That used to be the case, but the current Enterprise version, with the poorly-named "GPT 5.6 think deeper" option, is very decent indeed. Can't tell if it's Sol, Terra or a mixture of the two, but it's certainly not Luna.

(Stick with the default "Auto" and you probably get Phi-4 -- it's lobotomised AF.)

I use Copilot a lot now. Unlimited, free, high-quality, enterprise-protected inference is not to be sniffed at. It also writes some of the nicest code I've ever seen from an LLM, that's almost entirely free of comments.