Share your thoughts, 1 month free Claude Pro on usSee more

Audio-Visual Question Answering on Music-AVQA

81.3Accuracy

VideoLLaMA2

Updated 18d ago

Evaluation Results

Method	Links
VideoLLaMA2 2026.01		81.3
VideoLLaMA2 w/ FastAV 2026.01		81.2
VALORL 2023.04		78.9
Q-TriM 2026.07		77.68
VALORB 2023.04		76.6
MAVEN 2026.07		76.21
VALORL 2023.04		74.8
MUSIC-AVQA 2023.04		71.5
VideoLLaMA2 2026.07		66.85
Qwen2.5-VL 2026.07		57.07
GPT-4o 2026.07		56.06
TSV Merging 2025.05		53.78
MMER 2025.05		53.54
NaiveMC 2025.05		53.5
OptMerge 2025.05		53.17
DAMC 2025.05		52.8
Iso-C 2025.05		52.77
WUDI Merging 2025.05		52.43
Task Arithmetic 2025.05		52.14
Vision 2025.05		50.77
Ties Merging 2025.05		50.35
AVicuna 2024.11		49.6
LongVALE-LLM 2024.11		49.4
Video 2025.05		49.02
CAT-7B 2024.03		48.6
Weight Average 2025.05		47.75
Video MLLM 2025.05		47.72
ChatBridge-13B 2024.03		47.6
OneLLM 2024.11		47.6
AV-LLM 2024.11		45.2
X-InstructBLIP 2024.11		44.5
Vision MLLM 2025.05		44.06
OneLLM-7B 2024.03		43
VideoLLaMA 2024.11		36.6
PandaGPT 2024.11		33.7
Macaw-LLM 2024.11		31.8
Audio MLLM 2025.05		30.63
Audio 2025.05		27.93