terminal-bench@2.0

Version 2.0 of Terminal-Bench, a benchmark for testing agents in terminal environments. More tasks, harder, and higher quality than 1.0.

← Back to Registry

Run this task

CLI:

inspect eval inspect_harbor/terminal_bench_2_0 --model openai/gpt-5

Python:

from inspect_ai import eval
from inspect_harbor import terminal_bench_2_0

eval(terminal_bench_2_0(), model="openai/gpt-5")

Dataset information

Harbor registry	terminal-bench@2.0
Inspect task	terminal_bench_2_0
Version	2.0
Samples	89
Paper	arxiv

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