\n\n\n 👋 Join our WeChat or Discord community.\n
\n 📖 Check out the GLM-5.1 blog and GLM-5 Technical report.\n
\n 📍 Use GLM-5.1 API services on Z.ai API Platform. \n
\n 🔜 GLM-5.1 will be available on chat.z.ai in the coming days.\n
![\"DeepSeek-V3\"](\"https://github.com/deepseek-ai/DeepSeek-V2/blob/main/figures/logo.svg?raw=true\"){kind=logo}
\n![\"License\"](\"https://img.shields.io/badge/License-MIT-f5de53?&color=f5de53\"){kind=icon}
\n \n\n Technical Report👁️\n
\n\n## Introduction\n\nWe introduce **DeepSeek-V3.2**, a model that harmonizes high computational efficiency with superior reasoning and agent performance. Our approach is built upon three key technical breakthroughs:\n\n1. **DeepSeek Sparse Attention (DSA):** We introduce DSA, an efficient attention mechanism that substantially reduces computational complexity while preserving model performance, specifically optimized for long-context scenarios.\n2. **Scalable Reinforcement Learning Framework:** By implementing a robust RL protocol and scaling post-training compute, *DeepSeek-V3.2* performs comparably to GPT-5. Notably, our high-compute variant, **DeepSeek-V3.2-Speciale**, **surpasses GPT-5** and exhibits reasoning proficiency on par with Gemini-3.0-Pro.\n - *Achievement:* 🥇 **Gold-medal performance** in the 2025 International Mathematical Olympiad (IMO) and International Olympiad in Informatics (IOI).\n3. **Large-Scale Agentic Task Synthesis Pipeline:** To integrate **reasoning into tool-use** scenarios, we developed a novel synthesis pipeline that systematically generates training data at scale. This facilitates scalable agentic post-training, improving compliance and generalization in complex interactive environments.\n\n![](\"assets/benchmark.png\")
\n![\"Homepage\"](\"https://github.com/deepseek-ai/DeepSeek-V2/blob/main/figures/badge.svg?raw=true\"){kind=icon}
\n ![\"Chat\"](\"https://img.shields.io/badge/🤖%20Chat-DeepSeek%20V3-536af5?color=536af5&logoColor=white\"){kind=icon}
\n ![\"Hugging](\"https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-DeepSeek%20AI-ffc107?color=ffc107&logoColor=white\"){kind=icon}
\n ![\"Discord\"](\"https://img.shields.io/badge/Discord-DeepSeek%20AI-7289da?logo=discord&logoColor=white&color=7289da\"){kind=icon}
\n ![\"Wechat\"](\"https://github.com/deepseek-ai/DeepSeek-V2/blob/main/figures/qr.jpeg?raw=true\")
\n ![\"Twitter](\"https://img.shields.io/badge/Twitter-deepseek_ai-white?logo=x&logoColor=white\"){kind=icon}
\n