Blind Test: 3 Coding Models Build a 3D World
MaziyarPanahi · x · 2026-07-18
A blind test was conducted on Kimi K3, GLM-5.2, and Opus 4.8: they were tasked with generating a complete 3D world using only a single HTML file and three.js. The author manually altered no code, leaving another blinded model to score the rendered results.
The author initially expected a closed-source model to win, but that wasn't the case. They also noted that all three models in this setup are "top-tier coding models," making the outcome entirely dependent on the final generation quality.
Related event: Kimi K3 Stuns with Coding and 3D Reasoning, Beating SOTA Models(5 posts)→
More from coding & agent
- Scoble says AI “loops” really means long-running multi-agent workspaces — Scobleizer · 2026-07-22
- Open-source runtime lets each repo define its own AI code reviewer — ibabufrik · 2026-07-22
- Indie Dev Asks: What's Actually Broken in Your AI Agent's Memory Today? — AcceptableTime7937 · 2026-07-22
- Fractal adds recursive agent loops for complex multi-step workflows — ryanpettry · 2026-07-22
- ACM essay says AI did not make programming easier, only differently difficult — tchalla · 2026-07-22
- Building a Multimodal Agent Orchestrator from the Ground Up — dair_ai · 2026-07-22