Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Audio-Visual Question Answering on AVQA
Loading...
92
Accuracy
CAT-7B
42.6
55.425
68.25
81.075
Mar 7, 2024
Jul 1, 2024
Oct 26, 2024
Feb 20, 2025
Jun 16, 2025
Oct 11, 2025
Feb 5, 2026
Accuracy
Updated 4d ago
Evaluation Results
Method
Method
Links
Accuracy
CAT-7B
Evaluation Protocol=fi...
2024.03
92
PSTP-Net
Evaluation Protocol=fi...
2024.03
90.2
EgoAVU (LoRA)
Fine-tuning Strategy=LoRA
2026.02
89.7
EgoAVU (Full)
Fine-tuning Strategy=Full
2026.02
89.5
Qwen2.5-Omni
2026.02
89.4
HCRN + HAVF
Evaluation Protocol=fi...
2024.03
89
HGA + HAVF
Evaluation Protocol=fi...
2024.03
87.7
Crab
2025.03
78.94
VALOR
2025.03
78.9
VideoLLaMA2 w/ FastAV
FLOPs=56, Latency=0.32...
2026.01
62.3
VideoLLaMA2
FLOPs=100, Latency=0.4...
2026.01
61.4
video-SALMONN2 w/ FastAV
FLOPs=58, Latency=0.29...
2026.01
58.4
video-SALMONN2
FLOPs=100, Latency=0.4...
2026.01
57.6
X-InstructBLIP
zero-shot=true
2025.03
44.5
Feedback
Search any
task
Search any
task