MusGU+: Musician-Centered Evaluation Framework

The Music-Generative Usable+ AI (MusGU+) framework is a musician-centered evaluation framework designed to assess how generative music models can be adapted, used, and controlled in real-world creative contexts. The framework evaluates models along three complementary dimensions, with each dimension addressing a key question from the musician's perspective:

• Adaptability — Can I realistically adapt this model to my own data?
• Usability — Can I access, run, and integrate this model into my music-making workflow?
• Controllability — Can I guide the model in musically meaningful and interpretable ways?

This website accompanies the paper MusGU+: Toward a Musician-Centered Evaluation Framework and Discovery Tool for Generative Music AI, authored by Laura Ibáñez-Martínez, Roser Batlle-Roca, Xavier Serra, and Martín Rocamora, and accepted for presentation at the 7th Conference on AI Music Creativity (AIMC 2026). It is a living resource that continues to expand through community contributions.

📖 Read the detailed evaluation criteria

How to navigate this table?

The MusGU+ framework evaluates models across 15 criteria distributed among three dimensions: Adaptability (5 criteria), Usability (6 criteria), and Controllability (4 criteria). Each criterion is evaluated on a three-level scale: ✔︎ fully supported, ~ partially supported, or ✘ not supported.

The table includes interactive elements:

• Model and criterion links: Click a model name to open its detail page; click an evaluation score to jump to its status, notes, and tags.
• Tag filters: Under Musical Applications and within criterion headers, filter the table to models with those features.
• Hover tooltips: Evaluation cells reveal the comment or justification behind each score.
• Dimension headers: Reorder the table by that dimension; the accompanying ≥60% button filters models meeting that threshold.

For the underlying evaluation files, explore the corresponding YAML entries in the projects folder.

Contributing

If you would like to help expand or refine MusGU+, there are two main ways to contribute:

• Suggest a new model. The simplest option is to open an issue using the Suggest a New Model template. A brief explanation and any relevant links are enough; maintainers will take care of the detailed evaluation. More experienced contributors can instead create a new branch, add a YAML evaluation following the YAML template, and submit a pull request.
• Propose changes to an existing evaluation. If you think a current model entry should be updated, corrected, or expanded, you can open an issue or submit a pull request with supporting evidence.

Citation

The paper MusGU+: Toward a Musician-Centered Evaluation Framework and Discovery Tool for Generative Music AI was accepted at the 7th Conference on AI Music Creativity (AIMC 2026). If our work is relevant to you, please cite it as follows:

@InProceedings{ibanezmartinez2026musgu,
  author    = {Ibáñez-Martínez, Laura and Batlle-Roca, Roser and Serra, Xavier and Rocamora, Martín},
  title     = {MusGU+: Toward a Musician-Centered Evaluation Framework and Discovery Tool for Generative Music AI},
  booktitle = {Proceedings of the 7th Conference on AI Music Creativity (AIMC 2026)},
  year      = {2026},
  month     = sep,
  publisher = {AIMC},
  doi       = {10.5281/zenodo.22281934},
  url       = {https://doi.org/10.5281/zenodo.22281934}
}

Relationship to MusGO

MusGU+ builds on the MusGO framework (Music-Generative Open AI), adopting its composite and graded evaluation approach while shifting the emphasis from openness toward practical suitability for musicians. While MusGO focuses on openness and responsible research practices, MusGU+ focuses on whether generative music systems can be adapted, used, and controlled in real-world creative contexts. The two frameworks provide complementary perspectives on generative music AI.

Discovery tool last updated on 2026-09-14 at 21:32 UTC.