2026Alibaba Qwen Teamopen source
E-Commerce Bench
E-Commerce Bench is a comprehensive, open-source benchmark designed to evaluate LLM agents in a simulated 365-day autonomous business environment. Agents act as store owners, managing tasks such as supplier negotiation, inventory procurement, pricing, and cash-flow management to maximize year-end total assets.
365-day long-horizon simulation of autonomous business operations
Deterministic environment ensuring reproducibility for fair model comparison
Multi-dimensional evaluation across seven metrics including negotiation, fraud detection, and financial discipline
pricingFree and open-source
regionChina