Finance
CEO-Bench
Language-model agents manage a simulated startup; retain published outcomes and complete released trajectories.
3items
18subjects
No explicit data license found in the reviewed viewer or source repository.license
agents_and_tool_usedomain
financedomain
reasoningdomain
textmodality
item-level responses released
Response matrix
Loading response matrix…
lowhighUnobserved
Scale: Item-specific grading scales