🤔 Skywork-OR1 (Open Reasoner 1)

🔥 News

• May 13, 2025: We release the final version of Skywork-OR1 (Open Reasoner 1) series of models, including Skywork-OR1-32B and Skywork-OR1-7B. We open-source
  • 🤗 Model weights: Skywork-OR1-32B, Skywork-OR1-7B
  • 🤗 Training data: Skywork-OR1-RL-Data
  • 🧑‍💻 Code: Skywork-OR1
  The complete technical report is coming soon. See our Notion Blog for training recipes and preliminary experimental results. More analysis and insights will be included in the final technical report, which is dedicated to helping the community better research, understand, and push the frontier of open reasoning models.

📖 Overview

_{The AIME24 and AIME25 scores versus training steps of Skywork-OR1-32B in our training pipeline.}

The Skywork-OR1 (Open Reasoner 1) model series consists of powerful math and code reasoning models trained using large-scale rule-based reinforcement learning with carefully designed datasets and training recipes. This series includes two general-purpose reasoning modelsl, Skywork-OR1-7B and Skywork-OR1-32B.

• Skywork-OR1-32B outperforms Deepseek-R1 and Qwen3-32B on math tasks (AIME24 and AIME25) and delivers comparable performance on coding tasks (LiveCodeBench).
• Skywork-OR1-7B exhibits competitive performance compared to similarly sized models in both math and coding scenarios.

📊 Evaluation

⚙️ Training Recipe

Data

• We select, clean, and curate a dataset of 110K verifiable, challenging, and diverse math problems and 14K coding questions from open-source datasets.
• We perform model-aware difficulty estimation for each problem and model and conduct rigorous quality assessment prior to training to ensure training efficiency and effectiveness.

Training

• We perform both offline and online difficulty-based filtering and rejection sampling to improve training efficiency.
• We incorporate a multi-stage training pipeline coupled with adaptive entropy control and other techniques to enhance exploration and stability.

📄 Technical Report

🙏 Acknowledgements

• Both of our models are trained on top of DeepSeek-R1-Distill-Qwen-7B and DeepSeek-R1-Distill-Qwen-32B.
• Both models are trained using a custom fork of the wonderful verl project.

📚 Citation