{"url":"/dataset/plotqa","name":"PlotQA","full_name":null,"description_markdown":"PlotQA is a VQA dataset with 28.9 million question-answer pairs grounded over 224,377 plots on data from real-world sources and questions based on crowd-sourced question templates.\r\nExisting synthetic datasets (FigureQA, DVQA) for reasoning over plots do not contain variability in data labels, real-valued data, or complex reasoning questions. Consequently, proposed models for these datasets do not fully address the challenge of reasoning over plots. In particular, they assume that the answer comes either from a small fixed size vocabulary or from a bounding box within the image. However, in practice this is an unrealistic assumption because many questions require reasoning and thus have real valued answers which appear neither in a small fixed size vocabulary nor in the image. In this work, we aim to bridge this gap between existing datasets and real world plots by introducing PlotQA. Further, 80.76% of the out-of-vocabulary (OOV) questions in PlotQA have answers that are not in a fixed vocabulary.","description_withheld":null,"homepage":"https://github.com/NiteshMethani/PlotQA","introduced_date":"2019-09-03","introduced_date_note":null,"introduced_by":{"paper":"/paper/data-interpretation-over-plots","title":"PlotQA: Reasoning over Scientific Plots","first_author":"Nitesh Methani","url":null},"license":{"name":"public","url":"https://arxiv.org/licenses/nonexclusive-distrib/1.0/license.html"},"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Question Answering","url":"/task/question-answering","datasets_with_task":"/datasets/task/question-answering"},{"name":"Visual Question Answering (VQA)","url":"/task/visual-question-answering","datasets_with_task":"/datasets/task/visual-question-answering"},{"name":"Visual Question Answering","url":"/task/visual-question-answering-1","datasets_with_task":"/datasets/task/visual-question-answering-1"},{"name":"Chart Question Answering","url":"/task/chart-question-answering","datasets_with_task":"/datasets/task/chart-question-answering"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["PlotQA","PlotQA-D1","PlotQA-D2"],"data_loaders":[],"num_papers_in_archive":50,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/chart-question-answering-on-plotqa","task":"Chart Question Answering","dataset_variant":"PlotQA","rows":6,"metrics":["1:1 Accuracy"],"first_row_in_archive_order":{"model":"MatCha4096 + LaMenDa","paper":"/paper/synthesize-step-by-step-tools-templates-and-1","metrics":{"1:1 Accuracy":"92.89"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/visual-question-answering-on-plotqa-d1","task":"Visual Question Answering (VQA)","dataset_variant":"PlotQA-D1","rows":4,"metrics":["1:1 Accuracy"],"first_row_in_archive_order":{"model":"MatCha4096 + LaMenDa","paper":"/paper/synthesize-step-by-step-tools-templates-and-1","metrics":{"1:1 Accuracy":"93.94"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/visual-question-answering-on-plotqa-d2","task":"Visual Question Answering (VQA)","dataset_variant":"PlotQA-D2","rows":4,"metrics":["1:1 Accuracy"],"first_row_in_archive_order":{"model":"MatCha4096 + LaMenDa","paper":"/paper/synthesize-step-by-step-tools-templates-and-1","metrics":{"1:1 Accuracy":"91.84"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/visual-question-answering-on-plotqa-d1-1","task":"Visual Question Answering","dataset_variant":"PlotQA-D1","rows":2,"metrics":["1:1 Accuracy"],"first_row_in_archive_order":{"model":"MatCha4096 + LaMenDa","paper":"/paper/synthesize-step-by-step-tools-templates-and-1","metrics":{"1:1 Accuracy":"93.94"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/visual-question-answering-on-plotqa-d2-1","task":"Visual Question Answering","dataset_variant":"PlotQA-D2","rows":2,"metrics":["1:1 Accuracy"],"first_row_in_archive_order":{"model":"MatCha4096 + LaMenDa","paper":"/paper/synthesize-step-by-step-tools-templates-and-1","metrics":{"1:1 Accuracy":"91.84"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/synthesize-step-by-step-tools-templates-and-1","title":"Synthesize Step-by-Step: Tools Templates and LLMs as Data Generators for Reasoning-Based Chart VQA","date":"2024-01-01","rows_on_this_dataset":5,"code_links":0,"syntology":null},{"paper":"/paper/deplot-one-shot-visual-language-reasoning-by","title":"DePlot: One-shot visual language reasoning by plot-to-table translation","date":"2022-12-20","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/matcha-enhancing-visual-language-pretraining","title":"MatCha: Enhancing Visual Language Pretraining with Math Reasoning and Chart Derendering","date":"2022-12-19","rows_on_this_dataset":3,"code_links":1,"syntology":null},{"paper":"/paper/chartqa-a-benchmark-for-question-answering","title":"ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoning","date":"2022-03-19","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/classification-regression-for-chart","title":"Classification-Regression for Chart Comprehension","date":"2021-11-29","rows_on_this_dataset":3,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":1,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/data-interpretation-over-plots","title":"PlotQA: Reasoning over Scientific Plots","date":"2019-09-03","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/answering-questions-about-data-visualizations","title":"Answering Questions about Data Visualizations using Efficient Bimodal Fusion","date":"2019-08-05","rows_on_this_dataset":2,"code_links":1,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":1,"samples_harvested":1,"samples_ran":1,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}