I gave the same card to the latest AI and let them draw it freely.
I was just impressed But when I compared them, Suddenly, the “AI comparison” itself became irrelevant. Gemini 3.7 Flash, Grok 4.6, Qwen 3.8 Max, Claude Opus 5 Give everyone the ace of clubs,
Local models just made an insane generational leap.
🤯 This Flappy Bird gameplay (physics, collisions, and game loop) was 100% coded by Qwen 3.8 27B (6-bit). Zero hallucinations on the canvas, flawless logic. The gap with cloud models is gone. 👇
I've released the benchmark for 7 different models
GPT 4.6, GPT 5.6 Sol, GLM 5.2 & 5.3, Laguna S2.1, Qwen 3.8 27B and DeepSeek Flash V4 0731 ! some local, some cloud with one single prompt and no steering, using OMP (for the first time). Yotubue Link :
Qwen 3.8 27b firework show creation using my local build MARCUS.
Prompt: "Create a 4th of July fireworks show over NYC skyline. Make it detailed, polished, with eye popping effects. Do any web search needed to gather more information about the NYC skyline and the locations of
You have reached the end of the archive
All of qwen38