{"url":"/dataset/chartqa","name":"ChartQA","full_name":null,"description_markdown":"Charts are very popular for analyzing data. When exploring charts, people often ask a variety of complex reasoning questions that involve several logical and arithmetic operations. They also commonly refer to visual features of a chart in their questions. However, most existing datasets do not focus on such complex reasoning questions as their questions are template-based and answers come from a fixed-vocabulary. In this work, we present a large-scale benchmark covering 9.6K human-written questions as well as 23.1K questions generated from human-written chart summaries. To address the unique challenges in our benchmark involving visual and logical reasoning over charts, we present two transformer-based models that combine visual features and the data table of the chart in a unified way to answer questions. While our models achieve the state-of-the-art results on the previous datasets as well as on our benchmark, the evaluation also reveals several challenges in answering complex reasoning questions.","description_withheld":null,"homepage":"https://github.com/vis-nlp/ChartQA","introduced_date":"2022-03-19","introduced_date_note":null,"introduced_by":{"paper":"/paper/chartqa-a-benchmark-for-question-answering","title":"ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoning","first_author":"Ahmed Masry","url":null},"license":null,"modalities":[],"tasks":[{"name":"Chart Question Answering","url":"/task/chart-question-answering","datasets_with_task":"/datasets/task/chart-question-answering"}],"languages":[],"variants":["ChartQA"],"data_loaders":[],"num_papers_in_archive":278,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/chart-question-answering-on-chartqa","task":"Chart Question Answering","dataset_variant":"ChartQA","rows":27,"metrics":["1:1 Accuracy"],"first_row_in_archive_order":{"model":"ChartPaLI-5B + PaLM 2-S","paper":"/paper/chart-based-reasoning-transferring","metrics":{"1:1 Accuracy":"81.3"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/chart-based-reasoning-transferring","title":"Chart-based Reasoning: Transferring Capabilities from LLMs to VLMs","date":"2024-03-19","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/screenai-a-vision-language-model-for-ui-and","title":"ScreenAI: A Vision-Language Model for UI and Infographics Understanding","date":"2024-02-07","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"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":1,"code_links":0,"syntology":null},{"paper":"/paper/gemini-a-family-of-highly-capable-multimodal-1","title":"Gemini: A Family of Highly Capable Multimodal Models","date":"2023-12-19","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/omni-smola-boosting-generalist-multimodal","title":"Omni-SMoLA: Boosting Generalist Multimodal Models with Soft Mixture of Low-rank Experts","date":"2023-12-01","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/pali-3-vision-language-models-smaller-faster","title":"PaLI-3 Vision Language Models: Smaller, Faster, Stronger","date":"2023-10-13","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":3,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/structchart-perception-structuring-reasoning","title":"StructChart: On the Schema, Metric, and Augmentation for Visual Chart Understanding","date":"2023-09-20","rows_on_this_dataset":2,"code_links":3,"syntology":null},{"paper":"/paper/qwen-vl-a-frontier-large-vision-language","title":"Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond","date":"2023-08-24","rows_on_this_dataset":2,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":2,"samples_ran":0,"samples_unverified":2,"pointer_only_for_licence":2,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/pali-x-on-scaling-up-a-multilingual-vision","title":"PaLI-X: On Scaling up a Multilingual Vision and Language Model","date":"2023-05-29","rows_on_this_dataset":3,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":7,"samples_ran":6,"samples_unverified":1,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/unichart-a-universal-vision-language","title":"UniChart: A Universal Vision-language Pretrained Model for Chart Comprehension and Reasoning","date":"2023-05-24","rows_on_this_dataset":1,"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/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":6,"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":1,"code_links":1,"syntology":null},{"paper":"/paper/pix2struct-screenshot-parsing-as-pretraining","title":"Pix2Struct: Screenshot Parsing as Pretraining for Visual Language Understanding","date":"2022-10-07","rows_on_this_dataset":2,"code_links":4,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":5,"samples_ran":0,"samples_unverified":5,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"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":1,"code_links":1,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":5,"samples_harvested":18,"samples_ran":10,"samples_unverified":8,"pointer_only_for_licence":2,"papers_with_no_sample_that_ran":2,"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."}