vibrantlabsai/itsm-bench

Assistants
Professional

ITSMBench: enterprise ITSM agent tasks graded on database state.

← Back to Registry

Run this task

CLI:

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

Python:

from inspect_ai import eval
from inspect_harbor import vibrantlabsai_itsm_bench

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

Dataset information

Harbor registry vibrantlabsai/itsm-bench
Inspect task vibrantlabsai_itsm_bench
Latest digest sha256:b26edd5cb47cfe17f2db4b4cbe4bbba98307dc1aba1358e73f4171b342717620
Samples 53
Source https://github.com/vibrantlabsai/Enterprise-Worlds

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