MV-MATH: Evaluating Multimodal Math Reasoning in Multi-Visual Contexts
This addresses the need for better benchmarks in multimodal math reasoning for real-world applications, though it is incremental as it builds on existing datasets by adding multi-visual contexts.
The authors tackled the problem of evaluating multimodal large language models (MLLMs) in mathematical reasoning with multiple visual contexts, introducing the MV-MATH dataset of 2,009 problems and finding that MLLMs face substantial challenges with a considerable performance gap compared to humans.
Multimodal Large Language Models (MLLMs) have shown promising capabilities in mathematical reasoning within visual contexts across various datasets. However, most existing multimodal math benchmarks are limited to single-visual contexts, which diverges from the multi-visual scenarios commonly encountered in real-world mathematical applications. To address this gap, we introduce MV-MATH: a meticulously curated dataset of 2,009 high-quality mathematical problems. Each problem integrates multiple images interleaved with text, derived from authentic K-12 scenarios, and enriched with detailed annotations. MV-MATH includes multiple-choice, free-form, and multi-step questions, covering 11 subject areas across 3 difficulty levels, and serves as a comprehensive and rigorous benchmark for assessing MLLMs' mathematical reasoning in multi-visual contexts. Through extensive experimentation, we observe that MLLMs encounter substantial challenges in multi-visual math tasks, with a considerable performance gap relative to human capabilities on MV-MATH. Furthermore, we analyze the performance and error patterns of various models, providing insights into MLLMs' mathematical reasoning capabilities within multi-visual settings.