video-Language Pre-training with Decoupled Visual-Motional Tokenization","code":"https://github.com/jy0205/lavit","n_code_links":1,"syntology":{"n_ran":3,"n_unverified":2,"n_samples":5,"n_pointer_only_licence":5}},{"rank_in_archive_order":5,"model":"NSM","metrics":{"Accuracy":"62.95"},"uses_additional_data":false,"paper_date":"2019-07-09","paper":"/paper/learning-by-abstraction-the-neural-state","paper_url":"https://arxiv.org/abs/1907.03950v4","paper_title":"Learning by Abstraction: The Neural State Machine","code":"https://github.com/stanfordnlp/mac-network","n_code_links":4,"syntology":{"n_ran":3,"n_unverified":18,"n_samples":21,"n_pointer_only_licence":2}},{"rank_in_archive_order":6,"model":"Lyrics","metrics":{"Accuracy":"62.4"},"uses_additional_data":false,"paper_date":"2023-12-08","paper":"/paper/lyrics-boosting-fine-grained-language-vision","paper_url":"https://arxiv.org/abs/2312.05278v2","paper_title":"Lyrics: Boosting Fine-grained Language-Vision Alignment and Comprehension via Semantic-aware Visual Objects","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":7,"model":"LXMERT (Pre-train + scratch)","metrics":{"Accuracy":"60.0"},"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":8,"model":"single-hop + LCGN (ours)","metrics":{"Accuracy":"55.8"},"uses_additional_data":false,"paper_date":"2019-05-10","paper":"/paper/language-conditioned-graph-networks-for","paper_url":"https://arxiv.org/abs/1905.04405v2","paper_title":"Language-Conditioned Graph Networks for Relational Reasoning","code":"https://github.com/ronghanghu/lcgn","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":10,"n_samples":10,"n_pointer_only_licence":0}},{"rank_in_archive_order":9,"model":"HYDRA","metrics":{"Accuracy":"47.9"},"uses_additional_data":false,"paper_date":"2024-03-19","paper":"/paper/hydra-a-hyper-agent-for-dynamic-compositional","paper_url":"https://arxiv.org/abs/2403.12884v2","paper_title":"HYDRA: A Hyper Agent for Dynamic Compositional Visual Reasoning","code":"https://github.com/ControlNet/HYDRA","n_code_links":1,"syntology":{"n_ran":5,"n_unverified":3,"n_samples":8,"n_pointer_only_licence":0}},{"rank_in_archive_order":10,"model":"BLIP-2 ViT-G FlanT5 XXL (zero-shot)","metrics":{"Accuracy":"44.7"},"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":11,"model":"BLIP-2 ViT-L FlanT5 XL (zero-shot)","metrics":{"Accuracy":"44.4"},"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":12,"model":"BLIP-2 ViT-G FlanT5 XL (zero-shot)","metrics":{"Accuracy":"44.2"},"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":"PNP-VQA","metrics":{"Accuracy":"41.9"},"uses_additional_data":false,"paper_date":"2022-10-17","paper":"/paper/plug-and-play-vqa-zero-shot-vqa-by-conjoining","paper_url":"https://arxiv.org/abs/2210.08773v3","paper_title":"Plug-and-Play VQA: Zero-shot VQA by Conjoining Large Pretrained Models with Zero Training","code":"https://github.com/salesforce/lavis","n_code_links":3,"syntology":{"n_ran":2,"n_unverified":1,"n_samples":3,"n_pointer_only_licence":3}},{"rank_in_archive_order":14,"model":"BLIP-2 ViT-G OPT 6.7B (zero-shot)","metrics":{"Accuracy":"36.4"},"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":15,"model":"BLIP-2 ViT-G OPT 2.7B (zero-shot)","metrics":{"Accuracy":"34.6"},"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":16,"model":"BLIP-2 ViT-L OPT 2.7B (zero-shot)","metrics":{"Accuracy":"33.9"},"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":17,"model":"FewVLM (zero-shot)","metrics":{"Accuracy":"29.3"},"uses_additional_data":false,"paper_date":"2021-10-16","paper":"/paper/a-good-prompt-is-worth-millions-of-parameters","paper_url":"https://arxiv.org/abs/2110.08484v2","paper_title":"A Good Prompt Is Worth Millions of Parameters: Low-resource Prompt-based Learning for Vision-Language Models","code":"https://github.com/woojeongjin/fewvlm","n_code_links":1,"syntology":null}],"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":14,"rows_with_any_sample_ran":13,"distinct_papers_with_graph_line":9,"distinct_papers_with_any_sample_ran":8,"samples_over_distinct_papers":{"n_ran":35,"n_unverified":56,"n_samples":91,"n_pointer_only_licence":14,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":55,"n_unverified":76,"n_samples":131,"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"}}}