That boils down to you not understanding what you're using. It didn't used to be better, it quite literally used to be horrible. Newer models are significantly better in general. As for why it generated different results, LLMs are not deterministic in nature.
Literally used the same llms different versions. Used to make life easier, now it doesn't. Out walking the dog so not going to dig into the data.
Ps wasn't using them to be deterministic. That's no good with llms
But you are talking about them as if they are, which would be intentionally misleading. You shared nothing about your use case except implying that you expected the result to be deterministic. So at this point, you're not behaving much better than what you claim AI to be doing.
And? You've shared nothing about how you tested, what the metric was for success, what the tolerance was for error, or even what you were promoting. You are just expecting me to run with whatever you say and that in itself is a big reason why people fail at using AI. No worries, I'm going to work
If you'd like to discuss that, we should move somewhere without a character limit as this isn't conducive to a real discussion.