PianoBench: Evaluating Musical Perception and Reasoning in Language Models
Multimodal language models continue to improve on broad music understanding benchmarks, but which musical features can they perceive and reason about? We investigate this question by introducing PianoBench, a benchmark that tasks language models with reasoning about musical performances across congruent acoustic and sy...
Louis Bradshaw, Irmak Bukey, Dan Lin et al.
· 0 citations