Back
AI summary
Written by AI from the official notes. Check them for exact details.DeepSeek-V3.1 upgrades both deepseek-chat and deepseek-reasoner with improved efficiency and capabilities.
- Hybrid reasoning architecture supports both thinking and non-thinking modes
- Improved reasoning efficiency provides faster answers
- Enhanced agent capabilities with major improvements in tool usage
Why it matters: Users of DeepSeek tools should care for enhanced performance and faster responses in their applications.
Full release notes5 changes
Both deepseek-chat and deepseek-reasoner have been upgraded to DeepSeek-V3.1. deepseek-chat corresponds to DeepSeek-V3.1's non-thinking mode, while deepseek-reasoner corresponds to its thinking mode.
- Key updates in DeepSeek-V3.1: Hybrid reasoning architecture: A single model supports both thinking mode and non-thinking mode
- Improved reasoning efficiency: Compared to DeepSeek-R1-0528, DeepSeek-V3.1-Think provides answers in significantly less time
- Enhanced agent capabilities: With post-training optimization, the new model achieves major improvements in tool usage and intelligent agent tasks SWE-bench Verified: 66.0
- SWE-bench Multilingual: 54.5
- Terminal-bench: 31.3