It's on par/better/worse depending on the problem. o1 is significantly worse, for example, in Rust programming than Claude 3.5; at least for me.

Claude really likes producing code, that’s for sure. I feel like it’s a useful tool once I’ve deconstructed a project past a certain point.

It’s pretty on par with o1, better at many coding questions.

I found it better at reasoning, worse at coding.

Not doubting your experience, just thinking how subjective it all is.