[bottlepalm]

Better code hands down. Actually GPT 5.5 is a good example of a model that's generally better at solving problems than Opus 4.8, but the code it generates is worse - over engineered, shortcuts, etc.. Fable does both, better code and solves problems, but it's also very expensive. Currently I use Opus mostly, Codex for code reviews because it is pedantic, and Fable for tough problems and high level design.

[zarzavat]

The way I'd describe it, Fable is the first model that's good enough.

If all I had was Fable for the next couple of years then I'd be totally fine with that. I have never felt that about any version of Opus.

[dools]

That’s the way I feel about GPT 5.2