> I mean, yes, but also because it's not as good as Claude today.
I'm not sure, sometimes GPT-5 Codex (or even the regular GPT-5 with Medium/High reasoning) can do things Sonnet 4.5 would mess up (most recently, figuring out why some wrappers around PrimeVue DataTable components wouldn't let the paginator show up and work correctly; alongside other such debugging) and vice versa, sometimes Gemini 2.5 Pro is also pretty okay (especially when it comes to multilingual stuff), there's a lot of randomness/inconsistency/nuance there but most of the SOTA models are generally quite capable. I kinda thought GPT-5 wasn't very good a while ago but then used it a bunch more and my views of it improved.
Codex is great for fixing memory leaks systematically. Claude will just read the code and say “oh, it’s right here” then change something and claim it fixed it. It didn’t fix it and it doesn’t undo its useless change when you point out that it didn’t fix it.
Afraid not, a bit outside of my budget (given that I've been pushing millions of tokens daily, especially for lots of refactoring that'd be great to do in an automated fashion but codegen solutions for which... just don't exist). From what little I've used Opus in the past, I'm sure it'd do reasonably as well. Maybe even Sonnet with more attempts, different prompts etc.
I'm not sure, sometimes GPT-5 Codex (or even the regular GPT-5 with Medium/High reasoning) can do things Sonnet 4.5 would mess up (most recently, figuring out why some wrappers around PrimeVue DataTable components wouldn't let the paginator show up and work correctly; alongside other such debugging) and vice versa, sometimes Gemini 2.5 Pro is also pretty okay (especially when it comes to multilingual stuff), there's a lot of randomness/inconsistency/nuance there but most of the SOTA models are generally quite capable. I kinda thought GPT-5 wasn't very good a while ago but then used it a bunch more and my views of it improved.