MMAU Speech
multimodal
+
+
+
+
About
MMAU-Speech is a specialized subset of the MMAU benchmark focusing on speech understanding and reasoning tasks. It evaluates models' ability to comprehend spoken language, analyze speech characteristics, understand prosodic features, and perform complex reasoning about speech content, testing both linguistic comprehension and acoustic analysis capabilities in speech processing contexts.
+
+
+
+
Evaluation Stats
Total Models1
Organizations1
Verified Results0
Self-Reported1
+
+
+
+
Benchmark Details
Max Score1
Language
en
+
+
+
+
Performance Overview
Score distribution and top performers
Score Distribution
1 models
Top Score
59.8%
Average Score
59.8%
High Performers (80%+)
0Top Organizations
#1Alibaba Cloud / Qwen Team
1 model
59.8%
+
+
+
+
Leaderboard
1 models ranked by performance on MMAU Speech
| License | Links | ||||
|---|---|---|---|---|---|
| Mar 27, 2025 | Apache 2.0 | 59.8% |
