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.
More from Models
- Agents spent years hillclimbmaxxing while the human at the keyboard became an afterthought — tokenbender · 2026-11-19
- Speculation: Argon/Carbon/Neon may be nested distillations, with 'adapted' dodging 'post-trained' — teortaxesTex · 2026-11-19
- 6.2-Astra reportedly crushes contest benchmarks, finding a novel AWTF26 solution in 2 hours — i_dg23 · 2026-11-19
- KVARK Flash: a proxy that caps DeepSeek's thinking per request, 30-50% fewer tokens — Ill_Contribution_717 · 2026-11-19
- GPT's Ultrafast mode is 'really good' but burns through tokens, says dev — lxfater · 2026-11-19
- NousResearch's Hermes adapter lifts Qwen3.8-27B agent scores: SWE-Bench Pro 29.4%→43.1% at 4× fewer tokens — yb2698 · 2026-11-19