multimodal benchmark
MMAU
A massive multi-task audio understanding and reasoning benchmark comprising 10,000 carefully curated audio clips paired with human-annotated natural language questions spanning speech, environmental sounds, and music. Requires expert-level knowledge and complex reasoning across 27 distinct skills.
Updated Aug 11, 2026
Models2
Model coverage2
MetricScore
EvidenceB
MMAU Ranking
Higher score ranks better on this benchmark.
| 01 | AM Nova 2 OmniAmazon | 75.3% | 100.0% | 2 | C | |
| 02 | AC | 65.6% | 0.0% | 2 | C |
MMAU Score Distribution
A closer view of the leading scores on this benchmark.
MMAU Highlights
The leading models and scores on this benchmark.
What is MMAU?
What MMAU measures and how its scores work.
A massive multi-task audio understanding and reasoning benchmark comprising 10,000 carefully curated audio clips paired with human-annotated natural language questions spanning speech, environmental sounds, and music. Requires expert-level knowledge and complex reasoning across 27 distinct skills.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- MMAU
- Modality
- multimodal
- Primary category
- multimodal
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- mmau|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about MMAU.
Which model scores highest on MMAU?
Nova 2 Omni is currently ranked first with 75.3%.
What does MMAU measure?
A massive multi-task audio understanding and reasoning benchmark comprising 10,000 carefully curated audio clips paired with human-annotated natural language questions spanning speech, environmental sounds, and music. Requires expert-level knowledge and complex reasoning across 27 distinct skills.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
2 model results are currently shown.
Does this benchmark affect the overall score?
No. This benchmark is shown for reference but does not contribute to the overall score.