15 examples of what Gemini 3 can do

Our newest model, Gemini 3, can help you learn anything, build anything and plan anything. It’s the best model in the world for multimodal understanding, meaning it can synthesize information about any topic across text, images, video, audio, code and more. It’s also our most powerful agentic and vibe coding model yet, offering a big productivity boost for developers. And Gemini 3 can better help you get things done, taking action on your behalf by navigating complex, multi-step workflows from start to finish all while under your control and guidance.

We’ve released Gemini 3 Pro in preview and made it available across a suite of Google products — including the Gemini app, AI Mode in Search, Google AI Studio and more — so you can use it in your daily life. To give you some inspiration, here are 15 examples of what our most intelligent model can help you do.

Learn anything

1) Break down technical scientific topics with coded visualizations

Gemini 3 is state-of-the-art on multimodal understanding and has a 1 million-token context window. So it can take any kind of input you give it — from text to video to code and beyond — and help you learn in ways that make sense for you, like with an interactive guide based on a dense research paper.

2) Get presentation coaching tailored to you

With just a recording of your practice presentation and your slides, Gemini 3 can act as your presentation coach. The model uses advanced reasoning to not only understand and evaluate your performance, but also applies its in-depth knowledge to offer constructive and actionable advice. 

3) Dive deep into a scientific concept

AI Mode in Search now uses Gemini 3’s reasoning power, multimodal understanding and generative UI capabilities to dynamically create the ideal layout for your questions. When the model detects that an interactive tool will help you better understand the topic, it codes a custom simulation or tool in real-time and adds it into your response. That way it can show you what RNA does instead of just telling you, plus you’ll see links to keep exploring content from across the web.

4) Learn with detailed infographics

Nano Banana Pro (Gemini 3 Pro Image) uses Gemini 3’s state-of-the-art reasoning and real-world knowledge to visualize information better than ever before and help you learn about new subjects. You can ask it to create content like infographics for anything from the weather in a specific city, to how to make Elaichi Chai, to the care and keeping of your latest house plant. 

5) Make strides in your hobby

With Gemini 3’s massive long-context window; state-of-the-art reasoning capabilities; and vision and spatial understanding, you can upload a video of yourself playing a sport for up to an hour and receive coach-level advice. Gemini 3 will identify that you’re the player, filter out noise and offer a detailed visual analysis, complete with information like form evaluation and suggested drills.

6) Generate custom interfaces to explore different concepts

Gemini 3’s reasoning and multimodal capabilities have enabled generative interfaces like dynamic view, a new experiment in the Gemini app. Dynamic view uses the model’s agentic coding capabilities to design and code a custom user interface in real-time, perfectly suited to your prompt. For example, ask Gemini to “explain the Van Gogh Gallery with life context for each piece,” and you'll receive a stunning, interactive response that lets you tap, scroll and learn in ways static text can’t.

7) Evoke complex scientific topics with art

It can be tough to wrap your mind around something like, say, nuclear fusion. But Gemini 3 can deeply comprehend this kind of nuanced scientific topic, then express that understanding creatively through both code and poetry simultaneously.

Build anything

8) Vibe code rich, interactive web UI

Gemini 3 is exceptional at zero-shot generation. It handles the heavy lifting of multi-step planning and coding details, allowing you to focus on the creative vision. With natural language, describe what you have in mind, like a website to promote a retro dance night. The model’s significantly improved complex instruction following and deep tool use can translate your high-level idea into an interactive landing page with a single prompt.

9) Make a static image interactive 

Thanks to Gemini 3, a static image can become a board game, a napkin sketch can turn into a full website and a diagram can take on new life through an interactive lesson. The model’s deep multimodal understanding can interpret when the content of an image might be most compelling in an interactive format, then translate it to be functional.

10) Illustrate massive differences in scale

You know a sub-atomic particle is tiny, and the galaxy is huge. But with Gemini 3, you can build a way to see those differences in size. The model excels at coding because of its ability to synthesize disparate pieces of information and follow complex, creative instructions. It also understands the intent behind your idea, allowing you to go from a rough concept to a functional starting point in a single step.

11) Generate code that works IRL

With our new agentic development platform Google Antigravity, you can build faster and manage intelligent agents that operate across the editor, terminal and browser. Antigravity uses Gemini 3’s advanced reasoning, tool use and agentic coding capabilities to act as your partner, generating code complex enough to work in the real world — like in the case of the classic cartpole problem.

12) Create a custom trip itinerary

Visual layout is another experimental generative interface experience in the Gemini app. It moves beyond text with an immersive, magazine-style view featuring photos and modules that you can interact with to further customize your response. For instance, ask it to “plan a 3-day trip to Rome,” and you get an explorable itinerary tailored to your preferences.

13) Get help with what’s important to you

Gemini 3’s generative UI capabilities in Search can also help build tools for your more practical questions. Now, AI Mode can make you a custom-built interactive loan calculator to compare two different options and see which offers the most long-term savings, and gives you the ability to change and customize the inputs to help you get even more insights.

14) Achieve inbox zero 

Gemini Agent is an experimental feature that handles multi-step tasks directly inside the Gemini app, and it can help with things like triaging your emails. Built on insights from Project Mariner and using Gemini 3’s advanced reasoning, Gemini breaks down complex requests using tools like Deep Research; Canvas; your Google Workspace connected apps like Gmail and Calendar; and live web browsing. When using it, you remain in control: Gemini is designed to seek confirmation before critical actions, and you can take over anytime. 

15) Make the most of your weekends

With Gemini 3 in Search, you can ask even more complicated questions and get richer, more visual and helpful responses in AI Mode. Let’s say you have very specific conditions in mind for catching some waves — put those guidelines into AI Mode. Gemini 3 once again uses its multimodal understanding and agentic coding to generate the most helpful layout on the fly, even building visual elements like images, tables and grids to help you choose. Surf’s up!