{"task":"Chart Question Answering","dataset":"PlotQA","metric_names":["1:1 Accuracy"],"rows":[{"id":26563,"task":"Chart Question Answering","parent_task":"Visual Question Answering (VQA)","dataset":"PlotQA","model_name":"MatCha4096 + LaMenDa","metrics":{"1:1 Accuracy":"92.89"},"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","paper_date":"2024-01-01","code_links":[],"metrics_order":"[\"1:1 Accuracy\"]","area":"Computer Code","uses_additional_data":0,"source":"archive","tags":[]},{"id":26564,"task":"Chart Question Answering","parent_task":"Visual Question Answering (VQA)","dataset":"PlotQA","model_name":"MatCha","metrics":{"1:1 Accuracy":"91.5"},"paper_url":"https://arxiv.org/abs/2212.09662v2","paper_title":"MatCha: Enhancing Visual Language Pretraining with Math Reasoning and Chart Derendering","paper_date":"2022-12-19","code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"}],"metrics_order":"[\"1:1 Accuracy\"]","area":"Computer Code","uses_additional_data":0,"source":"archive","tags":[]},{"id":26565,"task":"Chart Question Answering","parent_task":"Visual Question Answering (VQA)","dataset":"PlotQA","model_name":"DePlot+FlanPaLM+Codex\n(PoT Self-Consistency)","metrics":{"1:1 Accuracy":"66.6"},"paper_url":"https://arxiv.org/abs/2212.10505v2","paper_title":"DePlot: One-shot visual language reasoning by plot-to-table translation","paper_date":"2022-12-20","code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"}],"metrics_order":"[\"1:1 Accuracy\"]","area":"Computer Code","uses_additional_data":0,"source":"archive","tags":[]},{"id":26566,"task":"Chart Question Answering","parent_task":"Visual Question Answering (VQA)","dataset":"PlotQA","model_name":"VL-T5-OCR","metrics":{"1:1 Accuracy":"66.0"},"paper_url":"https://arxiv.org/abs/2203.10244v1","paper_title":"ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoning","paper_date":"2022-03-19","code_links":[{"title":"vis-nlp/chartqa","url":"https://github.com/vis-nlp/chartqa"}],"metrics_order":"[\"1:1 Accuracy\"]","area":"Computer Code","uses_additional_data":0,"source":"archive","tags":[]},{"id":26567,"task":"Chart Question Answering","parent_task":"Visual Question Answering (VQA)","dataset":"PlotQA","model_name":"CRCT","metrics":{"1:1 Accuracy":"55.7"},"paper_url":"https://arxiv.org/abs/2111.14792v2","paper_title":"Classification-Regression for Chart Comprehension","paper_date":"2021-11-29","code_links":[{"title":"levymsn/cqa-crct","url":"https://github.com/levymsn/cqa-crct"}],"metrics_order":"[\"1:1 Accuracy\"]","area":"Computer Code","uses_additional_data":0,"source":"archive","tags":[]},{"id":26568,"task":"Chart Question Answering","parent_task":"Visual Question Answering (VQA)","dataset":"PlotQA","model_name":"VisionTapas-OCR","metrics":{"1:1 Accuracy":"53.9"},"paper_url":"https://arxiv.org/abs/2203.10244v1","paper_title":"ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoning","paper_date":"2022-03-19","code_links":[{"title":"vis-nlp/chartqa","url":"https://github.com/vis-nlp/chartqa"}],"metrics_order":"[\"1:1 Accuracy\"]","area":"Computer Code","uses_additional_data":0,"source":"archive","tags":[]},{"id":128628,"task":"Chart Question Answering","parent_task":null,"dataset":"PlotQA","model_name":"MatCha4096 + LaMenDa","metrics":{"1:1 Accuracy":"92.89"},"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","paper_date":"2024-01-01","code_links":[],"metrics_order":"[\"1:1 Accuracy\"]","area":"Computer Code","uses_additional_data":0,"source":"archive","tags":[]},{"id":128629,"task":"Chart Question Answering","parent_task":null,"dataset":"PlotQA","model_name":"MatCha","metrics":{"1:1 Accuracy":"91.5"},"paper_url":"https://arxiv.org/abs/2212.09662v2","paper_title":"MatCha: Enhancing Visual Language Pretraining with Math Reasoning and Chart Derendering","paper_date":"2022-12-19","code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"}],"metrics_order":"[\"1:1 Accuracy\"]","area":"Computer Code","uses_additional_data":0,"source":"archive","tags":[]},{"id":128630,"task":"Chart Question Answering","parent_task":null,"dataset":"PlotQA","model_name":"DePlot+FlanPaLM+Codex\n(PoT Self-Consistency)","metrics":{"1:1 Accuracy":"66.6"},"paper_url":"https://arxiv.org/abs/2212.10505v2","paper_title":"DePlot: One-shot visual language reasoning by plot-to-table translation","paper_date":"2022-12-20","code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"}],"metrics_order":"[\"1:1 Accuracy\"]","area":"Computer Code","uses_additional_data":0,"source":"archive","tags":[]},{"id":128631,"task":"Chart Question Answering","parent_task":null,"dataset":"PlotQA","model_name":"VL-T5-OCR","metrics":{"1:1 Accuracy":"66.0"},"paper_url":"https://arxiv.org/abs/2203.10244v1","paper_title":"ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoning","paper_date":"2022-03-19","code_links":[{"title":"vis-nlp/chartqa","url":"https://github.com/vis-nlp/chartqa"}],"metrics_order":"[\"1:1 Accuracy\"]","area":"Computer Code","uses_additional_data":0,"source":"archive","tags":[]},{"id":128632,"task":"Chart Question Answering","parent_task":null,"dataset":"PlotQA","model_name":"CRCT","metrics":{"1:1 Accuracy":"55.7"},"paper_url":"https://arxiv.org/abs/2111.14792v2","paper_title":"Classification-Regression for Chart Comprehension","paper_date":"2021-11-29","code_links":[{"title":"levymsn/cqa-crct","url":"https://github.com/levymsn/cqa-crct"}],"metrics_order":"[\"1:1 Accuracy\"]","area":"Computer Code","uses_additional_data":0,"source":"archive","tags":[]},{"id":128633,"task":"Chart Question Answering","parent_task":null,"dataset":"PlotQA","model_name":"VisionTapas-OCR","metrics":{"1:1 Accuracy":"53.9"},"paper_url":"https://arxiv.org/abs/2203.10244v1","paper_title":"ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoning","paper_date":"2022-03-19","code_links":[{"title":"vis-nlp/chartqa","url":"https://github.com/vis-nlp/chartqa"}],"metrics_order":"[\"1:1 Accuracy\"]","area":"Computer Code","uses_additional_data":0,"source":"archive","tags":[]}]}