Benchmark RadarAI BENCHMARK PROFILE
MADB
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
- Readiness
- Runnable
- Primary field
- General AI
Why it matters
Provides structured aesthetic annotations for a previously underexplored area, enabling measurement of model-human gaps in music understanding.
Motivation
Music aesthetic assessment is a challenging yet underexplored problem, requiring models to capture fine-grained, multi-dimensional human perceptual judgments.
Primary resources
Benchmark Radar records only publicly supported details and links back to primary sources for verification.