Gemini for Science
Powering scientific discovery with AI
Accelerate your research with AI tools and resources built to support scientific endeavors
Science experimental tools on Google Labs
A collection of experiments exploring the future of AI-powered scientific discovery
Literature Insights
Synthesize scholarly literature to identify new research opportunities. Create grounded research artifacts and extract paper data into queryable tables mapped directly to source evidence.
Hypothesis Generation
Generate potential research directions for breakthrough discoveries. Use a multi-agent system that simulates the scientific method to identify knowledge gaps and propose testable research plans.
Computational Discovery
Discover models and algorithms to accelerate your research. Leverage an agentic research engine that generates and scores code variations based on your optimization metrics.
Science in Google Antigravity
Turn Google Antigravity into a professional scientific workbench by orchestrating frontier models and unified scientific resources. Condense complex multi-step analysis pipelines that normally take hours into minutes.
Proving the potential
We believe AI can be a force multiplier for human ingenuity, empowering researchers to tackle some of the world's most pressing challenges.
These tools are already assisting in real-world discovery across multiple fields of science. From combating antimicrobial resistance to optimizing fabrication methods for crystal growth, see how leading experts are using our AI tools to accelerate a new era of discovery.
Slide 1 of 5
Co-Scientist: Accelerating breakthrough Science
We’ve put Co-Scientist into the hands of real scientists to help some of the world's leading experts develop new hypotheses and tackle some of the hardest problems.
Combating antimicrobial resistance
Ben Luisi’s lab at the University of Cambridge is using a suite of AI tools to target two essential bacterial processes at once, creating a powerful new way to fight superbugs without triggering further resistance.
Optimizing 2D semiconductor fabrication
At Duke University, the Wang Lab utilized Deep Think mode to solve a complex challenge in materials science: optimizing fabrication methods for crystal growth.
Identifying logical errors in complex mathematics research
Lisa Carbone, a mathematician at Rutgers University, used Deep Think mode to review a specialized paper in the field of high-energy physics and infinite-dimensional algebra.
Accelerating mechanical engineering and rapid prototyping
Anupam Pathak, an R&D lead in Google’s Platforms and Devices division, tested Deep Think mode to accelerate the design and prototyping of complex physical components.
Go deeper
Accelerate discoveries with specialized Gemini tools that scale your research and sharpen your reasoning.
Gemini Deep Research
Save hours of work with Deep Research as your personal research assistant
Gemini Deep Think
By blending deep scientific knowledge with everyday engineering utility, Deep Think mode moves beyond abstract theory to drive practical applications