DishwasherBench – Can Frontier Models Stack a Dishwasher?
DishwasherBench is a new simulation-based game designed to benchmark how language models handle physical tasks like loading a dishwasher. It uses rigid-body physics to evaluate the efficiency and logic of AI agents in a controlled, repeatable environment.
Why it matters
This provides a standardized, physical-world benchmark for AI agents, moving beyond text-based evaluation to test real-world spatial reasoning and task planning.
DishwasherBench is a dishwasher-loading game on a physical simulation of one real machine, built to benchmark language models and playable by people in a browser. The game inside is called Spotless , and the packages are named @spotless/* .
A player loads a 3D model of a Bosch SMV4HAX40G with rigid-body physics. A wash on its Eco 50 programme is then simulated (jets, droplets, run-off, soil and detergent chemistry), and the player gets points for every item that comes out clean. On every level after the first, not everything fits, so the player has to choose what to load and how.
Get smarter about the news
Sign up free for a feed built around what you actually care about, Dive Deeper research on any story, and the full text of every article.
Create free accountAlready have an account? Sign in