Gemini 4 Neon, same picture

One picture, four 3D worlds. Google's Gemini 4 Neon in Antigravity CLI at four effort levels.

Google's Gemini 4 Neon built the island cabin picture as a Three.js world on low, medium, high and extra high effort, from the same prompt and the same copy of Three.js as the Claude, GPT, Muse Ember and Gemini 4 Hydrogen runs. One run each, with no human edits.

This is not a CmdBench benchmark run: no checks, scores or verdicts.

AI-generated picture of a miniature island: a wooden cabin with a stone chimney, a jetty and rowboat, a yellow crane over a half-built timber frame, lumber stacks, rocks and pine trees, in warm late-afternoon light.
Reference picture, AI-generated. Every run got this picture and the same prompt.

The four worlds

One run on each effort level. Each world is served exactly as the model wrote it, with no fixes, and opens full screen in this tab.

Costs are estimates, computed from each run's token counts at Google's Gemini API list prices of 19.11.2026. Antigravity CLI reports no cost.

How it was made

Picture
AI-generated. The exact PNG every run got
Prompt
The same for every run: read the prompt (TASK.md)
Agent
Antigravity CLI 1.5.12
Effort levels
low, medium, high and extra high; one run each
Tools
Read, write and edit file tools in its own folder: no shell, no browser, no web. The model never saw its world running.
Time limit
60 minutes per run
Three.js
0.187.0
Human edits
None. Each world is served exactly as the agent wrote it, with no fixes.
Run date