multimodal benchmark
MMAU Leaderboard
MMAU is a multimodal benchmark for audio understanding and reasoning across speech, environmental sounds, and music.
Updated Oct 23, 2026
Models5
Model coverage5
MetricScore
EvidenceB
MMAU Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelAC | Score81.80% | Percentile100.00% | Participants5 | EvidenceC | Evaluated |
| Rank02 | ModelTM | Score77.20% | Percentile75.00% | Participants5 | EvidenceC | Evaluated |
| Rank03 | ModelTM | Score77.00% | Percentile50.00% | Participants5 | EvidenceC | Evaluated |
| Rank04 | ModelAM Nova 2 OmniAmazon | Score75.30% | Percentile25.00% | Participants5 | EvidenceC | Evaluated |
| Rank05 | ModelAC | Score65.60% | Percentile0.00% | Participants5 | EvidenceC | Evaluated |
MMAU Highlights
The leading models and scores on this benchmark.
MMAU Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for MMAU
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
What is MMAU?
What MMAU measures and how its scores work.
MMAU is a benchmark comprising 10,000 audio clips paired with human-annotated natural language questions across 27 distinct skills.
MMAU measures audio understanding and reasoning performance using a Score reported as a ratio.
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
- overall
LLM Stats. Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about MMAU.
Which model scores highest on MMAU?
Qwen3.8 Omni Flash is currently ranked first with 81.80%.
What are the top three models on MMAU?
The current leaders are Qwen3.8 Omni Flash (81.80%), Inkling (77.20%), and Inkling-Small (77.00%).
Which MMAU model has the lowest official input price?
Qwen2.5-Omni-7B has the lowest matched official input price at $0.10 input / $0.40 output per 1M tokens.
Which models are fastest among MMAU results?
No matched runtime record is currently available.
Does the highest score result prove overall model quality?
No. This benchmark measures one defined capability or task. The overall LLMBoard score uses a separate aggregation across eligible benchmark evidence.