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 7, 2026
Published models2
Registry coverage2
MetricScore
EvidenceB
MMAU leaderboard
Sorted by the source-provided rank. Higher score is better according to the registry.
| 1 | AM Nova 2 OmniAmazon | 75.3% | 100.0% | 2 | C | |
| 2 | AC | 65.6% | 0.0% | 2 | C |
Score distribution
Top published rows on the benchmark's original scale.
MMAU highlights
The top published results on this benchmark's own scale.
What is MMAU?
Definition and scoring fields from the benchmark registry.
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. The current registry marks this benchmark as not independently verified with evidence level B.
- Family
- MMAU
- Modality
- multimodal
- Primary category
- multimodal
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- mmau|llm-stats-current
Source-native results are preserved. Eligibility for the overall LLMBoard score is a separate policy decision.
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 unique published model results are currently shown.
Does this benchmark affect the overall score?
This benchmark is preserved as source-native evidence but is not eligible for the current overall score.