Pixel32Bench makes LLMs draw 32×32 pixel Super Mario blind, then compares them
TheMoonMidas · x · 2026-09-23
Moon Midas launched Pixel32Bench, a fan experiment giving LLMs one prompt and a 32×32 canvas to draw pixel Super Mario zero-shot. A local Node.js harness sends identical prompts via OpenRouter with strict JSON schema validation, logging price and time. Results are filterable and cross-referenced with Artificial Analysis intelligence scores; models hitting output limits are marked failed. A 16×16 version and downloadable runner also exist.
Related event: Pixel32Bench Tests LLMs at Drawing 32×32 Pixel Mario(2 posts)→
More from Fun
- Modder turns N64 Ocarina of Time into a fully voice-acted modern AAA-style game — banteg · 2026-11-12
- Gas-for-AI-datacenters forum co-located with CoRL shows energy demand spillover — carlosdponx · 2026-11-12
- ML meme: linear algebra dominates all other fields of math, 'add nonlinearities' — burny_tech · 2026-11-12
- Robot fails at folding a towel, reassuring roboticists frontier models won't eat robotics yet — chris_j_paxton · 2026-11-12
- AI-Generated EXO 'Growl' MV Parodies US vs. China AI Giants — basedjensen · 2026-11-12
- The Goldman Sachs riddle where eating the poison is right—with exactly 253 lions — aakashgupta · 2026-11-12