Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Automated Audio Captioning on MACS
Loading...
64.9
AAC Score
Kimi-Audio
1.512
17.9685
34.425
50.8815
Sep 24, 2025
AAC Score
Updated 24d ago
Evaluation Results
Method
Method
Links
AAC Score
Kimi-Audio
Size=7B
2025.09
64.9
SLAM-Omni
Size=0.5B
2025.09
50.46
TtT
Size=3B
2025.09
48.87
Qwen2.5-3B (AR)
Size=3B
2025.09
48.64
Pretrain+TtT
Size=3B
2025.09
42.86
Qwen2.5-3B (NAR)
Size=3B
2025.09
27.4
GLM-4-Voice
Size=9B
2025.09
12.67
Moshi
Size=7B
2025.09
12.01
VITA-Audio
Size=7B
2025.09
7.94
LLaMA-Omni
Size=8B
2025.09
4.56
Mini-Omni
Size=0.5B
2025.09
4.45
SpeechGPT
Size=7B
2025.09
3.95
Feedback
Search any
task
Search any
task