← 研踪 PaperTrailarXiv:2608.28212 · v3
MuSP-Bench: Advanced Multimodal Benchmarking of Music Understanding across Score and Performance
首次提交 2026-08-28 19:31
版本更新 2026-11-07 20:55
雷达观测 2026-11-10 11:14
摘要
Musicians commonly communicate musical intent through scores and performances. To investigate whether models can reason across both modalities, we introduce MuSP-Bench, a human-authored benchmark of 490 questions assessing understanding across Musical Scores and Performances, both individually and in combination. The benchmark spans interpretive and long-horizon reasoning across classical piano and orchestral works, represented through ABC notation, score images, MIDI, and audio. Our evaluation of frontier multimodal large language models reveals substantial difficulties in understanding musical scores and even greater challenges in reasoning about audio.
作者备注：Accepted to ISMIR 2026 Late-Breaking Demo. Benchmark site: https://musp.vaclis.net/
观测到的版本
相邻记录可能跳过中间版本；首次发现 v2 及以上也会标为版本更新。
v3 · 2026-11-07 20:55 · 最新观测版本
MuSP-Bench: Advanced Multimodal Benchmarking of Music Understanding across Score and Performance
Musicians commonly communicate musical intent through scores and performances. To investigate whether models can reason across both modalities, we introduce MuSP-Bench, a human-authored benchmark of 490 questions assessing understanding across Musical Scores and Performances, both individually and in combination. The benchmark spans interpretive and long-horizon reasoning across classical piano and orchestral works, represented through ABC notation, score images, MIDI, and audio. Our evaluation of frontier multimodal large language models reveals substantial difficulties in understanding musical scores and even greater challenges in reasoning about audio.
查看此版本解读 →查看此版本原文 ↗