> Coding activities should be performed mostly with:
> * Gemini 2.5 PRO > * Claude Opus 4
I think trying out all the LLMs for each task is highly underappreciated. There is no pareto optimal LLM for all skills. I give each prompt to 8 different LLMs using a Mac app. In my experience while Gemini is consistently in top 3 of 8, the difference between best output and Gemini Pro could be huge.