Devstral 2
Mistral's next-generation coding model designed to compete with Anthropic and other coding-focused LLMs
Devstral 2
Mistral AI • December 2025
Training Data
Up to December 2025
Devstral 2
December 2025
Parameters
~22 billion
Training Method
Code-specialized Training
Context Window
128,000 tokens
Knowledge Cutoff
December 2025
Key Features
Code Specialization • 128K Context • Vibe Coding
Capabilities
Coding: Outstanding
Code Completion: Outstanding
Debugging: Excellent
What's New in This Version
Next-generation coding model catching up to bigger AI labs like Anthropic
Mistral's next-generation coding model designed to compete with Anthropic and other coding-focused LLMs
What's New in This Version
Next-generation coding model catching up to bigger AI labs like Anthropic
Technical Specifications
Key Features
Capabilities
Other Mistral AI Models
Explore more models from Mistral AI
Mistral Small 4
Mistral's unified open-weight MoE model combining reasoning, multimodal, and coding capabilities under Apache 2.0 with only 6.5B active parameters
Mistral Large 3
Mistral's state-of-the-art open-weight frontier model with multimodal and multilingual capabilities under Apache 2.0
Ministral 3 14B
Mistral's high-performance dense model in the new Ministral 3 family
