Last updated: 2026-07-27
Gemini for Science is Google's suite of agentic research tools launched at I/O 2026, built on Co-Scientist, AlphaEvolve, ERA, and NotebookLM. Its Empirical Research Assistance engine generated 14 COVID-19 forecasting models that beat the CDC's CovidHub Ensemble, validated in two peer-reviewed Nature papers.
About Gemini for Science
Gemini for Science is a suite of AI research tools that Google introduced at I/O 2026, built by Google DeepMind and Google Research to speed up the slowest parts of the scientific method for working scientists. It packages four components, Hypothesis Generation, Computational Discovery, Literature Insights, and Science Skills, so a single researcher can move from a research question to a testable model in far fewer manual steps than reading, coding, and testing by hand allows. Hypothesis Generation runs on Co-Scientist and stages a multi-agent idea tournament: separate AI agents propose competing hypotheses, debate their novelty and feasibility, and score them against the existing literature before a researcher ever writes code. Computational Discovery then hands the winning idea to AlphaEvolve and Empirical Research Assistance (ERA), which generates and runs thousands of code variations in parallel to test many modeling approaches at once. Two papers published in Nature alongside the launch reported that ERA produced 14 COVID-19 hospitalization forecasting models that beat the CDC's own CovidHub Ensemble, plus new single-cell analysis methods validated against public bioinformatics leaderboards. Literature Insights, built on NotebookLM, turns a pile of papers into a searchable table and a conversational interface, and can output the summary as a written report, a slide deck, an infographic, or an audio or video briefing. Science Skills is aimed squarely at life sciences teams, wiring in dozens of databases and tools such as UniProt, the AlphaFold Database, AlphaGenome, and InterPro so a computational biologist can query protein structure and genomic data without switching tools. The suite targets academic labs, life sciences R&D teams, and epidemiology or climate researchers who need to test many modeling approaches quickly rather than one at a time. Access to Gemini for Science works through a gradual, request-based rollout on Google Labs, without a published consumer price during the current preview. Enterprises can reach the same Co-Scientist and AlphaEvolve agents in production via Google Cloud, specifically its Gemini Enterprise Agent Platform product, on custom contract terms. The tools run in-browser; there is no dedicated desktop or mobile app. Both Nature papers underpinning ERA were peer-reviewed ahead of the product announcement, a step Google took specifically to back the platform's benchmark claims with independent review rather than marketing copy alone.
Pricing
Free during the Google Labs preview (request-only access, no self-serve paid plan). Google Cloud enterprise deployment of Co-Scientist and AlphaEvolve through the Gemini Enterprise Agent Platform is billed on custom, unpublished contract terms.
Key Features
- Hypothesis Generation tournament: Co-Scientist runs a multi-agent debate that scores rival hypotheses for novelty and feasibility against existing literature before a researcher writes any code.
- Computational Discovery agentic search: AlphaEvolve and Empirical Research Assistance run and score thousands of code variations in parallel, an approach Google calls an agentic search engine rather than a single model call.
- Literature Insights briefings: Built on NotebookLM, it organizes a curated set of papers into a searchable table and exports findings as a report, slide deck, infographic, or audio or video briefing.
- Science Skills database wiring: Connects to more than 30 life science databases and tools, including UniProt, the AlphaFold Database, AlphaGenome, and InterPro, through a single query interface.
- Peer-reviewed bioinformatics benchmark: The ERA research produced 40 novel single-cell analysis methods that outperformed the top human-built methods on a public leaderboard, part of the same peer review published in Nature.
Pros
- Google backed Computational Discovery's benchmark claims with peer-reviewed Nature publications rather than a product blog post alone, an unusual step for a launch announcement.
- Science Skills reaches into dozens of life science databases and tools through one query interface, so a biologist skips manually checking each source.
- Literature Insights turns one briefing request into several deliverable formats, saving research communications teams a manual write-up step.
Cons
- Access is a gradual, request-only rollout through a Google Labs form, so researchers cannot self-serve sign up the way they can for a standard SaaS product.
- There is no published price list for either the Labs previews or the Google Cloud enterprise tier, so budget owners must request a custom quote before committing.
- The suite is split across separate previews rather than one unified workspace: a researcher moves between distinct interfaces depending on whether the task is generating a hypothesis, running an experiment, or reading literature.
Frequently Asked Questions
How much does Gemini for Science cost in 2026?
Google has not published a retail price for Gemini for Science. The Google Labs experiments are free to request during the gradual rollout, while the underlying Co-Scientist and AlphaEvolve agents are also offered to organizations through Google Cloud's Gemini Enterprise Agent Platform on custom contract pricing that Google does not publish as a plan.
Is Gemini for Science free to use?
Yes, for individual researchers: entry to the Labs experiments is currently at no cost, gated behind a request form rather than a self-serve signup, and rolling out gradually rather than to everyone at once. There is no published usage cap because the product has not left the request-access stage.
What are the best alternatives to Gemini for Science?
Consensus and NotebookLM both cover the literature-review half of the workflow if you don't need hypothesis generation or experiment automation. ChatGPT and Perplexity work as general-purpose research assistants but lack a dedicated agentic experiment runner like AlphaEvolve and ERA or the peer-reviewed benchmark backing Google published in Nature.
How does Gemini for Science compare to Consensus?
Consensus is built specifically for fast literature search and answer-finding across papers, with instant self-serve access. Gemini for Science covers that same literature step through its NotebookLM-based Literature Insights tool, then goes further into hypothesis generation and parallel computational experiments, at the cost of a request-only rollout instead of instant signup.
How do you get started with Gemini for Science?
Visit labs.google/science and submit the access request form; Google reviews requests as part of the gradual rollout rather than granting instant access. Enterprises that want Co-Scientist or AlphaEvolve as production agents should instead contact Google Cloud about the Gemini Enterprise Agent Platform.
Top Alternatives
- Consensus: Pick Consensus if you just need fast, self-serve literature search; pick Gemini for Science if the same team also needs to generate hypotheses and run experiments.
- NotebookLM: Pick standalone NotebookLM if literature summarization is the only job; pick Gemini for Science for hypothesis generation and computational experiment running on top of that.
- Perplexity: Pick Perplexity for general web-search answers; pick Gemini for Science when the workflow is a formal scientific method with peer-reviewed benchmark backing.
- ChatGPT: Pick ChatGPT for a general-purpose assistant; pick Gemini for Science for a dedicated pipeline that generates and tests scientific hypotheses end to end.