Vending-Bench what it measures, how it is scored and who leads it
Agents and tools · Andon Labs · introduced Feb 20, 2025 · Net worth
About this benchmark
- Task
- Run a simulated vending machine business for a long time: inventory, orders, prices, fees.
- Dataset
- A simulated environment; runs exceed 20 million tokens.
- Method
- Scored on money made over the run; tests long-horizon coherence.
- Metric
- Net worth
- Organization
- Andon Labs
- Introduced
- Feb 20, 2025
Versions
Newest first. New versions are added, never rewritten.
| Version | Date | |
|---|---|---|
| 1Released with the paper. | Feb 20, 20251 year ago | Released with the paper. |
Sources: each benchmark's paper (arXiv) and its official site or leaderboard. Scores are the boards captured here every day, exactly as published.