cohere/terminal_bench_aai

Coding
Assistants

AAII Terminal-Bench Hard: 44 hard tasks from terminal-bench v1 (terminal-bench-core==0.1.1), used with the Terminus-2 agent.

← Back to Registry

Run this task

CLI:

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

Python:

from inspect_ai import eval
from inspect_harbor import cohere_terminal_bench_aai

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

Dataset information

Harbor registry cohere/terminal_bench_aai
Inspect task cohere_terminal_bench_aai
Latest digest sha256:d8908945101bb9a713690ac46539d13ca7d44658637f2650a857470926c191b9
Samples 44
Paper arxiv
Source https://github.com/harbor-framework/terminal-bench

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