Google DeepMind

Gemini 3.1 Pro benchmark comparison showing ARC-AGI-2 and RE-Bench scores versus Gemini 3 Pro and other frontier models

Gemini 3.1 Pro: Google's Reasoning-First Model

Gemini 3.1 Pro scores 77.1% on ARC-AGI-2, doubling Gemini 3 Pro. Features 1M context, configurable thinking depth, and a custom tools endpoint for agents.

Feb 19, 2026·6 min read