Medicine
HealthAdminBench
Computer-use agent results on 135 synthetic healthcare-administration tasks, with original strict and process-check-removed judgments.
540items
7subjects
Apache-2.0license
medicinedomain
agents_and_tool_usedomain
textmodality
imagemodality
item-level responses released
Saturation status: No
Response matrix
Loading response matrix…
Correct (1)Incorrect (0)Unobserved
Scale: 1 = correct · 0 = incorrect