Webpage · 2025

Vending-Bench 2

Andon Labs

URLhttps://andonlabs.com/evals/vending-bench-2
TopicsReplicHAI / Agent Evals / 07 General, long-horizon & economic tasks
Tagsagent-eval

Abstract

Measures: Year-long simulated vending business. Metric: Final balance ($).

BibTeX

@misc{andon_labs_vending-bench_2025,
	title = {Vending-{Bench} 2},
	url = {https://andonlabs.com/evals/vending-bench-2},
	abstract = {Measures: Year-long simulated vending business. Metric: Final balance (\$).},
	author = {{Andon Labs}},
	year = {2025},
	keywords = {agent-eval},
}