# MMAU: Voice Benchmark Profile

> Measures expert-level understanding and reasoning across speech, environmental sound, and music.

- Scope: 10,000 audio clips; 27 tasks; speech, sound, and music domains
- Measurement lanes: Spoken reasoning
- Primary metric: Test accuracy by domain and overall average
- Available evidence: Machine-readable benchmark-owner leaderboard
- Owner: MMAU authors
- Source snapshots refreshed: 2026-09-11

## Interpretation limit

The refreshed table uses the parsed MMAU-v05.15.25 test results. It does not merge older benchmark versions or unverified community-reported rows.

## Primary sources

- [Paper](https://arxiv.org/abs/2410.19168)
- [Code](https://github.com/Sakshi113/MMAU)
- [Dataset](https://huggingface.co/datasets/gamma-lab-umd/MMAU-test)
- [Owner page](https://sakshi113.github.io/mmau_homepage/#leaderboard-v15-parsed)

Canonical page: https://benchlm.ai/voice-benchmarks/mmau