FoodTruck Bench, an LLM agent business-sim benchmark, lands on Papers with Code

NielsRogge · x · 2026-11-19

NielsRogge added the FoodTruck Bench benchmark to Papers with Code and proposed an automatic sync so new model results appear as they're released.

The benchmark tests sustained business decision-making: an LLM agent starts a simulated Austin food truck with $2,000 and runs it for 30 days using 34 tools — choosing locations, setting menus and prices, ordering perishables, managing staff, negotiating with suppliers and taking loans. Conversation resets each morning, so only the agent's own notes persist; final net worth (median across runs) ranks models. Gemini 4 Carbon leads at $77,217, ahead of Claude Opus 5 and Qwen4 Max.

Original post →

More from Models

Models channel →