Audio Visual Question Answering on AVQA (test)

94.3Total Accuracy

UniMVU

Updated 7d ago

Evaluation Results

Method	Links
UniMVU 2026.05		94.3
JavisGPT 2025.12		93.8
PAVE* 2026.05		93.4
UniMVU 2026.05		92.3
UniMVU† 2026.05		92.2
CAT-FT 2026.05		92
Qwen2.5-Omni 2025.12		91.5
AV-Master 2025.10		91.4
AV-Master 2026.05		91.4
QSTar 2026.01		91.2
UniMVU† 2026.05		91.1
QSTar 2026.01		90.9
TSPM 2026.01		90.8
TSPM 2025.10		90.8
MCD 2025.10		90.8
LLaVA-OV-FT (video-only) 2026.05		90.8
PSTP 2026.01		90.2
PSTP-Net 2025.10		90.2
PSTP-Net 2026.05		90.2
SaSR-Net 2025.10		89.9
LLaVA-OV-FT* (video-audio concat) 2026.05		89.9
PAVE* 2026.05		89.6
HCRN 2026.01		89
HCRN 2025.10		89
ACRTransformer 2025.10		87.8
HGA 2025.10		87.7
PSAC 2026.01		87.4
PSAC 2025.10		87.4
LLaVA-OV-FT (video-only) 2026.05		86.4
HME 2025.10		85
LADNet 2025.10		84.1
VideoLLaMA 2025.12		80.9
Macaw-LLM 2025.12		78.7
AV-LLM 2025.12		78.7
UnifiedIO-2 2025.12		61.2
NExT-GPT 2025.12		25.3