Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Video Question Answering on Video-MME w.o. sub. Overall
Loading...
71.1
Accuracy
Qwen2-VL + ReQuest
38.236
46.768
55.3
63.832
Jul 2, 2026
Accuracy
Updated 22d ago
Evaluation Results
Method
Method
Links
Accuracy
Qwen2-VL + ReQuest
LLM Size=8B, #Frames=≤...
2026.07
71.1
Qwen2-VL
LLM Size=8B, #Frames=5...
2026.07
70
LLaVA-Video + ReQuest
LLM Size=7B, #Frames=32
2026.07
65.6
NVILA
LLM Size=8B, #Frames=1024
2026.07
64
LLaVA-Video
LLM Size=7B, #Frames=3...
2026.07
62.6
LongVU
LLM Size=7B, #Frames=1fps
2026.07
60.9
LLaVa-OneVision + ReQuest
LLM Size=7B, #Frames=3...
2026.07
60.9
VideoTree
LLM Size=–, #Frames=–
2026.07
60.6
LLaVa-OneVision
LLM Size=7B, #Frames=3...
2026.07
58.7
Frame-Voyager
LLM Size=7B, #Frames=8
2026.07
57.5
LLoVi
LLM Size=–, #Frames=–
2026.07
54.7
VideoLLaMA2
LLM Size=7B, #Frames=16
2026.07
47.9
TimeSuite
LLM Size=7B, #Frames=128
2026.07
46.3
Chat-UniVi-V1.5
LLM Size=7B, #Frames=64
2026.07
40.6
Video-LLaVA
LLM Size=7B, #Frames=8
2026.07
39.9
ShareGPT4Video
LLM Size=8B, #Frames=16
2026.07
39.9
VideoChat2
LLM Size=7B, #Frames=16
2026.07
39.5
Feedback
Search any
task
Search any
task