CMMaTH: A Chinese Multi-modal Math Skill Evaluation Benchmark for Foundation Models

TL;DR

CMMaTH is a comprehensive Chinese multimodal math benchmark with 23,000 questions spanning K12 levels, designed to evaluate large models' capabilities in solving diverse multimodal mathematical problems in Chinese.

Contribution

It introduces the largest Chinese multimodal math dataset and an open-source evaluation tool, addressing the lack of fine-grained assessment resources for Chinese K12 multimodal math models.

Findings

Largest Chinese multimodal math dataset to date

Includes diverse problem types and detailed annotations

Provides an open-source evaluation tool for models

Abstract

Due to the rapid advancements in multimodal large language models, evaluating their multimodal mathematical capabilities continues to receive wide attention. Despite the datasets like MathVista proposed benchmarks for assessing mathematical capabilities in multimodal scenarios, there is still a lack of corresponding evaluation tools and datasets for fine-grained assessment in the context of K12 education in Chinese language. To systematically evaluate the capability of multimodal large models in solving Chinese multimodal mathematical problems, we propose a Chinese Multi-modal Math Skill Evaluation Benchmark, named CMMaTH, contraining 23k multimodal K12 math related questions, forming the largest Chinese multimodal mathematical problem benchmark to date. CMMaTH questions from elementary to high school levels, provide increased diversity in problem types, solution objectives, visual elements, detailed knowledge points, and standard solution annotations. We have constructed an open-source tool GradeGPT integrated with the CMMaTH dataset, facilitating stable, rapid, and cost-free model evaluation. Our data and code are available.