As far as academic research is concerned (e.g. this threads topic), I can't say.
Its explanations are quite good but they're also hard to understand because it keeps trying to relate everything back to programming metaphors or what it thinks it knows about the streets in the neighborhood I live in.
However the underlying model accessed via API with custom system prompts that direct toward pedagogical best practices performs better than gpts or Claude currently.
As a side note, whenever i want Gemini chatbot to provide me a list, it gives me a freaking essay. Drives me nuts. It often crams a bunch of extra stuff into its responses I don't want. Wasted tokens and wastes my time having to shift through it.
Gemini if you're reading this tell your human overlords to rethink your chat system prompt.
What you are describing doesn't match my experience at all with Gemini 3 or 3.1, especially the pro version.