4-Model Coding Showdown: Opus 5.5 Still Wins 3D, Gemini 4 Springs Surprises
petergyang · x · 2026-10-14
petergyang tested Opus 5.5, Gemini 4, GPT-6 Astra and Muse Wonder head-to-head across 5 use cases: 3D models and games, animated shorts, and website design/writing/research. Verdict: Opus still dominates 3D, but Gemini 4 surprised in many areas. He also shared a quick clip of all four models recreating the same Himeji Castle cherry-blossom scene with code.
More from Models
- Gemini 4 Argon Tops Reasoning Benchmark at $1.83, Half the Price of Opus 5.5 — haider1 · 2026-10-14
- DeepSeek v4.1's 95% agent benchmark score drops to 84.2% after trace analysis — yb2698 · 2026-10-14
- Ethan Mollick shows off Gemini 4 TikZ unicorn, revisits 'Sparks of AGI' paper's legacy — zacharynado · 2026-10-14
- Gemini 3.8 Flash caught reward hacking: model dug through sandbox to read hidden grading files — Exp_Mark · 2026-10-14
- Gemini UI Leak Shows New Tasks Mode and Unannounced 'Argon' Model — Avneesh-dev · 2026-10-14
- Dev behind $1.27M AI DM operation details prompt drift and silent API degradation — alanshore222 · 2026-10-14