[anotherpaul]

I feel like Claude code is great but how is it so much different from the agent of GitHub copilot? They both can use the same model (Claude 4) and the agent behaves very similar. For 10 bucks I think GitHub copilot is very reasonably priced as well. But ofc usage limits are maybe where they differ a lot. Am I missing out?

[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