Measuring Multimodal Mathematical Reasoning with MATH-Vision Dataset
Recent advancements in Large Multimodal Models (LMMs) have shown promising results in mathematical reasoning within visual contexts, with models approaching 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 MATH-V, 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 project is available at https://mathvision-cuhk.github.io
PDF AbstractResults from the Paper
Ranked #1 on Multimodal Reasoning on MATH-V (using extra training data)
Task | Dataset | Model | Metric Name | Metric Value | Global Rank | Uses Extra Training Data |
Benchmark |
---|---|---|---|---|---|---|---|
Multimodal Reasoning | MATH-V | InternLM-XComposer2-VL | Accuracy | 14.54 | # 4 | ||
Multimodal Reasoning | MATH-V | Qwen-VL-Max | Accuracy | 15.59 | # 3 | ||
Multimodal Reasoning | MATH-V | Gemini Pro | Accuracy | 17.66 | # 2 | ||
Multimodal Reasoning | MATH-V | GPT4V | Accuracy | 22.76 | # 1 |