Large language models can now write complete, interactive 3D worlds as code, but grading those worlds automatically is unreliable.
Existing judges take one view of the output: a vision-language model scores a few rendered snapshots, or a language model reads the source.
On worlds written by five frontier models we find that the two views disagree on 32% of required items, mostly code that no frame shows, and that fixed views miss small close-up contents.
WorldBench
We present WorldBench, a benchmark and judge for open-ended, LLM-generated Three.js worlds.
From one prompt describing a floating voxel island with ten biomes, physics, and day/night and seasonal cycles, the judge explores the running world, controlling its clock, orbiting it, and sending a navigator agent to frame each biome, and reads the code for what it sees.
Mutation Test
A mutation test, in which we remove features by construction, shows that code-only judging gives full credit to four of five removed features, because their code remains in the file.
Our judge cuts the points kept on removed features by a third (5.44 to 3.55 of 7.11), and what it still credits is mostly code that exists but never runs.
Model Evaluation
We evaluate five frontier models: Claude Fable 5.1, GPT-6 Astra, Kimi K3, Grok 4.7 and Gemini 3.1 Pro.
Code, prompt, tests and judge configuration are available at https://github.com/KrishBakshi/worldbench.