MusICA-MetaBench (ChoraleBricks): leaderboard
MusICA-MetaBench (2026) generates five-option music-perception questions from MusicXML scores and poses them over audio recordings, sheet-music images and ABC notation; this board is one 300-question instance built from the ChoraleBricks chorales. Accuracy in percent, higher is better; random choice scores 20.
Metric: Accuracy (%; 300 five-option music-perception questions generated from ChoraleBricks MusicXML, 100 each from audio recordings, sheet-music images and ABC notation, one benchmark instance; none-of-the-above is correct 20% of the time; random choice 20%). Source: arxiv.org. Saturation forecast: Around February 2027. 5 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 59 | #94 |
| 2 | Gemini 3.1 Flash Lite (Preview) | 45.7 | #418 |
| 3 | Gemini 2.5 Flash Lite | 41 | #958 |
| 4 | Gemini 2.0 Flash Lite | 40.3 | #1032 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=musica-metabench-choralebricks · How It Works · Data refreshed daily, snapshot 2026-11-13.