Artificial Analysis launches AA-3D benchmark to rank AI models on interactive 3D scenes

What happened

The independent AI benchmarking firm announced AA-3D on 12 October 2026. How AA-3D works A model receives a text brief describing a scene.

AA-3D's human-judged benchmark (a standard test used to compare systems) could drive AI models to prioritize user-centric design, impacting AI development and user experience standards. 12, 2026 Artificial Analysis has a new way to test frontier AI models: ask them to build a 3D world, then let humans decide whose world is better.

The benchmark measures how well models can generate interactive 3D scenes from written briefs, with results ranked by human judges using an Elo-style rating system. It then has to produce a functional three.js experience from that description.

For the uninitiated, three.js is a JavaScript (high-level programming language) library used to render 3D graphics in a web browser. The model is not drawing a picture of a scene.

It is writing the code that builds one. Those outputs are then run in an offline sandbox environment. Advertisement A recruited panel casts blind pairwise preference votes.

Key facts

• The independent AI benchmarking firm — announced: AA-3D on 12 October 2026