{"url":"/sota/visual-question-answering-on-plotqa-d1-1","task":{"name":"Visual Question Answering","url":"/task/visual-question-answering-1","note":null},"dataset":{"name":"PlotQA-D1","url":"/dataset/plotqa"},"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":["1:1 Accuracy"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"1:1 Accuracy":"higher"}},"counts":{"rows":2,"rows_with_code":1,"rows_with_paper_page":2,"rows_dated":2,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"MatCha4096 + LaMenDa","metrics":{"1:1 Accuracy":"93.94"},"uses_additional_data":false,"paper_date":"2024-01-01","paper":"/paper/synthesize-step-by-step-tools-templates-and-1","paper_url":"http://openaccess.thecvf.com//content/CVPR2024/html/Li_Synthesize_Step-by-Step_Tools_Templates_and_LLMs_as_Data_Generators_for_CVPR_2024_paper.html","paper_title":"Synthesize Step-by-Step: Tools Templates and LLMs as Data Generators for Reasoning-Based Chart VQA","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":2,"model":"MatCha","metrics":{"1:1 Accuracy":"92.3"},"uses_additional_data":false,"paper_date":"2022-12-19","paper":"/paper/matcha-enhancing-visual-language-pretraining","paper_url":"https://arxiv.org/abs/2212.09662v2","paper_title":"MatCha: Enhancing Visual Language Pretraining with Math Reasoning and Chart Derendering","code":"https://github.com/huggingface/transformers","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":0,"rows_with_any_sample_ran":0,"distinct_papers_with_graph_line":0,"distinct_papers_with_any_sample_ran":0,"samples_over_distinct_papers":{"n_ran":0,"n_unverified":0,"n_samples":0,"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":0,"n_unverified":0,"n_samples":0,"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"}}}