Measuring Multimodal Mathematical Reasoning with MATH-Vision Dataset

Ke Wang, Junting Pan, Weikang Shi, Zimu Lu, Houxing Ren, Aojun Zhou, Mingjie Zhan, Hongsheng Li

Keywords: mathematical reasoning, multimodality, large language model

TL;DR: MATH-Vision dataset to measure LLMs' multimodal mathematical reasoning capabilities.

Abstract: Recent advancements in Large Multimodal Models (LMMs) have shown promising results in mathematical reasoning within visual contexts, with models exceeding human-level performance on existing benchmarks such as MathVista. However, we observe significant limitations in the diversity of questions and breadth of subjects covered by these benchmarks. To address this issue, we present the MATH-Vision (MATH-V) dataset, a meticulously curated collection of 3,040 high-quality mathematical problems with visual contexts sourced from real math competitions. Spanning 16 distinct mathematical disciplines and graded across 5 levels of difficulty, our dataset provides a comprehensive and diverse set of challenges for evaluating the mathematical reasoning abilities of LMMs. Through extensive experimentation, we unveil a notable performance gap between current LMMs and human performance on \datasetname, underscoring the imperative for further advancements in LMMs. Moreover, our detailed categorization allows for a thorough error analysis of LMMs, offering valuable insights to guide future research and development. The dataset is released at [MathLLMs/MathVision](https://huggingface.co/datasets/MathLLMs/MathVision)

Flagged For Ethics Review: true

Submission Number: 602