Live page · Day archive

Frontier3DBench: Benchmarking Coding Agents for 3D Creation across Objects, Scenes, and Interactive Open Worlds

Read the original at HF Daily Papers

Summary

Frontier3DBench evaluates coding agents across 145 tasks, revealing that GPT-6.1-sol leads object and scene creation while GPT-6-astra excels in interactive worlds.

Carried by: HF Daily Papers. First seen: .