multimodal benchmark
A subset of the MMAU benchmark focused specifically on speech understanding and reasoning tasks. Part of a comprehensive multimodal audio understanding benchmark that evaluates models on expert-level knowledge and complex reasoning across speech audio clips.
Updated Aug 7, 2026
Sorted by the source-provided rank. Higher score is better according to the registry.
| 1 | AC | 59.8% | 100.0% | 1 | C |
The top published results on this benchmark's own scale.
Definition and scoring fields from the benchmark registry.
A subset of the MMAU benchmark focused specifically on speech understanding and reasoning tasks. Part of a comprehensive multimodal audio understanding benchmark that evaluates models on expert-level knowledge and complex reasoning across speech audio clips.
Scores are shown in ratio. The current registry marks this benchmark as not independently verified with evidence level B.
Source-native results are preserved. Eligibility for the overall LLMBoard score is a separate policy decision.
Common questions about MMAU Speech.
Qwen2.5-Omni-7B is currently ranked first with 59.8%.
A subset of the MMAU benchmark focused specifically on speech understanding and reasoning tasks. Part of a comprehensive multimodal audio understanding benchmark that evaluates models on expert-level knowledge and complex reasoning across speech audio clips.
Yes. Higher values rank better for this benchmark.
1 unique published model results are currently shown.
This benchmark is preserved as source-native evidence but is not eligible for the current overall score.