Family
Benchmark · 2025
ChartQAPro
A realistic chart question-answering benchmark with conversational, hypothetical, fact-checking, and unanswerable cases.
Open the primary source ↗Task
Answer 1,948 human-written questions over 1,341 charts from 157 sources.
Evidence
Question-answering accuracy by task category plus a bounded expert human reference.
What it establishes
Shows that older chart specialists transfer poorly to harder and more realistic chart-reading distributions.
What it does not establish
The small human estimate is not a population norm, and static QA omits interaction, authoring, and reader outcomes.
Useful for
Audience routes that point here.
Related entities
Continue through the library.
- ChartographyA deliberately difficult set of practitioner-authored professional chart-reading tasks.
- PolyChartQA: multi-chart figuresA multi-chart scientific-figure benchmark whose name collides with a separate multilingual chart benchmark.
- POLYCHARTQA: multilingual chart QAA multilingual chart-question-answering benchmark distinct from the similarly named multi-chart scientific-figure dataset.