aime/aime

Mathematics

Problems from the American Invitational Mathematics Examination (AIME), a 3-hour high-school competition with integer answers (0–999) used to evaluate mathematical reasoning.

← Back to Registry

Run this task

CLI:

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

Python:

from inspect_ai import eval
from inspect_harbor import aime

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

Dataset information

Harbor registry aime/aime
Inspect task aime
Latest digest sha256:534167df6e50234cdc0aa9c40a7dc6a60f27aeffc18ac981577f5e3272da3589
Samples 60

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