LemonadeBench: Evaluating the Economic Intuition of Large Language Models in Simple Markets
Fuente:
arXiv
Guardado en:
| Autor principal: | |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866911451749285888 |
|---|---|
| author | Vyas, Aidan |
| author_facet | Vyas, Aidan |
| contents | We introduce LemonadeBench v0.5, a minimal benchmark for evaluating economic intuition, long-term planning, and decision-making under uncertainty in large language models (LLMs) through a simulated lemonade stand business. Models must manage inventory with expiring goods, set prices, choose operating hours, and maximize profit over a 30-day period-tasks that any small business owner faces daily. All models demonstrate meaningful economic agency by achieving profitability, with performance scaling dramatically by sophistication-from basic models earning minimal profits to frontier models capturing 70% of theoretical optimal, a greater than 10x improvement. Yet our decomposition of business efficiency across six dimensions reveals a consistent pattern: models achieve local rather than global optimization, excelling in select areas while exhibiting surprising blind spots elsewhere. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_13209 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | LemonadeBench: Evaluating the Economic Intuition of Large Language Models in Simple Markets Vyas, Aidan General Finance Artificial Intelligence We introduce LemonadeBench v0.5, a minimal benchmark for evaluating economic intuition, long-term planning, and decision-making under uncertainty in large language models (LLMs) through a simulated lemonade stand business. Models must manage inventory with expiring goods, set prices, choose operating hours, and maximize profit over a 30-day period-tasks that any small business owner faces daily. All models demonstrate meaningful economic agency by achieving profitability, with performance scaling dramatically by sophistication-from basic models earning minimal profits to frontier models capturing 70% of theoretical optimal, a greater than 10x improvement. Yet our decomposition of business efficiency across six dimensions reveals a consistent pattern: models achieve local rather than global optimization, excelling in select areas while exhibiting surprising blind spots elsewhere. |
| title | LemonadeBench: Evaluating the Economic Intuition of Large Language Models in Simple Markets |
| topic | General Finance Artificial Intelligence |
| url | https://arxiv.org/abs/2602.13209 |