Family
Benchmark · 2026
PolyChartQA: multi-chart figures
A multi-chart scientific-figure benchmark whose name collides with a separate multilingual chart benchmark.
Open the primary source ↗Task
Answer 2,694 questions over 534 images containing 2,297 subcharts from computer-science papers.
Evidence
Human and model-judge accuracy, BERTScore, source and difficulty ablations, and manually verified questions.
What it establishes
Shows that localization and reasoning across subcharts are harder, especially for human-authored questions.
What it does not establish
The paper-domain sample and mostly homogeneous subchart types do not represent every multi-chart document or audience.
Related entities
Continue through the library.
- POLYCHARTQA: multilingual chart QAA multilingual chart-question-answering benchmark distinct from the similarly named multi-chart scientific-figure dataset.
- ChartQAProA realistic chart question-answering benchmark with conversational, hypothetical, fact-checking, and unanswerable cases.
- ChartographyA deliberately difficult set of practitioner-authored professional chart-reading tasks.