As far as I can tell 5.2 is the stronger model on paper, but it's been optimized to think less and do less web searches. I daily drive Thinking variants, not Auto or Instant, and usually want the _right_ answer even if it takes a minute. 5.1 does a very good job of defensively web searching, which avoids almost all of its hallucinations and keeps docs/APIs/UIs/etc up-to-date. 5.2 will instead often not think at all, even in Thinking mode. I've gotten several completely wrong, hallucinated answers since 5.2 came out, whereas maybe a handful from 5.1. (Even with me using 5.2 far less!)

The same seems to persist in Codex CLI, where again 5.2 doesn't spend as much time thinking so its solutions never come out as nicely as 5.1's.

That said, 5.1 is obviously slower for these reasons. I'm fine with that trade off. Others might have lighter workloads and thus benefit more from 5.2's speed.

Probably a relationship between what's the default and what model is being used the most. It is more about what OAI sets than what users care about. Flip side is "good enough is good enough" for most users.

> (it doesn't hallucinate on this)

But how do we know that you did not hallucinate the claim that ChatGPT does not hallucinate its version number?

We could try to exfiltrate the system prompt which probably contains the model name, but all extraction attempts could of course be hallucinations as well.

(I think there was an interview where Sam Altman or someone else at OpenAI where it was mentioned that they hardcoded the model name in the prompt because people did not understand that models don't work like that, so they made it work. I might be hallucinating though.)