Nemotron Research Reasoning Qwen 1.5B

🚀 Nemotron-Research-Reasoning-Qwen-1.5B

The leading generalist reasoning model for cutting-edge research and development, excelling in complex reasoning tasks such as math, coding, and logic puzzles.

🚀 Quick Start

This model is for research and development only.

✨ Features

Nemotron-Research-Reasoning-Qwen-1.5B is the world's leading 1.5B open-weight model for complex reasoning tasks such as mathematical problems, coding challenges, scientific questions, and logic puzzles. It is trained using the ProRL algorithm on a diverse and comprehensive set of datasets, achieving impressive results and outperforming Deepseek's 1.5B model by a large margin on a broad range of tasks, including math, coding, and GPQA.

🔧 Technical Details

ProRL: Prolonged Reinforcement Learning

ProRL is designed to enable extended RL training periods that facilitate deeper exploration of reasoning strategies. It enables more than 2k training steps and scales the training data across diverse tasks—from traditional math and code tasks to STEM problems, logical puzzles, and instruction following, which, we hypothesize, are crucial for generalization. Based on Group Relative Policy Optimization (GRPO), ProRL introduces three key techniques:

1. Mitigating Entropy Collapse
2. Decoupled clip and dynamic sampling policy optimization (DAPO)
3. KL regularization and reference policy reset

Using ProRL, we developed the world's best 1.5B reasoning model that significantly outperforms its base model, DeepSeek-R1-1.5B, and matches or even surpasses the performance of DeepSeek-R1-7B across a diverse range of benchmarks. Notably, compared to DeepSeek-R1-1.5B, we achieve average pass@1 improvements of 14.7% on math benchmarks, 13.9% on coding, 54.8% on logic puzzles, 25.1% on STEM reasoning, and 18.1% on instruction-following tasks.

📦 Installation

No installation steps provided in the original document, so this section is skipped.

💻 Usage Examples

No code examples provided in the original document, so this section is skipped.

📚 Documentation

Training Datasets

Evaluation Results

Table 1: Performance (pass@1) comparison for benchmarks across Math domain

Table 2: Performance (pass@1) comparison across benchmarks for Code. We abbreviate benchmarks names for codecontests (cc), codeforces (cf), humanevalplus (human), and livecodebench (LCB).

Table 3: Performance comparison on STEM reasoning (GPQA Diamond), instruction following (IFEval), and logic puzzles (Reasoning Gym) tasks. We also present results on OOD tasks: acre, boxnet, and game_of_life_halting (game).

📄 License

The model is released under the cc-by-nc-4.0 license.

Ethical Considerations

⚠️ Important Note

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.

💡 Usage Tip

Please report security vulnerabilities or NVIDIA AI Concerns here.

Citation

If you find our dataset helpful, please cite the following paper:

@article{liu2025prorl,
  author    = {Mingjie Liu, Shizhe Diao, Ximing Lu, Jian Hu, Xin Dong, Yejin Choi, Jan Kautz, Yi Dong},
  title={ProRL: Prolonged Reinforcement Learning Expands Reasoning Boundaries in Large Language Models}, 
  journal   = {arXiv preprint},
  year      = {2025},
  archivePrefix = {arXiv},
  primaryClass = {cs.CL},
  url={https://arxiv.org/abs/2505.24864}, 
}