Starting today, the new Claude 3.5 Sonnet begins rolling out on GitHub Copilot, enabling developers to choose Claude 3.5 Sonnet for coding—directly in Visual Studio Code and GitHub.com. This integration brings Claude’s coding capabilities to GitHub’s community of over 100 million developers.
The upgraded Claude 3.5 Sonnet outperforms all publicly available models on SWE-bench Verified, a benchmark that measures how models solve real-world GitHub issues. It also achieves the top score in its class (93.7%) on HumanEval, a benchmark testing the ability to write correct Python functions from natural language descriptions.
Claude 3.5 Sonnet will be available in public preview to all GitHub Copilot Chat users and organizations over the coming weeks.
Use cases
With context about your entire codebase, you can use Claude 3.5 Sonnet on GitHub Copilot to:
- Write production-ready code: Ask GitHub Copilot Chat to transform natural language descriptions into high-quality code that matches your project’s patterns and conventions.
- Debug with inline chat: Highlight problematic code to get instant analysis and fixes, or ask GitHub Copilot Chat to explain error messages and suggest solutions.
- Create tests from implementation: Select any function to automatically generate comprehensive test suites that match your testing framework and cover edge cases.
- Understand code with contextual explanations: Hover over functions or highlight blocks of code in VS Code to get explanations of what the code does and how it fits into your project.
Getting started
GitHub is releasing Claude 3.5 Sonnet in public preview starting today. Claude 3.5 Sonnet runs on GitHub Copilot via Amazon Bedrock, leveraging Bedrock’s cross-region inference to further enhance reliability.
All developers and organizations should have access to Claude 3.5 Sonnet over the coming weeks. Explore the GitHub blog and documentation to learn more.