Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Audio-to-Text Generation on Image-Text-Audio
Loading...
54.41
CIDEr
FlowBind
5.8316
18.4433
31.055
43.6667
Jun 15, 2026
CIDEr
Updated 1mo ago
Evaluation Results
Method
Method
Links
CIDEr
FlowBind
Category=Generalists
2026.06
54.41
MoPoE
Category=Multimodal VA...
2026.06
50.34
MMVAE
Category=Multimodal VA...
2026.06
47.43
MUNI†
Category=Generalists
2026.06
47.38
MUNI
Category=Generalists
2026.06
43.72
OmniFlow
Category=Generalists
2026.06
31.42
Qwen2-Audio
Category=Specialists
2026.06
21.39
UnifiedIO2-L
Category=Generalists
2026.06
15.18
CoDi
Category=Generalists
2026.06
7.7
Feedback
Search any
task
Search any
task