Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Audio-Visual Question Answering on VALOR (test) using Model-as-Judge
Loading...
44.67
M.J. Score
M3KG-RAG
24.8996
30.0323
35.165
40.2977
Dec 23, 2025
M.J. Score
Updated 4d ago
Evaluation Results
Method
Method
Links
M.J. Score
M3KG-RAG
MLLM=Qwen2.5-Omni
2025.12
44.67
VAT-KG
MLLM=Qwen2.5-Omni
2025.12
35.44
VTKG
MLLM=Qwen2.5-Omni
2025.12
32.7
None
MLLM=Qwen2.5-Omni
2025.12
32.42
M2ConceptBase
MLLM=Qwen2.5-Omni
2025.12
32.31
Wikidata
MLLM=Qwen2.5-Omni
2025.12
30.28
M3KG-RAG
MLLM=VideoLLaMA2
2025.12
29.25
VAT-KG
MLLM=VideoLLaMA2
2025.12
28.3
Wikidata
MLLM=VideoLLaMA2
2025.12
26.43
M2ConceptBase
MLLM=VideoLLaMA2
2025.12
25.93
VTKG
MLLM=VideoLLaMA2
2025.12
25.92
None
MLLM=VideoLLaMA2
2025.12
25.66
Feedback
Search any
task
Search any
task