Isn't it though? I've worked with plenty of devs who shipped much lower quality code into production than I see Claude 4.5 or GPT 5.2 write. I find that SOTA models are more likely to: write tests, leave helpful comments, name variables in meaningful ways, check if the build succeeds, etc.

Stuff that seems basic, but that I haven't always been able to count on in my teams' "production" code.