datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
ChartGalaxy
ChartGalaxy: A Dataset for Infographic Chart Understanding and Generation
🤗 Dataset | 🖥️ Code | 📄 Paper | 📄 Arxiv
🔥 News
[2026.09] 🎉🎉 A new high-quality batch of 14,809 synthetic infographic charts has been added.
This update features more complex layouts and richer chart variations.
[2026.02] 🎉🎉 A new batch of data has been added, comprising 108,208 infographic charts.
This update features broader diversity in title designs and more polished layouts… See the full description on the dataset page: https://huggingface.co/datasets/ChartGalaxy/ChartGalaxy.ChartQA
Dataset Card for "ChartQA"
More Information needed
ChartQA
Large-scale Multi-modality Models Evaluation Suite
Accelerating the development of large-scale multi-modality models (LMMs) with lmms-eval
🏠 Homepage | 📚 Documentation | 🤗 Huggingface Datasets
This Dataset
This is a formatted version of ChartQA. It is used in our lmms-eval pipeline to allow for one-click evaluations of large multi-modality models.
@article{masry2022chartqa,
title={ChartQA: A benchmark for question answering about charts with visual and… See the full description on the dataset page: https://huggingface.co/datasets/lmms-lab-encoder/ChartQA.ChartNet
ChartNet: A Million-Scale Multimodal Dataset for Chart Understanding
🌐 Homepage | 📖 arXiv
📝 Changelog
June 3, 2026 — Release of grounded_qa subset and completed reasoning subset (both subject to Notice Regarding Data Availability)
May 15, 2026 — Added link to 30K real-world charts and detailed captions dataset released by our collaborators Abaka AI/2077AI.
April 29, 2026 — Release of an additional 2.5 million row subset core_permissive (subject to… See the full description on the dataset page: https://huggingface.co/datasets/ibm-granite/ChartNet.ChartDiff
ChartDiff: A Large-Scale Benchmark for Comprehending Pairs of Charts
Overview
ChartDiff is a large-scale benchmark for cross-chart comparative summarization, designed to evaluate whether vision-language models can identify differences and generate coherent comparative descriptions across pairs of charts.
Unlike existing chart understanding datasets that emphasize single-chart interpretation, ChartDiff requires models to compare two charts jointly and generate a concise… See the full description on the dataset page: https://huggingface.co/datasets/ckchaos/ChartDiff.Chart2CodeFrom Charts to Code: A Hierarchical Benchmark for Multimodal Models
Welcome to Chart2Code! If you find this repo useful, please give a star ⭐ for encouragement.
Data Overview
Chart2Code is a hierarchical benchmark for evaluating multimodal models on chart understanding and chart-to-code generation. The dataset is organized into five Hugging Face configurations:
level1_direct
level1_customize
level1_figure
level2
level3
In the current Hugging Face… See the full description on the dataset page: https://huggingface.co/datasets/CSU-JPG/Chart2Code.ChartM3ChartDQAChartQAIf you wanna use the dataset, you need to download the zip file manually from the "Files and versions" tab.
Please note that this dataset can not be directly loaded with the load_dataset function from the datasets library.
If you want a version of the dataset that can be loaded with the load_dataset function, you can use this one: https://huggingface.co/datasets/ahmed-masry/chartqa_without_images
But it doesn't contain the chart images. Hence, you will still need to use the images stored in… See the full description on the dataset page: https://huggingface.co/datasets/ahmed-masry/ChartQA.chartography
Chartography
Chartography
Chartography measures professional visual reasoning over the charts that
professionals stake decisions on: Sankey diagrams, candlestick charts, contour
maps, back-trajectories, Bode plots, and more.
What it tests
The benchmark contains 100 real-world prompts and chart images spanning
12 professional domains, including Finance & Investing, Healthcare,
Manufacturing & Supply Chain, and STEM fields from Chemistry to Geosciences to
Electrical Engineering.… See the full description on the dataset page: https://huggingface.co/datasets/surgeai/chartography.adaption-charts-p2-gold
Adaption Charts P2 — Gold Chart-QA Dataset
A verified, quality-first chart question-answering dataset built for the
Adaption Labs AutoScientist Challenge (Part 2, Data Visualization track).
Two sources: a programmatically generated synthetic core
(correct-by-construction) and a hand-authored hardset built from real
public dashboards and reports.
At a glance
3803 rows total — 3705 synthetic + 98 hardset
7 chart types — bar, line, grouped_bar, stacked_bar, pie… See the full description on the dataset page: https://huggingface.co/datasets/vinod-anbalagan/adaption-charts-p2-gold.ChartMuseum
[NeurIPS 2025] ChartMuseum: Testing Visual Reasoning Capabilities of Large Vision-Language Models
Authors: Liyan Tang, Grace Kim, Xinyu Zhao, Thom Lake, Wenxuan Ding, Fangcong Yin, Prasann Singhal, Manya Wadhwa, Zeyu Leo Liu, Zayne Sprague, Ramya Namuduri, Bodun Hu, Juan Diego Rodriguez, Puyuan Peng, Greg Durrett
Leaderboard 🥇 | Paper 📃 | Code 💻
Overview
ChartMuseum is a chart question answering benchmark designed to evaluate reasoning capabilities of large… See the full description on the dataset page: https://huggingface.co/datasets/lytang/ChartMuseum.chartqaChartGen-200KChartVerse-SFT-600KChartVerse-SFT-600K is a large-scale, high-quality chart reasoning dataset with Chain-of-Thought (CoT) annotations, developed as part of the opendatalab/ChartVerse project. For more details about our method, datasets, and full model series, please visit our Project Page.
This dataset contains non-trivial samples filtered by failure rate (r > 0), ensuring that every sample provides meaningful learning signal. Samples that are too easy (r = 0, where the model always answers correctly) are… See the full description on the dataset page: https://huggingface.co/datasets/opendatalab/ChartVerse-SFT-600K.ChartQAVisRAG-Ret-Test-ChartQA
Dataset Description
This is a VQA dataset based on Charts from ChartQA dataset from ChartQA.
Load the dataset
from datasets import load_dataset
import csv
def load_beir_qrels(qrels_file):
qrels = {}
with open(qrels_file) as f:
tsvreader = csv.DictReader(f, delimiter="\t")
for row in tsvreader:
qid = row["query-id"]
pid = row["corpus-id"]
rel = int(row["score"])
if qid in qrels:… See the full description on the dataset page: https://huggingface.co/datasets/openbmb/VisRAG-Ret-Test-ChartQA.visualization-chartsChartVerse-SFT-1800KChartVerse-SFT-1800K is an extended large-scale chart reasoning dataset with Chain-of-Thought (CoT) annotations, developed as part of the opendatalab/ChartVerse project. For more details about our method, datasets, and full model series, please visit our Project Page.
This dataset contains all verified correct samples without failure rate filtering. Unlike SFT-600K which excludes easy samples (r=0), SFT-1800K includes the complete set of truth-anchored QA pairs for maximum coverage and scale.… See the full description on the dataset page: https://huggingface.co/datasets/0xzanuee/ChartVerse-SFT-1800K.chartverse-allChartVerse-SFT-1.8MChartVerse-SFT-1800K is an extended large-scale chart reasoning dataset with Chain-of-Thought (CoT) annotations, developed as part of the opendatalab/ChartVerse project. For more details about our method, datasets, and full model series, please visit our Project Page.
This dataset contains all verified correct samples without failure rate filtering. Unlike SFT-600K which excludes easy samples (r=0), SFT-1800K includes the complete set of truth-anchored QA pairs for maximum coverage and scale.… See the full description on the dataset page: https://huggingface.co/datasets/opendatalab/ChartVerse-SFT-1.8M.ChartArena
ChartArena
A Comprehensive Bilingual Benchmark for General Chart Parsing across Families, Scenarios, and Formats
Github Repo •
Paper
Overview
ChartArena is a bilingual benchmark for evaluating the chart parsing capabilities of vision-language models. It covers the full difficulty spectrum of real-world charts, spanning eight chart families across three visual scenarios and two languages.
Contents
Statistics
Dataset… See the full description on the dataset page: https://huggingface.co/datasets/psp-dada/ChartArena.ChartQA_small_preprocessedChart2NCode
Aligned Multi-View Scripts for Universal Chart-to-Code Generation
Chart2NCode is a multi-language chart-to-code dataset: every chart image is paired with three aligned plotting scripts — Python (matplotlib), R (ggplot2), and LaTeX (pgfplots) — that render visually equivalent outputs. Released with the paper "Aligned Multi-View Scripts for Universal Chart-to-Code Generation" (ACL 2026).
Paper: https://arxiv.org/abs/2604.24559
Code: https://github.com/zhihan72/CharLuMA
Models:… See the full description on the dataset page: https://huggingface.co/datasets/Zhihan/Chart2NCode.ChartGazescientific-chart-qa-17k
Scientific Chart QA, 17,070 rows
A multimodal chart-interpretation dataset built around one idea: teaching a model when not to
answer matters as much as teaching it to answer.
One in seven questions here cannot be answered from its figure, and the correct response is
cannot be determined. Baseline vision-language models overwhelmingly guess a plausible-looking
number instead. That is the behaviour this set targets.
The four things worth… See the full description on the dataset page: https://huggingface.co/datasets/manifesta/scientific-chart-qa-17k.Chartographer
Chartographer
Chartographer is a chart reasoning dataset for evaluating whether
vision-language models answer chart questions through visual reasoning rather
than shortcuts or prior familiarity with a chart. Each chart-question family
contains an upstream original chart, a reconstructed chart, and ten
seed-controlled counterfactual variants with the same Chartographer chart_id
and question_id.
More details on the construction pipeline and evaluation protocol are available
in the… See the full description on the dataset page: https://huggingface.co/datasets/1fanj/Chartographer.ChartX
ChartX & ChartVLM: A Versatile Benchmark and Foundation Model for Complicated Chart Reasoning
[ Related Paper ] [ Website ] [Models 🤗(Hugging Face)]
ChartX & ChartVLM
Recently, many versatile Multi-modal Large Language Models (MLLMs) have emerged continuously. However, their capacity to query information depicted in visual charts and engage in reasoning based on the queried contents remains under-explored. In this paper, to comprehensively and rigorously benchmark the ability… See the full description on the dataset page: https://huggingface.co/datasets/InternScience/ChartX.ChartBench-Demo
ChartBench: A Benchmark for Complex Visual Reasoning in Charts
Introduction
We propose the challenging ChartBench to evaluate the chart recognition of MLLMs.
We improve the Acc+ metric to avoid the randomly guessing situations.
We collect a larger set of unlabeled charts to emphasize the MLLM's ability to interpret visual information without the aid of annotated data points.
Todo
Open source all data of ChartBench.
Open source the evaluate… See the full description on the dataset page: https://huggingface.co/datasets/SincereX/ChartBench-Demo.ChartSync
ChartSync
This dataset accompanies ChartSync: A Benchmark for Visuo-Logical Cascading Chart Editing. ChartSync is a benchmark for evaluating Visuo-Logical Cascading Editing (VLCE) in statistical chart images.
Code
The official codebase is now available at kaka-yjk/ChartSyncCodebase.
Dataset Statistics
870 expert-validated editing triplets
9 chart categories
4 task types
235 geometry-coupled VLCE instances
Dataset Structure
The… See the full description on the dataset page: https://huggingface.co/datasets/JiakangYu/ChartSync.