actava-ai/chi-bench

χ-Bench: long-horizon, policy-rich U.S. healthcare workflow agent benchmark spanning provider prior-authorization, payer utilization management, and care management (78 hub tasks).

← Back to Registry

Run this task

CLI:

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

Python:

from inspect_ai import eval
from inspect_harbor import actava_ai_chi_bench

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

Dataset information

Harbor registry	actava-ai/chi-bench
Inspect task	actava_ai_chi_bench
Latest digest	sha256:bd0b20dd71a286d4c4e7b7f17b3047bd9af572bb78bae3091db8f01a9761b325
Samples	78
Paper	arxiv

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