at least for our scope of work (data, interfacing with data, building things to extract data quickly and dump to warehouse, resuming) claude is performing night and day better than codex. we're still continuing tinkering with codex here to see if we're happy with it but it's taking a lot more human-in-the-loop to keep it from going down the wrong path and we're finding that we're constantly prompt-nudging it to the end result. for the most part after ~3 days we're not super happy with it. kinda feels like claude did last year idk. it's worth checking out and seeing if it's succeeding at the stuff you want it to do.