
What you need to know
- Google is previewing Gemini 3.1 Pro, with a focus on complex, multi-step problem-solving that stumps most chatbots.
- The model scored 77.1% on the ARC-AGI-2 benchmark — more than double the reasoning performance of Gemini 3.0 Pro.
- You can use it across the Gemini app, NotebookLM, Vertex AI, and the Gemini API.