Who leads the MusicCaps benchmark?

MusicLM currently leads MusicCaps with a score of 4.00 on fad.

What is the state-of-the-art score on MusicCaps?

The state-of-the-art result on MusicCaps is 4.00 (fad), achieved by MusicLM as of 2026.

How many models are tracked on MusicCaps?

Codesota tracks 3 models on MusicCaps.

When was the MusicCaps leaderboard last updated?

The MusicCaps leaderboard on Codesota includes results through 2026.

Codesota · Audio · Music Generation · MusicCapsTasks/Audio/Music Generation

Music Generation · benchmark dataset · 2023 · EN

MusicCaps.

Name: MusicCaps Benchmark Results
Creator: Codesota
Published: 2026-01-01
License: https://creativecommons.org/licenses/by/4.0/

Music generation evaluated on 5.5K expert-annotated music clips

Submit a result ↵

§ 01 · Leaderboard

Best published scores.

3 results indexed across 1 metric. Shaded row marks current SOTA; ties broken by submission date.

Primary: fad · higher is better

fad· primary

3 rows

#	Model	Org	Submitted	Paper / code	fad
01	MusicLM	Google	Apr 2026	editorial	4.00
02	MusicGen LargeOSS	Meta AI	Apr 2026	editorial	3.80
03	Noise2Music	Google	Apr 2026	editorial	2.13

Fig 2 · Rows sorted by score within each metric. Shaded row marks SOTA. Dates reflect model or paper release where available, otherwise the date Codesota accessed the source.

§ 03 · Progress

1 steps
of state of the art.

Each row below marks a model that broke the previous record on fad. Intermediate submissions are kept in the leaderboard above; only SOTA-setting entries are re-listed here.

Higher scores win. Each subsequent entry improved upon the previous best.

SOTA line · fad

Apr 5, 2026MusicLMGoogle4.00

Fig 3 · SOTA-setting models only. 1 entries span Apr 2026 → Apr 2026.

§ 06 · Contribute

Have a score that beats
this table?

Submit a checkpoint and a reproduction script. We will run it, publish the score, and — if it takes the top — annotate the step on the progress chart with your name.

Submit a result ↵Read submission guide

What a submission needs

01A public checkpoint or API endpoint
02A reproduction script with frozen commit + seed
03Declared evaluation environment (Python, deps)
04One row per metric declared by this dataset
05A contact so we can follow up on discrepancies

MusicCaps.

Best published scores.

1 stepsof state of the art.

Have a score that beatsthis table?

1 steps
of state of the art.

Have a score that beats
this table?