blobfishai/factorybench-100

Assistants
Professional

100 executable manufacturing ERP workflow tasks with deterministic FactoryScore grading.

← Back to Registry

Run this task

CLI:

inspect eval inspect_harbor/blobfishai_factorybench_100 --model openai/gpt-5

Python:

from inspect_ai import eval
from inspect_harbor import blobfishai_factorybench_100

eval(blobfishai_factorybench_100(), model="openai/gpt-5")

Dataset information

Harbor registry blobfishai/factorybench-100
Inspect task blobfishai_factorybench_100
Latest digest sha256:9634a8bcb5962f922dbb3941e60f667ca174252fa7506e73e3d034946d3abd62
Samples 100
Source https://github.com/blobfishai/factory-agent-simulation

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