MAI-Code-1.1-Flash: Better, faster, at a quarter of the cost | Microsoft AI

The model is 25% more token-efficient, 25% faster, and costs a quarter of the previous version.

• 22% improvement on Terminal-Bench 2.1 for CLI tasks and 15% improvement on .NET tasks.
• Code survival rose 4% and return visits increased 9% in production.
• Trained with hundreds of thousands of reinforcement-learning environments in GitHub Copilot.
• Available now in GitHub Copilot; feedback can be submitted via issues.

Developers using GitHub Copilot get faster, cheaper, and higher-quality code generation, improving productivity and reducing costs.

Sources

• Microsoft AI: MAI-Code-1.1-Flash: Better, faster, at a quarter of the cost | Microsoft AI

Read this as text

Back to the AI news