Finance
CoffeeBench
Recorded net income of language-model agents managing a coffee roaster in a 90-day multi-agent economy.
1items
7subjects
Reference code: Apache-2.0. The trajectory website does not state a separate data license.license
agents_and_tool_usedomain
financedomain
reasoningdomain
textmodality
item-level responses released
Response matrix
Loading response matrix…
lowhighUnobserved
Scale: Unbounded numeric score