Benchmark Radar™
Star —

MADB Benchmark

Explore score history ↗

MADB is a large-scale dataset and benchmark for music aesthetic assessment, comprising 9,999 tracks annotated by 30 trained annotators across 10 perceptual dimensions and an overall score, with textual comments. It includes a unified evaluation framework over multiple pretrained models.

Released
2026-07-08
Institutions
Central Conservatory of Music · Beijing Institute for General Artificial Intelligence · Tianjin Conservatory of Music
Evaluates
General AI, Language & Knowledge, cs.SD
Openness
unknown
Importer
Claire Radar
Review status
unreviewed

MADB paper and code

No reported scores are on record for this benchmark yet.

Which sources cite MADB?

Related General AI, Language & Knowledge, cs.SD benchmarks