MMTutorBench: The First Multimodal Benchmark for AI Math Tutoring

TL;DR

MMTutorBench is a pioneering multimodal benchmark designed to evaluate AI systems' ability to perform comprehensive math tutoring tasks, including problem-solving, diagnosis, and guidance, revealing significant performance gaps.

Contribution

This paper introduces the first multimodal benchmark for AI math tutoring with structured evaluation metrics and assesses 12 models, highlighting current limitations and diagnostic insights.

Findings

Proprietary models outperform open-source counterparts.

OCR pipelines reduce tutoring quality.

Few-shot prompting offers limited improvements.

Abstract

Effective math tutoring requires not only solving problems but also diagnosing students' difficulties and guiding them step by step. While multimodal large language models (MLLMs) show promise, existing benchmarks largely overlook these tutoring skills. We introduce MMTutorBench, the first benchmark for AI math tutoring, consisting of 685 problems built around pedagogically significant key-steps. Each problem is paired with problem-specific rubrics that enable fine-grained evaluation across six dimensions, and structured into three tasks-Insight Discovery, Operation Formulation, and Operation Execution. We evaluate 12 leading MLLMs and find clear performance gaps between proprietary and open-source systems, substantial room compared to human tutors, and consistent trends across input variants: OCR pipelines degrade tutoring quality, few-shot prompting yields limited gains, and our rubric-based LLM-as-a-Judge proves highly reliable. These results highlight both the difficulty and diagnostic value of MMTutorBench for advancing AI tutoring.