terminal-bench/terminal-bench

Terminal-Bench is a benchmark for measuring agents’ abilities to complete tasks using a terminal.

← Back to Registry

Run this task

CLI:

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

Python:

from inspect_ai import eval
from inspect_harbor import terminal_bench

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

Dataset information

Harbor registry	terminal-bench/terminal-bench
Inspect task	terminal_bench
Latest digest	sha256:39d9f44b40420cde8fdcc087579c0d72a7e14fa3656d603c3f0d22fb35e27732
Samples	66
Paper	arxiv
Source	https://github.com/harbor-framework/terminal-bench

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