Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Video Question Answering on Video-MME w.o. sub. Short
Loading...
80
Accuracy
Qwen2-VL + ReQuest
43.912
53.281
62.65
72.019
Jul 2, 2026
Accuracy
Updated 22d ago
Evaluation Results
Method
Method
Links
Accuracy
Qwen2-VL + ReQuest
LLM Size=8B, #Frames=≤...
2026.07
80
Qwen2-VL
LLM Size=8B, #Frames=5...
2026.07
78.6
LLaVA-Video + ReQuest
LLM Size=7B, #Frames=32
2026.07
77
LLaVA-Video
LLM Size=7B, #Frames=3...
2026.07
76.2
NVILA
LLM Size=8B, #Frames=1024
2026.07
75
LLaVa-OneVision + ReQuest
LLM Size=7B, #Frames=3...
2026.07
71.7
LLaVa-OneVision
LLM Size=7B, #Frames=3...
2026.07
70.3
VideoTree
LLM Size=–, #Frames=–
2026.07
67.8
Frame-Voyager
LLM Size=7B, #Frames=8
2026.07
67.3
LongVU
LLM Size=7B, #Frames=1fps
2026.07
64.7
LLoVi
LLM Size=–, #Frames=–
2026.07
62.1
VideoLLaMA2
LLM Size=7B, #Frames=16
2026.07
56
VideoChat2
LLM Size=7B, #Frames=16
2026.07
48.3
ShareGPT4Video
LLM Size=8B, #Frames=16
2026.07
48.3
Chat-UniVi-V1.5
LLM Size=7B, #Frames=64
2026.07
45.7
Video-LLaVA
LLM Size=7B, #Frames=8
2026.07
45.3
Feedback
Search any
task
Search any
task