MMSU: Spoken Language Reasoning Benchmark with 47 Linguistic Sub-Tasks

MMSU is a multimodal benchmark for spoken language understanding and reasoning featuring 47 sub-tasks across linguistic domains like phonetics and prosody. Created by ddwang2000 and documented in Arxiv 2506.04779, the collection contains between 1,000 and 10,000 records.

Use Cases

• Evaluating phonetic recognition within the 47 sub-tasks
• Testing prosodic reasoning using audio features
• Benchmarking question answering on rhetorical speech patterns

Strengths

• 47 distinct sub-tasks for granular evaluation
• Multimodal audio-text pairs
• MIT licensed

Limitations

• Small sample size of 1,000 to 10,000 records
• Restricted to English language

Provenance

Source

ddwang2000 (Arxiv 2506.04779)

Freshness

Last updated February 2026.

Geography

United States