Gemini 3.1 pro is really good for knowledge tasks. Google has done well there. And image analysis with Gemini flash 3.6 is solid. It’s just anything coding or agentic they fall short.
I wonder if that'll be a mistake as LLMs are used for internal LLM R&D. Either Google will not take this approach, use a 3rd party model (weird, data leak risk?), or use a non-public internal model (big sunk dev cost with no recoup by trickling it to public).
there were news that google uses claude internally, and also other news that Apple has its own claude tuned on internal data, maybe google has the same..