AIHacker Newsabout 2 hours ago
AI models draw Mona Lisa in canvas arena
1 min read
Four vision models used colored-pencil tools to draw the Mona Lisa and Starry Night. Gemini 3.6 Flash scored highest on structural similarity (0.449 peak) but over-edited. GPT-5.6 Sol produced the best-looking drawings. Claude Fable 5 cost $160, roughly 20x the others, for worse output. Grok 4.5 rarely produced usable results.
Level
Hype check
Tap to vote and see what everyone thinks.
Summary by ByteBrief
