---
title: "Music · instrumental: model rankings and source evidence · Undominated.ai"
canonical: https://undominated.ai/rankings/music-instrumental/
description: "Music · instrumental ranked by Music Arena score. Inspect exact model variants, source dates, measurement limits and downloadable evidence."
---

# Music · instrumental: model rankings and source evidence · Undominated.ai

> Music · instrumental ranked by Music Arena score. Inspect exact model variants, source dates, measurement limits and downloadable evidence.

[All rankings](/rankings/) / Music

# Music · instrumental

Blind listener preferences published by Carnegie Mellon University’s Music Arena. Vocal and instrumental results are separate populations.

**15 entries** · Music Arena score · Higher is better

Source publication: 2026-07-31. Retrieved 2026-11-05.

Source: [Carnegie Mellon University · Music Arena](https://github.com/gclef-cmu/music-arena) · [MIT](https://github.com/gclef-cmu/music-arena/blob/8b330f4bd6cb4969ff7e32ffeec266a8a4ca8b0e/LICENSE).

Ranks use confidence bounds. Several models can share a rank; the rows within a shared rank are displayed by score.

Music · instrumental · Music Arena score

| Significance rank | Model / evaluated variant | Music Arena score | 95% confidence interval | Votes |
| --- | --- | --- | --- | --- |
| 1 | Lyria 3 Pro Google DeepMind | 1,394 | 1,336 – 1,452 | 241 |
| 1 | Stable Audio 3 (Medium) Stability AI | 1,333 | 1,295 – 1,371 | 444 |
| 3 | Riffusion FUZZ v1.0 Producer.ai | 1,225 | 1,159 – 1,291 | 220 |
| 3 | Sonauto v2.2 Sonauto | 1,150 | 1,109 – 1,191 | 469 |
| 3 | Riffusion FUZZ v1.1 Producer.ai | 1,119 | 1,076 – 1,162 | 452 |
| 5 | ElevenLabs Music v1 ElevenLabs | 1,055 | 1,015 – 1,095 | 330 |
| 5 | Lyria 3 Clip Google DeepMind | 1,003 | 929 – 1,077 | 85 |
| 6 | Sonauto v3 Preview Sonauto | 950 | 855 – 1,045 | 41 |
| 7 | Magenta RealTime (Large) Google DeepMind | 911 | 885 – 937 | 829 |
| 7 | ACE-Step 1.5 Turbo (1.7B) ACE Studio / StepFun | 894 | 839 – 949 | 176 |
| 9 | Stable Audio Open Stability AI | 842 | 812 – 872 | 694 |
| 9 | MusicGen Medium Meta | 838 | 807 – 869 | 569 |
| 9 | Magenta RealTime 2 (Base) Google DeepMind | 809 | 740 – 878 | 200 |
| 11 | MusicGen Small Meta | 794 | 759 – 829 | 463 |
| 15 | Stable Audio Open Small Stability AI | 682 | 638 – 726 | 435 |

## What this ranking can tell you

 - The date is the end of the source’s evaluation window, not the date this page was fetched.
- These results cover the source’s tested model versions. They do not establish the quality of later releases.
- Confidence bounds are reconstructed from the source’s rounded score and ± interval. Small differences should not be interpreted as decisive.
- No audio is redistributed. A benchmark result does not grant rights to a model or its generated music.

## Check the source

The original evidence is retained byte for byte. The downloadable board includes the source URLs, revision and SHA-256 hashes.

[Download this board and provenance →](/data/rankings/music-instrumental.json)

 Source files and licences - [metadata · 1eb799639740](/data/rankings/evidence/1eb7996397401da56076ad1af441defb71e36fbd8ca6f81f94b44a3da529f2d0.json) · [upstream source ↗](https://api.github.com/repos/gclef-cmu/music-arena/git/trees/main?recursive=1)
- [licence · 90d047765c7f](/data/rankings/evidence/90d047765c7fa5d9b33340634e86ae0b6e96821e17ef93f6c8e3acf1ff576f13.txt) · [upstream source ↗](https://raw.githubusercontent.com/gclef-cmu/music-arena/8b330f4bd6cb4969ff7e32ffeec266a8a4ca8b0e/LICENSE)
- [rows · 2deb18bd7bd6](/data/rankings/evidence/2deb18bd7bd6123e799a3370b8f9d1e847d7648595a5911c357f7a96bae52b73.tsv) · [upstream source ↗](https://raw.githubusercontent.com/gclef-cmu/music-arena/8b330f4bd6cb4969ff7e32ffeec266a8a4ca8b0e/components/frontend/ma_frontend/leaderboard/20260731/instrumental_leaderboard_20250728_to_20260731.tsv)

[Explore other model types →](/rankings/)[Read the benchmark guide →](/benchmarks/)

## Continue your investigation

 - [Understand the measurements](/benchmarks/)
- [Compare task performance](/best/)
- [Compare embedding models](/embeddings/)
- [Inspect ranking rules](/methodology/)