1
See
The agent gets eight pictures of a scene with their camera poses, up to 16 close-ups, and the scene's tasks in plain words. Weights and friction are never given.
Can coding agents build functional and versatile 3D worlds?
Can coding agents build one simulated world that supports a scene's many uses? 3DSceneBench covers 49 whole-room scenes in seven categories, with up to 3,002 objects per scene, 471 tasks and 36,871 per-object tests. Each world is scored for appearance, geometry and functionality.
The 3D scenes are not in this copy of the site. Run fetch_scenes.sh to add them.
1
The agent gets eight pictures of a scene with their camera poses, up to 16 close-ups, and the scene's tasks in plain words. Weights and friction are never given.
2
In a closed container, with up to 180 minutes or 10M output tokens, it writes one MuJoCo scene. Every object is a named body; every door and drawer is a real joint.
3
Verifiers load the world, render it, measure it, push its objects, open its doors and let a robot work in it, then do the same in the reference room. The dials show the best score any agent reaches.
A picture can't tell you if it carries.
Same scene, same camera, same test, both recorded in the simulator. The submitted world is drawn in plain colours, without its textures.
Same scene, same camera, same test, both recorded in the simulator. Marks are from each build's grade report. The submitted world is drawn in plain colours, without its textures.
3DSceneBench mini is out: seven of the 49 scenes, one from each category, each with its reference room inside the task, so a run ends with the full scores on your own machine. The seven are the Shared Office, Pipe Maintenance Room, Outdoor Gear Store, Rehabilitation Center, Chemistry Lab, Bakery and Home Office. The other 42 scenes are coming soon. Getting started, step by step →
First
git clone https://github.com/PranaLabs/3DSceneBench cd 3DSceneBench uv tool install harbor==0.23.0 harbor auth login harbor download pranalabs-ai-team/3dscenebench-mini@v1.0.0
Then build the grader once and check your setup for free, as the guide shows. The benchmark scores a world and does not mind how the world was made, so there are two ways to produce one.
Way 1
For testing a coding agent or a model. Harbor starts your agent inside each scene's container, the agent builds the world there, and the grader scores it. Claude Code, Codex and OpenCode are supported.
harbor run -p 3dscenebench-mini -a claude-code \ -m anthropic/<model> \ --ak disallowed_tools=WebFetch,WebSearch -n 1
Way 2
For testing a method you already have, such as a reconstruction pipeline or a scene generator. Build the worlds anywhere, with no limits, and hand in the files. Harbor only grades them.
PYTHONPATH=$PWD harbor run -p 3dscenebench-mini \ -a scenebench_harbor.submit_files:SubmitFiles \ --ak folder=$PWD/my_copies -n 1
For more information about adding your run to the leaderboard, see Get on the leaderboard on GitHub.