Comment by dimitrios1

I have both as well. I trust the output of Claude to a higher degree than what I get with Codex. I always have claude review codex output. That being said, I find gpt 5.5 more generically useful at a wider breadth of tasks. Straight coding though, it's no contest.

Obligatory YMMV, maybe your prompting style fits gpt better. We forget that this matters a lot