Openmath Nemotron 32B

🚀 OpenMath-Nemotron-32B

OpenMath-Nemotron-32B is created by finetuning Qwen/Qwen2.5-32B on OpenMathReasoning dataset. This model is ready for commercial use.

🚀 Quick Start

OpenMath-Nemotron models achieve state-of-the-art results on popular mathematical benchmarks. We present metrics as pass@1 (maj@64) where pass@1 is an average accuracy across 64 generations and maj@64 is the result of majority voting. Please see our paper for more details on the evaluation setup.

We used a version of OpenMath-Nemotron-14B model to secure the first place in AIMO-2 Kaggle competition!

✨ Features

• Achieve state-of-the-art results on popular mathematical benchmarks.
• Ready for commercial use.
• Can be used in 3 inference modes: chain-of-thought (CoT), tool-integrated reasoning (TIR) and generative solution selection (GenSelect).

📦 Installation

The pipeline we used to produce the data and models is fully open-sourced!

• Code
• Models
• Dataset
• Paper

We provide all instructions to fully reproduce our results, including data generation.

💻 Usage Examples

Basic Usage

Our models can be used in 3 inference modes: chain-of-thought (CoT), tool-integrated reasoning (TIR) and generative solution selection (GenSelect). To run inference with CoT mode, you can use this example code snippet.

import transformers
import torch

model_id = "nvidia/OpenMath-Nemotron-32B"

pipeline = transformers.pipeline(
    "text-generation",
    model=model_id,
    model_kwargs={"torch_dtype": torch.bfloat16},
    device_map="auto",
)

messages = [
    {
        "role": "user", 
        "content": "Solve the following math problem. Make sure to put the answer (and only answer) inside \\boxed{}.\n\n" + 
        "What is the minimum value of $a^2+6a-7$?"},
]

outputs = pipeline(
    messages,
    max_new_tokens=4096,
)
print(outputs[0]["generated_text"][-1]['content'])

Advanced Usage

To run inference with TIR or GenSelect modes, we highly recommend to use our reference implementation in NeMo-Skills.

⚠️ Important Note

These models have not been instruction tuned on general data and thus might not provide good answers outside of math domain.

📚 Documentation

Additional information

📄 License

Use of this model is governed by CC-BY-4.0. Additional Information: Apache License Version 2.0.

📚 Citation

If you find our work useful, please consider citing us!

@article{moshkov2025aimo2,
  title   = {AIMO-2 Winning Solution: Building State-of-the-Art Mathematical Reasoning Models with OpenMathReasoning dataset},
  author  = {Ivan Moshkov and Darragh Hanley and Ivan Sorokin and Shubham Toshniwal and Christof Henkel and Benedikt Schifferer and Wei Du and Igor Gitman},
  year    = {2025},
  journal = {arXiv preprint arXiv:2504.16891}
}

🔒 Ethical Considerations

NVIDIA believes Trustworthy AI is a shared responsibility and we have established policies and practices to enable development for a wide array of AI applications. When downloaded or used in accordance with our terms of service, developers should work with their internal model team to ensure this model meets requirements for the relevant industry and use case and addresses unforeseen product misuse.

For more detailed information on ethical considerations for this model, please see the Model Card++ Explainability, Bias, Safety & Security, and Privacy Subcards.

Please report security vulnerabilities or NVIDIA AI Concerns here.