MultiChartQA

This repository contains the questions and answers for our MultiChartQA Benchmark. At present, both the data and the test code are available. We welcome everyone to use and explore our benchmark!

Introduction

MultiChartQA is an extensive and demanding benchmark that features real-world charts. We source charts from various places to ensure both diversity and completeness. Each multi-chart group includes 2 or 3 charts, and each group is accompanied by 4 questions, typically spanning four distinct main categories. Now the expanded version of MultiChartQA contains 500 sets of multi-chart samples, 1370 charts, and 2000 questions.

Overview

Evaluation

Model Response Generation

python code/evaluation.py

Calculate Accuracy

python code/calculate_acc.py