[nicewood]

I only know the old Github Copilot (like 2yrs+ ago) so cannot speak to it directly, but even the Cursor Agent (with Sonnet 4 or GPT-5) is IMO inferior to Claude Code (CC). In my experience, it is faster and better performing. CC seems to spend tokens more deliberately + gives superior coding tools to the model than other provider.

Recently my CC subscription ran out, tried 3 prompts with Cursor Agent and then went back to subscribing CC. I still use Cursor though for autocompletion.

[anotherpaul]

Yeah the old one was much worse. They have really stepped up their game recently. Thats why I am wondering how large the gap still is. I only ever see people compare cursor and Claude code. Never GitHub copilot. So I assume there is either a blind spot or it's much worse