MathReal: We Keep It Real! A Real Scene Benchmark for Evaluating Math Reasoning in Multimodal Large Language Models

• URL: http://arxiv.org/abs/2508.06009v1
• Date: Fri, 08 Aug 2025 04:39:16 GMT
• Title: MathReal: We Keep It Real! A Real Scene Benchmark for Evaluating Math Reasoning in Multimodal Large Language Models
• Authors: Jun Feng, Zixin Wang, Zhentao Zhang, Yue Guo, Zhihan Zhou, Xiuyi Chen, Zhenyang Li, Dawei Yin,
• Abstract summary: We introduce MathReal, a dataset comprising 2,000 mathematical questions with images captured by handheld mobile devices in authentic scenarios.<n>MathReal spans five core knowledge and ability categories, which encompass three question types and are divided into three difficulty levels.<n>We evaluate the multimodal mathematical reasoning abilities of state-of-the-art MLLMs in real-world scenarios.
• Score: 29.7077721906364
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Multimodal Large Language Models (MLLMs) have demonstrated remarkable capabilities in visual mathematical reasoning across various existing benchmarks. However, these benchmarks are predominantly based on clean or processed multimodal inputs, without incorporating the images provided by real-world Kindergarten through 12th grade (K-12) educational users. To address this gap, we introduce MathReal, a meticulously curated dataset comprising 2,000 mathematical questions with images captured by handheld mobile devices in authentic scenarios. Each question is an image, containing the question text and visual element. We systematically classify the real images into three primary categories: image quality degradation, perspective variation, and irrelevant content interference, which are further delineated into 14 subcategories. Additionally, MathReal spans five core knowledge and ability categories, which encompass three question types and are divided into three difficulty levels. To comprehensively evaluate the multimodal mathematical reasoning abilities of state-of-the-art MLLMs in real-world scenarios, we design six experimental settings that enable a systematic analysis of their performance. Through extensive experimentation, we find that the problem-solving abilities of existing MLLMs are significantly challenged in realistic educational contexts. Based on this, we conduct a thorough analysis of their performance and error patterns, providing insights into their recognition, comprehension, and reasoning capabilities, and outlining directions for future improvements. Data and code: https://github.com/junfeng0288/MathReal.

Related papers

• MathSight: A Benchmark Exploring Have Vision-Language Models Really Seen in University-Level Mathematical Reasoning? [21.777853590188688]
  We present MathSight, a university-level multimodal mathematical reasoning benchmark designed to disentangle and quantify the effect of visual input.<n> Experiments on state-of-the-art Vision-Language Models reveal a consistent trend: the contribution of visual information diminishes with increasing problem difficulty.
  arXiv  Detail & Related papers  (2025-11-28T11:55:05Z)
• VideoMathQA: Benchmarking Mathematical Reasoning via Multimodal Understanding in Videos [89.39873803375498]
  VideoMathQA is a benchmark designed to evaluate whether models can perform temporally extended cross-modal reasoning on videos.<n>The benchmark spans 10 diverse mathematical domains, covering videos ranging from 10 seconds to over 1 hour.<n>It requires models to interpret structured visual content, understand instructional narratives, and jointly ground concepts across visual, audio, and textual modalities.
  arXiv  Detail & Related papers  (2025-06-05T17:59:58Z)
• MV-MATH: Evaluating Multimodal Math Reasoning in Multi-Visual Contexts [34.972503583614674]
  We introduce MV-MATH: a meticulously curated dataset of 2,009 high-quality mathematical problems.<n>Each problem integrates multiple images interleaved with text, derived from authentic K-12 scenarios, and enriched with detailed annotations.<n>MV-MATH includes multiple-choice, free-form, and multi-step questions, covering 11 subject areas across 3 difficulty levels.<n>We observe that MLLMs encounter substantial challenges in multi-visual math tasks, with a considerable performance gap relative to human capabilities on MV-MATH.
  arXiv  Detail & Related papers  (2025-02-28T07:50:36Z)
• MC-Bench: A Benchmark for Multi-Context Visual Grounding in the Era of MLLMs [61.56904387052982]
  This paper proposes a new visual grounding task called multi-context visual grounding.<n>It aims to localize instances of interest across multiple images based on open-ended text prompts.<n>We benchmark over 20 state-of-the-art MLLMs and foundation models with potential multi-context visual grounding capabilities.
  arXiv  Detail & Related papers  (2024-10-16T07:52:57Z)
• Polymath: A Challenging Multi-modal Mathematical Reasoning Benchmark [53.61633384281524]
  PolyMATH is a benchmark aimed at evaluating the general cognitive reasoning abilities of MLLMs. The best scores achieved on PolyMATH are 41%, 36%, and 27%, obtained by Claude-3.5 Sonnet, GPT-4o and Gemini-1.5 Pro respectively. A further fine-grained error analysis reveals that these models struggle to understand spatial relations and perform drawn-out, high-level reasoning.
  arXiv  Detail & Related papers  (2024-10-06T20:35:41Z)
• Math-PUMA: Progressive Upward Multimodal Alignment to Enhance Mathematical Reasoning [5.9767694994869425]
  Multimodal Large Language Models (MLLMs) excel in solving text-based mathematical problems. They struggle with mathematical diagrams since they are primarily trained on natural scene images. We propose Math-PUMA, a methodology focused on Progressive Upward Multimodal Alignment.
  arXiv  Detail & Related papers  (2024-08-16T10:11:05Z)
• MathScape: Benchmarking Multimodal Large Language Models in Real-World Mathematical Contexts [18.91777213491096]
  We introduce MathScape, a novel benchmark focused on assessing MLLMs' reasoning ability in realistic mathematical contexts.<n>MathScape comprises 1,369 high-quality math problems paired with human-captured real-world images.<n>We conduct a thorough multi-dimensional evaluation across nine leading closed-source MLLMs, three open-source MLLMs with over 20 billion parameters, and seven smaller-scale MLLMs.
  arXiv  Detail & Related papers  (2024-08-14T13:23:43Z)
• MAVIS: Mathematical Visual Instruction Tuning with an Automatic Data Engine [85.80851893886161]
  We propose MAVIS, a MAthematical VISual instruction tuning pipeline for MLLMs, featuring an automatic data engine to efficiently create mathematical visual datasets. We use MAVIS-Caption to fine-tune a math-specific vision encoder (CLIP-Math) through contrastive learning, tailored for improved diagram visual encoding. Third, we adopt MAVIS-Instruct to perform the instruction tuning for robust problem-solving skills, and term the resulting model as MAVIS-7B.
  arXiv  Detail & Related papers  (2024-07-11T17:59:47Z)
• Math-LLaVA: Bootstrapping Mathematical Reasoning for Multimodal Large Language Models [62.815222721144636]
  We introduce Math-LLaVA, a LLaVA-1.5-based model fine-tuned with MathV360K. This novel approach significantly improves the multimodal mathematical reasoning capabilities of LLaVA-1.5. Math-LLaVA demonstrates enhanced generalizability, showing substantial improvements on the MMMU benchmark.
  arXiv  Detail & Related papers  (2024-06-25T05:43:21Z)
• MathVerse: Does Your Multi-modal LLM Truly See the Diagrams in Visual Math Problems? [99.0305256706604]
  We introduce MathVerse, an all-around visual math benchmark designed for an equitable and in-depth evaluation of MLLMs. We meticulously collect 2,612 high-quality, multi-subject math problems with diagrams from publicly available sources. This approach allows MathVerse to comprehensively assess whether and how much MLLMs can truly understand the visual diagrams for mathematical reasoning.
  arXiv  Detail & Related papers  (2024-03-21T17:59:50Z)
• ACQUIRED: A Dataset for Answering Counterfactual Questions In Real-Life Videos [53.92440577914417]
  ACQUIRED consists of 3.9K annotated videos, encompassing a wide range of event types and incorporating both first and third-person viewpoints. Each video is annotated with questions that span three distinct dimensions of reasoning, including physical, social, and temporal. We benchmark our dataset against several state-of-the-art language-only and multimodal models and experimental results demonstrate a significant performance gap.
  arXiv  Detail & Related papers  (2023-11-02T22:17:03Z)
• MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts [170.01089233942594]
  MathVista is a benchmark designed to combine challenges from diverse mathematical and visual tasks. The best-performing GPT-4V model achieves an overall accuracy of 49.9%, substantially outperforming Bard, the second-best performer, by 15.1%. GPT-4V still falls short of human performance by 10.4%, as it often struggles to understand complex figures and perform rigorous reasoning.
  arXiv  Detail & Related papers  (2023-10-03T17:57:24Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.