Prosus Vending Bench
Prosus Vending Bench is an open-source benchmark that evaluates how well AI agents run a simulated vending machine business.
1 article
Last mentioned Prosus Vending Bench is an open-source benchmark released by Prosus. An AI agent runs a simulated six-machine vending business for 30 days, starting with a €1,500 budget and handling shifting demand and inventory. It can be used to compare different large language models and agent harnesses.
This entry is based on AIPOST articles and widely known facts. If something is wrong, please send us a correction request.