Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Audio Captioning on Clotho (eval)
Loading...
31.88
SPIDEr
Audio Flamingo 3
4.2784
11.4442
18.61
25.7758
Feb 14, 2026
SPIDEr
FENSE
Updated 4d ago
Evaluation Results
Method
Method
Links
SPIDEr
FENSE
Audio Flamingo 3
2026.02
31.88
52.11
WavCaps CNN14
2026.02
31
-
WavCaps HTSAT
2026.02
29.7
-
Whisper-Cards
Training data=Pixtral...
2026.02
22.18
48.48
Whisper-Cards
Training data=Pixtral...
2026.02
22.07
48.67
Whisper-Baseline
Training data=Pixtral...
2026.02
21.05
47.61
Audio Flamingo 3
Mode=think
2026.02
13.22
50.19
Audio Flamingo 2
2026.02
7.25
33.71
GAMA
2026.02
5.34
43.21
Feedback
Search any
task
Search any
task