Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Text-to-Audio Generation on Grand Challenge (test)
Loading...
75.7
FAD
FluxAudio-S (Organizer’s Baseline)
53.964
59.607
65.25
70.893
Jul 2, 2026
FAD
CLAP
CSS
Updated 22d ago
Evaluation Results
Method
Method
Links
FAD
CLAP
CSS
FluxAudio-S (Organizer’s Baseline)
params=120M, Train Dat...
2026.07
75.7
8.8
59.2
MeanAudio-L-Full
params=480M, Train Dat...
2026.07
66
20.2
78.3
MeanAudio-S-Full
params=120M, Train Dat...
2026.07
64.9
21
80.8
proposed (Text-500)
params=480M, Train Dat...
2026.07
64.6
26
76.7
Stable Audio Open
params=1.1B, Train Dat...
2026.07
57.4
32.1
80
MusicGen-small
params=300M, Train Dat...
2026.07
57.4
37
87.5
MusicGen-large
params=3.3B, Train Dat...
2026.07
55.3
37.9
88.8
MusicGen-medium
params=1.5B, Train Dat...
2026.07
54.8
35.3
89.2
Feedback
Search any
task
Search any
task