Tag

ExeWorldBench

Evaluates whether models can reconstruct executable 3D worlds from visual or textual inputs by providing Blender-based tasks, assets, and automated evaluation for code-driven realizations.

BlenderWorld

Benchmark package for evaluating visual agents that produce editable 3D Blender projects from real-world text, image, and video briefs; includes 223 tasks, 2,651 binary rubrics, Harbor-compatible inputs with Base64 previews, and multi-view render verification.