Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Audio-Video Understanding on AVSD (test)
Loading...
62.8
Accuracy
Qwen2.5-Omni
14.648
27.149
39.65
52.151
Dec 28, 2025
Accuracy
Updated 4d ago
Evaluation Results
Method
Method
Links
Accuracy
Qwen2.5-Omni
Model Size=7-8B, Zero-...
2025.12
62.8
JavisGPT
Model Size=7-8B, #Samp...
2025.12
62.2
VideoLLaMA2
Model Size=7-8B, #Samp...
2025.12
57.2
VideoLLaMA2.1
Model Size=7-8B, #Samp...
2025.12
57.2
AV-LLM
Model Size=7-8B, Zero-...
2025.12
52.6
VideoLLaMA
Model Size=7-8B, Zero-...
2025.12
36.7
Macaw-LLM
Model Size=7-8B, Zero-...
2025.12
34.3
NExT-GPT
Model Size=7-8B, #Samp...
2025.12
30.8
UnifiedIO-2
Model Size=7-8B, #Samp...
2025.12
16.5
Feedback
Search any
task
Search any
task