Google's Gemini adds interactive 3D models and real-time simulations

Google has added the ability for Gemini to generate interactive 3D models and simulations, expanding the chatbot's visual capabilities beyond static images.

The new feature creates interactive visualizations that users can manipulate directly. Available responses include adjustable sliders for parameters like orbital speed, toggles to show or hide model elements, pause controls, and full 3D rotation and zoom functionality. When prompted with "show me a double pendulum" or "help me visualize the Doppler effect," Gemini generates a functional 3D model rather than a static diagram.

Access requires selecting the "Pro" model in the prompt bar and clicking the "Show me the visualization" button beneath Gemini's response. The feature is available to all Gemini app users at no additional cost beyond Pro subscription.

The capability demonstrates real-time computational interaction. A test simulation of the Moon orbiting Earth included an orbital speed slider, orbital path toggle, pause button, and full 3D manipulation controls—allowing users to adjust variables and observe results instantly.

Competitive Context

This announcement follows similar moves from competitors. Anthropic added interactive chart and diagram generation to Claude weeks prior. OpenAI introduced visualization generation for mathematical and scientific concepts in ChatGPT. Previously, Gemini could only generate static interactive images.

The feature represents a shift toward spatial and dynamic reasoning in AI interfaces. Rather than text descriptions or 2D diagrams, users now receive functional 3D models they can manipulate to understand concepts through interaction.

What this means

Google is positioning Gemini as a tool for exploratory learning and concept visualization. The ability to adjust simulation parameters in real-time transforms the chatbot from an explainer into an interactive learning environment. This capability particularly benefits education, physics simulation, engineering visualization, and scientific exploration. The feature parity race with Claude and ChatGPT continues to accelerate, with each model adding interactive and visual capabilities to remain competitive in enterprise and consumer markets.