Google is releasing the high-performing Deep Think AI to select researchers, supporting advanced reasoning tests and future optimization in complex math tasks.

The company says Gemini 2.5 Deep Think achieved new performance records—for AI, at least—on common knowledge and reasoning tests.

Google released its first publicly available "multi-agent" AI system, which uses more computational resources, but produces better answers.

Google AI Ultra subscribers now have access to Deep Think, Google’s most advanced reasoning model yet for Gemini 2.5. The new model was first unveiled at Google I/O, and after feedback from "early trusted testers,

Google DeepMind, Alphabet Inc.’s artificial intelligence research arm, today announced the rollout of Gemini 2.5 Deep Think, a new creative problem-solving AI model. The company stated the model is capable of addressing complex problems by considering multiple ideas simultaneously and choosing the best answer.

After previewing at I/O 2025 in May, Google is now rolling out the Gemini 2.5 Deep Think mode to AI Ultra subscribers. Google says “Deep Think pushes the frontier of thinking capabilities by leveraging parallel thinking techniques.