---
base_model:
- OpenGVLab/Mini-InternVL-Chat-2B-V1-5
language:
- en
library_name: transformers
license: apache-2.0
metrics:
- accuracy
pipeline_tag: image-text-to-text
---

# MathCoder-VL: Bridging Vision and Code for Enhanced Multimodal Mathematical Reasoning

Repo: [https://github.com/mathllm/MathCoder](https://github.com/mathllm/MathCoder)

Paper: [https://huggingface.co/papers/2505.10557](https://huggingface.co/papers/2505.10557)

## Introduction
We introduce MathCoder-VL, a series of open-source large multimodal models (LMMs) specifically tailored for general math problem-solving. We also introduce [FigCodifier-8B](https://huggingface.co/MathLLMs/FigCodifier), an image-to-code model.

| Base Model                                          	|Ours                                               |
|-------------------------------------------------------------------|-----------------------------------------------------------------------|
|  [Mini-InternVL-Chat-2B-V1-5](https://huggingface.co/OpenGVLab/Mini-InternVL-Chat-2B-V1-5)  |  [MathCoder-VL-2B](https://huggingface.co/MathLLMs/MathCoder-VL-2B)   	|
|  [InternVL2-8B](https://huggingface.co/OpenGVLab/InternVL2-8B)  |     	[MathCoder-VL-8B](https://huggingface.co/MathLLMs/MathCoder-VL-8B)|



## Usage

For training and inference code, please refer to [InternVL](https://github.com/OpenGVLab/InternVL).

**Example:** (Illustrative - adapt to your specific needs and refer to InternVL for details)

```python
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="MathLLMs/MathCoder-VL-2B", device=0) #replace with your preferred model and device

image = "path/to/your/image.png" #replace with your image path
prompt = "What is the area of the shape in this image?"

result = pipe(image=image, text=prompt)
print(result) 
```

## Motivation

<div align="center">
  <img src="./examples/fig1.png" width="100%" title="Result Figure">
</div>

## Construction of FigCodifier

<div align="center">
  <img src="./examples/fig2.png" width="100%" title="Result Figure">
</div>

## Construction of MathCoder-VL

<div align="center">
  <img src="./examples/fig4.png" width="100%" title="Result Figure">
</div>

## Performance

<div align="center">
  <img src="./examples/tab1.png" width="100%" title="Result Figure">
</div>

## **Citation**

Please cite the paper if you use our data, model or code.

```
@inproceedings{
wang2025mathcodervl,
title={MathCoder-{VL}: Bridging Vision and Code for Enhanced Multimodal Mathematical Reasoning},
author={Ke Wang and Junting Pan and Linda Wei and Aojun Zhou and Weikang Shi and Zimu Lu and Han Xiao and Yunqiao Yang and Houxing Ren and Mingjie Zhan and Hongsheng Li},
booktitle={The 63rd Annual Meeting of the Association for Computational Linguistics},
year={2025},
url={https://openreview.net/forum?id=nuvtX1imAb}
}
```
```
@inproceedings{
lu2025mathcoder2,
title={MathCoder2: Better Math Reasoning from Continued Pretraining on Model-translated Mathematical Code},
author={Zimu Lu and Aojun Zhou and Ke Wang and Houxing Ren and Weikang Shi and Junting Pan and Mingjie Zhan and Hongsheng Li},
booktitle={The Thirteenth International Conference on Learning Representations},
year={2025},
url={https://openreview.net/forum?id=1Iuw1jcIrf}
}
```
```
@inproceedings{
wang2024mathcoder,
title={MathCoder: Seamless Code Integration in {LLM}s for Enhanced Mathematical Reasoning},
author={Ke Wang and Houxing Ren and Aojun Zhou and Zimu Lu and Sichun Luo and Weikang Shi and Renrui Zhang and Linqi Song and Mingjie Zhan and Hongsheng Li},
booktitle={The Twelfth International Conference on Learning Representations},
year={2024},
url={https://openreview.net/forum?id=z8TW0ttBPp}
}
```