YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

LIMO: Less Is More for Reasoning 🚀

📌 Table of Contents

• Overview
• Key Results
• Model Zoo
• Datasets
• Quick Start
• Training
• Evaluation
• Citation

Overview

LIMO challenges the conventional wisdom in mathematical reasoning by demonstrating that models can achieve superior performance with significantly less but higher quality training data. Our approach:

• 🎯 Achieves SOTA with only 817 carefully curated training samples
• 🌟 Shows strong generalization across diverse problem types
• 🔬 Provides comprehensive evaluation on 10 benchmarks
• 📚 Releases high-quality datasets and evaluation tools

Key Results

Model Zoo

Our LIMO model is available on Hugging Face 🤗:

Datasets

We release our datasets through Hugging Face 🤗:

Note: We are gradually releasing additional datasets mentioned in our paper, including those used for comparative experiments, to facilitate reproducibility and further analysis by the research community. Stay tuned!

Quick Start

Our model is fine-tuned on Qwen2.5-32B-Instruct and is compatible with most mainstream frameworks like HF Transformers, VLLM, TensorRT-LLM and etc.

License

This project is licensed under the MIT License - see the LICENSE file for details.

Citation

@misc{ye2025limoreasoning,
 title={LIMO: Less is More for Reasoning}, 
 author={Yixin Ye and Zhen Huang and Yang Xiao and Ethan Chern and Shijie Xia and Pengfei Liu},
 year={2025},
 eprint={2502.03387},
 archivePrefix={arXiv},
 primaryClass={cs.CL},
 url={https://arxiv.org/abs/2502.03387}, 
}

3 items • Updated Sep 17, 2025