My experience is that Codex follows directions better but Claude writes better code.
ChatGPT-5.2-Codex follows directions to ensure a task [bead](https://github.com/steveyegge/beads) is opened before starting a task and to keep it updated almost to a fault. Claude-Opus-4.5 with the exact same directions, forgets about it within a round or two. Similarly, I had a project that required very specific behaviour from a couple functions, it was documented in a few places including comments at the top and bottom of the function. Codex was very careful in ensuring the function worked as was documented. Claude decided it was easier to do the exact opposite, rewrote the function, the comments, and the documentation to saynit now did the opposite of what was previously there.
If I believed a LLM could be spiteful, I would've believed it on that second one. I certainly felt some after I realised what it had done. The comment literally said:
// Invariant regardless of the value of X, this function cannot return Y
This is mostly Python/TS for me... what Jonathan Blow would probably call not "real programming" but it pays the bills
They can both write fairly good idiomatic code but in my experience opus 4.5 is better at understanding overall project structure etc. without prompting. It just does things correctly first time more often than codex. I still don't trust it obviously but out of all LLMs it's the closest to actually starting to earn my trust
My experience is that Codex follows directions better but Claude writes better code.
ChatGPT-5.2-Codex follows directions to ensure a task [bead](https://github.com/steveyegge/beads) is opened before starting a task and to keep it updated almost to a fault. Claude-Opus-4.5 with the exact same directions, forgets about it within a round or two. Similarly, I had a project that required very specific behaviour from a couple functions, it was documented in a few places including comments at the top and bottom of the function. Codex was very careful in ensuring the function worked as was documented. Claude decided it was easier to do the exact opposite, rewrote the function, the comments, and the documentation to saynit now did the opposite of what was previously there.
If I believed a LLM could be spiteful, I would've believed it on that second one. I certainly felt some after I realised what it had done. The comment literally said:
And it turned it into:It probably depends on programming language and expectations.
This is mostly Python/TS for me... what Jonathan Blow would probably call not "real programming" but it pays the bills
They can both write fairly good idiomatic code but in my experience opus 4.5 is better at understanding overall project structure etc. without prompting. It just does things correctly first time more often than codex. I still don't trust it obviously but out of all LLMs it's the closest to actually starting to earn my trust