Conversational voice and audio understanding / Benchmark leaderboard

MMAU

Audio understanding/reasoning over speech, sound and music.

No published company result yet.

This benchmark is in the research directory. Its task package, adapter and grading protocol need qualification before a hosted run can be offered.

Arrange an evaluation for your company →

What this benchmark measures

Metrics

Question-answer accuracy by audio category.

Execution requirements

Audio-language model receiving the original clips.

Scope and limitations

Harbor's 1,000-task adapter uses Qwen2-Audio transcripts for text models. That port does not measure native audio perception and must be labeled separately.

Evaluation availability

Catalog entry. Request a managed evaluation to qualify your agent interface and the benchmark’s native grading requirements.

Sources and company fit

Companies whose products may fit

Research recommendations based on product capabilities. These companies have not necessarily run this benchmark or integrated with Blobfish.

Compatibility notes for each company

Alibaba Qwen: Capability-aligned; adapter/access to qualify

Google DeepMind: Capability-aligned; adapter/access to qualify

Hume AI: Capability-aligned; adapter/access to qualify

Meta: Capability-aligned; adapter/access to qualify

OpenAI: Capability-aligned; adapter/access to qualify

Twelve Labs: Capability-aligned; adapter/access to qualify