mmau@1.0

Multimodal

MMAU: 1000 carefully curated audio clips paired with human-annotated natural language questions and answers spanning speech, environmental sounds, and music.

← Back to Registry

Run this task

CLI:

inspect eval inspect_harbor/mmau_1_0 --model openai/gpt-5

Python:

from inspect_ai import eval
from inspect_harbor import mmau_1_0

eval(mmau_1_0(), model="openai/gpt-5")

Dataset information

Harbor registry	mmau@1.0
Inspect task	`mmau_1_0`
Version	1.0
Samples	1000
Paper	arxiv

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