Except your single experience doesn't mean it's generally true, bud. For instance I have not switched to Opus despite claims that it is better because I don't want to go through the effort of cancelling my ChatGPT subscription and subbing to Claude. Plus I like getting new stuff early that OpenAI occasionally gives out and the same could apply for Google's AI.
Sorry, but lock in effects are real. End users, solo devs and startups might find it trivially easy, but enterprise clients would go through hoops before a decision is to be made. And enterprise clients would rather not go through with that, hence they'll stick to whoever came first, unless there's a massive differentiator between the two.
I’ve switched to Opus from GPT-4 for coding and it was non-trivially easy