MuSP-Bench: Advanced Multimodal Benchmarking of Music Understanding across Score and Performance

2026-08-28

AI Summary

为探究模型能否理解乐谱和演奏，本文引入MuSP-Bench基准，包含490个问题，评估多模态大语言模型在不同条件下的表现。

Abstract

Musicians commonly communicate music through scores and performances. Scores encode musical intent, while performances realize it in sound. To investigate whether models can meaningfully engage with both modalities, we introduce MuSP-Bench, a human-authored benchmark of 490 questions targeting understanding across Musical Scores and Performances. The benchmark distinguishes itself by spanning score-based, performance-based, interpretive, and long-horizon reasoning across classical piano and orchestral works. We evaluate frontier multimodal large language models under multiple input conditions. Our results show that these models struggle substantially to understand scores, while facing even greater challenges when reasoning about performance audio. The benchmark is available at https://musp.vaclis.net/.

Problem

• musical scores
• performances
• multimodal understanding
• reasoning

Innovation

• Multimodal Benchmarking
• Music Understanding
• Musical Scores and Performances
• Interpretive Reasoning