I can confirm GPT 5.2 is better than Gemini and Claude. GPT 5.2 Codex is probably even better.
It’s significantly slower though. At least for my use cases I rather ask Claude 4.5 opus and switch to GPT if Claude is stuck.
I'm gonna call bs on these kind of comments. "better" on what? Coding models shouldn't even be compared isolated. A big part of making it work in a real/big codebase is the tool that calls the model (claude code, gemini-cli, etc). I'll bet claude code will still keep stealing your lunch every day of the week against any competitor out there
Gemini 2.5 or 3? (3 was released yesterday)