Comment by aerhardt
3 hours ago
Codex has been good enough to me and it’s much cheaper.
I code non-trivial stuff with it like multi-threaded code and at least for my style of AI coding which is to do fairly small units of work with multiple revisions it is good enough for me to not to even consider the competition.
Just giving you a perspective on how the benchmarks might not be important at all for some people and how Claude may have a difficult time being the definitive coding model.
>> Codex has been good enough to me and it’s much cheaper.
It may be cheaper but it's much, much slower, which is a total flow killer in my experience.