Google is winning on every AI front

I run every query I do through all the major models, up to 10 of them at this point.

Benchmarks aside Gemini 2.5 Pro is a great model and now often produces the best code for me but it's not notably better than any of the other frontier models in my testing each of which tends to have their own strengths and weaknesses.

And Google's wrapper around Gemini is easily the most frustrating of any of the major AI companies. It's content guardrails are annoying and I just learned yesterday it won't let you upload json files for whatever reason (change the extension to txt without modifying the contents in any way and it works just fine).

Gemini 2.5 Pro does this annoying thing where it decides to refactor every part of your code even if you didn't ask, and also it outputs way too many damn comments on almost every line in the style of:

// Increment variable by 1

I find Claude 3.7 better at following instructions, even though the solutions it comes up with may not be the best at times

This is why we use Gemini and its context window as the architect and Sonnet 3.7 Max for implementation.

How does that work exactly? Gemini outlines it in pseudo code?, Sonnet writes it?