How do you decide which AI model to use for what?

genuinely curious how other people handle this. I've got chatgpt, claude and gemini all open pretty much every day and I never have a consistent rule for picking one, it's mostly vibes plus whichever tab is closest

sometimes I ask the same question to two of them just to see who gets it right, which honestly feels like a waste of time but I keep doing it anyway

curious if anyone's actually settled into a system, like "claude for writing, gpt for code" or something, or if everyone's just winging it like me. been building something to fix this for myself (pelladio, lets you mention

whichever model you need in the same chat instead of juggling tabs) but mostly just want to know if this is a me problem or if it's actually common