I’m still really surprised everyone loves Gemini 2.5 so much.
Even for coding I find GPT4o to be more concise and write more sensible things.
I get the one-shot ‘build me a flight simulator’ type thing is special to Gemini 2.5 - but who actually ever uses it that way?
I feel a bit old school for aging it, but I still prefer ChatGPT at this moment. Am I the only one?
If you’re not using something like Cline or Cursor you should give them a try.
I haven’t found any OpenAI models good for agentic coding. o3-mini and 4o were both worse than 3.5 Sonnet. 3.7 and Gemini 2.5 Pro both seem be better than 3.5. I still use 4o with search as my primary reference model though.