Concept preview made for @theartificialintelligence by Yash & teamConcept preview · by Yash & team Read the note →
The AI Globe

News · Models & labs · 3 August 2026

Qwen 3.8 Max just built better 3D physics scenes than Fable 5 while costing about 7x less to run.

Test was done by atomic chat, a desktop app that runs LLMs locally.

Outputs:

Qwen 3.8 Max: 46.6K tokens, $0.28

Fable 5: 38.7K tokens, $1.93

Both models got the same brief, three self-contained HTML files, each a scene that simulates itself.

The prompts asked for a marble machine lifting marbles onto a wheel and a loop, a car assembly line, and a sawmill cutting logs into planks.

These tests were actually pretty brutal. Shows whether the model maintained object state, collisions, and machine geometry across the whole scene.

First posted to our Telegram.