Skip to main content
Imagination, compiled

Gemini 4 Argon helps builders create 3D worlds

Google's newest frontier model, Gemini 4 Argon, was built for demanding work in coding, finance, law, cybersecurity and science. Since launch, community developers have pushed it far beyond expectations, turning single images and live data feeds into ambitious 3D creations. Google has spotlighted five standout builds that reveal how far it can go.
Gemini 4 Argon helps builders create 3D worlds
Gemini 4 Argon helps builders create 3D worlds

Google's new frontier model, Gemini 4 Argon, is designed for deep work on complex tasks in coding, finance, legal, cybersecurity, and science. Google says its depth and precision across multi-step tasks let Argon outperform other frontier models on benchmarks across those domains. Since the broad rollout, community builders have used it to create interactive tools and 3D worlds. Google highlighted five of these builds, including a globe that maps tectonic shockwaves in real time and a 3D multiplayer game.

Five builds, five different strengths

Argon's upgrades in spatial reasoning, mathematical precision, and visual coding make it capable of generating complex 3D environments. In a test by Lumina (@LuminaBench on X), Argon rendered a 3D seaplane simulation with realistic lighting, reflections, and water movement. Because it maintains depth and precision across multi-step tasks, it could coordinate the motions of different elements at the same time.

Argon also handles dense, unstructured data well. Using Gemini 4 Argon in Antigravity, Alex Patrascu (@maxescu on X) combined NASA's live global wildfire feed with seismic data from the U.S. Geological Survey to build an interactive 3D globe. Argon parsed the data, mapped coordinates, and rendered animated shockwaves and hotspots.

Ashutosh Shrivastava (@ai_for_success on X) used Gemini 4 Argon with Blender and Three.js to generate a detailed simulation of a high-bypass turbofan jet engine. The model displayed live measurements, data, and part-by-part specs. Argon modeled individual elements before rendering them together in a 3D environment.

Argon can also turn flat images into 3D scenes. The Bugged Dev (@thebuggeddev on X) gave the model a single image of a Gothic Victorian carriage and asked for an interactive 3D version. The result included functioning doors and windows, flickering oil lamps, and an undercarriage that reacts to bumps in the road.

Finally, Chong-U (@chongdashu on X) built “Backyard Rascals,” a multiplayer browser game in which cartoon animals race to capture the other team's flag. The characters run, collide, whack each other, and cheer as multiple players engage in real time. Google credits Argon's ability to maintain depth and precision across complex workflows for the game's features.

Map_1_tPX0cYV.mp4 1 / 3

Key Features at a Glance

  • Spatial reasoning: Major upgrade – enables complex 3D environments with realistic lighting, reflections, and motion, as in the seaplane simulation.
  • Mathematical precision: Major upgrade – supports accurate mapping of live coordinate data, as in the wildfire and seismic globe.
  • Visual coding: Major upgrade – powers interactive builds such as the jet engine simulation and the multiplayer game.
  • Multi-step task depth: Sustains long workflows – lets the model coordinate simultaneous elements and model parts before rendering them together.
  • Image-to-3D generation: Single image input – turns a flat carriage image into an interactive 3D experience with working doors, lamps, and suspension.
  • Cross-tool integration: Works with Antigravity, Blender, and Three.js – lets developers combine Argon with existing 3D and coding tools.
  • Availability

    — Google

    Gemini 4 Argon is available globally to developers and enterprises through the API, in AI Studio and the Gemini platform. Google AI Ultra and paid Pro subscribers can use it in Google Antigravity. Google AI Ultra and Pro subscribers can access it in the Gemini app and AI Mode in Search.

    Who Where available
    Developers and enterprises The API, AI Studio and the Gemini platform
    Google AI Ultra and paid Pro subscribers Google Antigravity
    Google AI Ultra and Pro subscribers The Gemini app and AI Mode in Search

    Felipe Santos

    “Artificial intelligence can process the world in milliseconds, but only the human heart can give meaning to every second lived” – Mr. Santos