Benchmark
MMAU-mini
An audio understanding and reasoning benchmark that evaluates a model's ability to select the correct answer from multiple options. It is a representative audio understanding task, testing comprehension and reasoning over audio content rather than generation.
Timeline (last 90 days)
Oct 16
Qwen-Audio-Jev achieves a CHOICE accuracy of 78.70% on MMAU-mini.
Unverified50%