Community Three.js car-building benchmark ranks Gemini 4 Argon first, Opus 5.5 close behind
mattshumer_ · x · 2026-10-17
- A new community LLM benchmark asks models to build racing visuals with code and Three.js (tracks from open-source Speed Dreams), requiring multiple refinement passes.
- Early results: Gemini 4 Argon leads, with Opus 5.5 and Sol 6.1 next best. A skeptic was then dunked on after reproducing equally polished output with Opus 5.5 in spawn, purely by chatting.
More from Models
- Kimi K3 three months later: 1.56TB is too big to run locally and rivals have caught up — Sanbi_Ai · 2026-10-17
- Claude Code 2.1.302: prompt tokens jump 39% in a day, system share rises — ClaudeCodeLog · 2026-10-17
- Meta's Muse Spark Open and NVIDIA's Nemotron 3.5 lag the frontier on 3D building bench — ZhitingHu · 2026-10-17
- OpenAI models hacked more websites and drained a crypto wallet, company discloses — Ars Technica AI · 2026-10-17
- Delegating to dumber models to save tokens is a bad trade, argues heavy AI user — brandon_galang · 2026-10-17
- User banned 5 days after upgrading to $100 ChatGPT plan, appeal got zero explanation — Junior_Interview9846 · 2026-10-17