josancamon19/physician-bench

Medicine

Professional

Harbor packaging of the 100 Apache-2.0 HealthRex PhysicianBench tasks. Runtime requires separately authorized access to the fhir-full:v1 EHR image from Stanford Redivis.

← Back to Registry

Run this task

CLI:

inspect eval inspect_harbor/josancamon19_physician_bench --model openai/gpt-5

Python:

from inspect_ai import eval
from inspect_harbor import josancamon19_physician_bench

eval(josancamon19_physician_bench(), model="openai/gpt-5")

Dataset information

Harbor registry	josancamon19/physician-bench
Inspect task	`josancamon19_physician_bench`
Latest digest	sha256:665cad8a072424b2e0c02d2f0b5dbe8e9e53dcce82bb5b7ae2215553c673cf01
Samples	100
Paper	arxiv
Source	https://github.com/HealthRex/PhysicianBench

See Task Parameters for the parameter set shared across all Harbor tasks.