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
- OpenAI ships GPT-6.1 Terra; Brockman says its computer use now beats his own speed — gdb · 2026-10-27
- Kolab Benchmark Uses Pro Screen Recordings to Show AI Agents Overestimate Collaboration Quality — minnesotanlp · 2026-10-27
- Dev argues Claude burns far more tokens than GPT models for the same coding work — haider1 · 2026-10-27
- Stop building agents that can't change models: stable contracts, external state, real evals — rseroter · 2026-10-27
- Cheap models can cost more in agent harnesses than frontier ones, researcher warns — vasuman · 2026-10-27
- Kanzo: A 5k-Line Rust Kanban Binary With MCP for Claude Code and Codex — allmudi · 2026-10-27