LilyBench
Explore score history ↗LilyBench evaluates symbolic music generation and understanding using LilyPond, with a 200-prompt generation suite and ten understanding tasks, scored via compile rate, descriptor similarity, and FMD.
- Released
- 2026-06-07
- Institutions
- University of Padua · Universitat Pompeu Fabra
- Evaluates
- General AI, Language & Knowledge, cs.SD
- Openness
- unknown
- Importer
- Claire Radar
- Review status
- unreviewed
LilyBench paper and code
No reported scores are on record for this benchmark yet.