We've been testing GPT-5.6-Sol for over 2 months now. It’s incredibly good in my day-to-day working on Next.js. It understands architecture tradeoffs. It can investigate complicated Next.js issue reports. It considers other areas of the codebase when fixing bugs. Needs very little guidance. Short prompts are enough. There’s some big refactors of the Next.js server that it implemented end-to-end with me pointing at high level possible improvements (we have skills for how to grab our failing test suites on PRs, deployment tests, etc.) Those PRs are ready to merge after Next.js 16.3 has been released.