theagentcompany/theagentcompany

Professional

Assistants

Coding

An agent benchmark with tasks in a simulated software company across GitLab, Plane, OwnCloud, and RocketChat services, evaluating LLM agents on real-world professional work.

← Back to Registry

Run this task

CLI:

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

Python:

from inspect_ai import eval
from inspect_harbor import theagentcompany

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

Dataset information

Harbor registry	theagentcompany/theagentcompany
Inspect task	`theagentcompany`
Latest digest	sha256:f31a4e945df5e24664acd8170637fdc774b6d593aac6274a1580fc7f2bb76cd0
Samples	174
Paper	arxiv
Source	https://github.com/TheAgentCompany/TheAgentCompany

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