Google has launched a significant update to Gemini 3 Deep Think, a specialized reasoning mode integrated into the Gemini app and now accessible via the Gemini API for select researchers, engineers, and enterprises. This release targets scientists, academic researchers, engineers, and enterprise users who tackle complex, open-ended problems with incomplete data. Public availability begins immediately for Google AI Ultra subscribers, while early access to the API is being offered to a limited group through an interest form.
We’ve upgraded our specialized reasoning mode Gemini 3 Deep Think to help solve modern science, research, and engineering challenges – pushing the frontier of intelligence. 🧠
— Google DeepMind (@GoogleDeepMind) February 12, 2026
Watch how the Wang Lab at Duke University is using it to design new semiconductor materials. 🧵 pic.twitter.com/BgSEmv00JP
Gemini 3 Deep Think stands out for its technical capabilities, excelling at advanced reasoning tasks across mathematics, physics, chemistry, and engineering. It has achieved leading benchmarks, scoring 48.4% on Humanity’s Last Exam, 84.6% on ARC-AGI-2, and an Elo of 3455 on Codeforces. Expert users have demonstrated its ability to spot overlooked logical errors in research, optimize materials science processes, and translate sketches into 3D-printable objects. Compared to previous versions, this release extends reach to more scientific disciplines and supports new workflows through API integration. Early testers from universities and Google’s own R&D have reported successful real-world applications, such as identifying flaws in academic papers and designing advanced manufacturing recipes.
Google leads this release, leveraging its experience in AI-driven research tools. This update aligns Gemini 3 Deep Think with broader company goals of supporting scientific discovery and practical engineering, furthering Google’s role in pushing the boundaries of computational reasoning and applied AI.
