As far as coding goes Claude seems to be the most competent right now, I like it. GPT5 is abysmal - I'm not sure if they're bugs, or what, but the new release takes a good few steps back. Gemini still a hit and miss - and Grok seems to be a poor man's Claude (where code is kind of okay, a bit buggy and somehow similar to Claude).

Are you evaluating gpt5-thinking on high mode, via API or Codex CLI on Pro tier? Just wondering what specifically you compared since those factors affect its performance and context