multimodal benchmark
MMAU Sound
A subset of the MMAU benchmark focused specifically on environmental sound understanding and reasoning tasks. Part of a comprehensive multimodal audio understanding benchmark that evaluates models on expert-level knowledge and complex reasoning across environmental sound clips.
Updated Aug 11, 2026
Models1
Model coverage1
MetricScore
EvidenceB
MMAU Sound Ranking
Higher score ranks better on this benchmark.
| 01 | AC | 67.9% | 100.0% | 1 | C |
MMAU Sound Highlights
The leading models and scores on this benchmark.
What is MMAU Sound?
What MMAU Sound measures and how its scores work.
A subset of the MMAU benchmark focused specifically on environmental sound understanding and reasoning tasks. Part of a comprehensive multimodal audio understanding benchmark that evaluates models on expert-level knowledge and complex reasoning across environmental sound clips.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- MMAU Sound
- Modality
- multimodal
- Primary category
- multimodal
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- mmau-sound|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about MMAU Sound.
Which model scores highest on MMAU Sound?
Qwen2.5-Omni-7B is currently ranked first with 67.9%.
What does MMAU Sound measure?
A subset of the MMAU benchmark focused specifically on environmental sound understanding and reasoning tasks. Part of a comprehensive multimodal audio understanding benchmark that evaluates models on expert-level knowledge and complex reasoning across environmental sound clips.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
1 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.