Google Gemini can now generate interactive 3D models and simulations

Google has updated Gemini: the chatbot can now generate interactive 3D models and physics simulations right in the conversation. Ask a question, and instead of static text or an image, the system builds an object you can interact with in real time. It is one of the most noticeable expansions of the response format in large language models in recent months.

Here is how it works: in response to a prompt, Gemini creates a three-dimensional model with a set of interactive controls. The user can rotate the object with a mouse, move sliders and enter numerical values, and immediately see how the system's behavior changes. There are no downloads, no detours to third-party services and no waiting for a render: everything happens inside the chat interface, without any additional tools. This is the key difference from the earlier situation, in which a chatbot simply generated a link to an external simulation or suggested downloading a file.

An editor at The Verge tested the feature on a concrete example. He asked Gemini to build a simulation of the Moon orbiting the Earth, with no code and no prior setup. The chatbot generated a three-dimensional scene with several controls: a slider to adjust orbital speed, a toggle for the visibility of the orbital path and a pause button. The physics worked correctly, objects moved smoothly, and all controls responded instantly. Such a result previously required a programmer and specialized software.

Until now, generative chatbots handled mainly text, code and images. Interactive simulations are a qualitatively different level: they require not just drawing an object but generating working logic for its behavior, including physics and response to user input. In effect, Gemini now acts not only as a content generator but also as a builder of educational and research tools on the fly, without involving developers.

The use of this response format is obvious in several areas. In education, instead of reading a description of planetary orbits, a student can move a slider and see how a change in speed affects the trajectory. In engineering, it allows quick visualization of a mechanism or physical process without launching specialized software such as MATLAB or SolidWorks. In medicine, it lets users examine an anatomical structure from all sides. In design, it makes it possible to judge an object's shape in three dimensions during a discussion, without leaving the conversation.

Google has not yet disclosed technical details of how exactly Gemini generates the simulation logic, whether it writes WebGL or Three.js code under the hood or uses another approach. Neither the methodology nor the limits on supported object types have been officially announced. From the end user's point of view, though, implementation details matter little: the result is what counts, and it already looks convincing in the first demonstrations.

The update fits into a broader competitive trend. Major AI labs are competing not only on the accuracy of text answers but also on the richness of output formats. OpenAI launched Canvas for collaborative editing of documents and code, Anthropic is developing artifacts with interactive HTML, and now Google is adding 3D and physics simulations. Chatbots are gradually turning from text assistants into multi-format work environments.

For Gemini users, this means expanded capabilities without extra technical skills. Want to understand how a pendulum works? Ask. Want to see a molecule in three dimensions? Ask that too. Want to compare the behavior of two different springs? Set the parameters and watch. The line between a question and an interactive textbook keeps blurring, and 3D simulations are one of the clearest confirmations of that.