blobfishai/domainbench-24

Assistants
Professional

24 deeply realistic stateful MCP tasks across six enterprise domains.

← Back to Registry

Run this task

CLI:

inspect eval inspect_harbor/blobfishai_domainbench_24 --model openai/gpt-5

Python:

from inspect_ai import eval
from inspect_harbor import blobfishai_domainbench_24

eval(blobfishai_domainbench_24(), model="openai/gpt-5")

Dataset information

Harbor registry blobfishai/domainbench-24
Inspect task blobfishai_domainbench_24
Latest digest sha256:c3f89005c548148c27dc4fe9836eb8a65571788ca8a5567ff6208405cc730078
Samples 24

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