Google 刚把 Gemini 3.6 Flash 塞进 GitHub Copilot，任务完成率比 3.5 高，写代码更省 token，试试看。
Google AI 的 Gemini 3.6 Flash 模型已在 GitHub Copilot 中全面上线。该模型针对 Web 开发、应用开发、编码及智能体任务进行了优化。测试数据显示，相比 Gemini 3.5 Flash，它在编码和智能体工作流中实现了更高的任务完成率和更优的 token 效率。用户可以通过 GitHub Copilot 应用或 VS Code 直接使用。
https://t.co/0uRoKUsz4C
x.com/github/status/… GitHub @github 🆕 @GoogleAI ’s Gemini 3.6 Flash is now generally available and rolling out in GitHub Copilot. ➡️ It is designed for web and app development, coding and agentic tasks ➡️ In testing, it demonstrated higher task-completion rates and better token efficiency than Gemini 3.5 Flash across coding and agentic workflows Try it out in the GitHub Copilot app or @code . github.blog/changelog/2026… W 🔗 View Quoted Tweet 💬 1 🔄 0 ❤️ 1 👀 454 📊 1 ⚡