3DSceneBench Tests Whether Coding Agents Can Build Functional 3D Worlds
PranaLabs 与 UC Berkeley 发布 3DSceneBench，首个评测编程智能体构建功能性 3D 世界的基准。它不以场景外观是否逼真为标准，而是考察重建结果能否真正使用，如抽屉能否打开等交互功能，面向
2026-11-14 ~ 2026-11-14 · 2 related posts
- 3DSceneBench: coding agents rebuild livable 3D rooms but top functionality score is just 42.1 — yizhu59 · 2026-11-14
- 3DSceneBench tests whether coding agents can build functional 3D worlds — yizhu59 · 2026-11-14