Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Long Video Understanding on VideoMME Long split (30-60 min)
Loading...
65.3
Accuracy
GPT-4o
36.804
44.202
51.6
58.998
Dec 4, 2025
Accuracy
Updated 3d ago
Evaluation Results
Method
Method
Links
Accuracy
GPT-4o
Input Frames=>=64
2025.12
65.3
VideoMem*
Size=8B, Input Frames=64
2025.12
64.2
Qwen2.5-VL
Size=72B, Input Frames...
2025.12
61.2
Qwen3-VL*
Size=8B, Input Frames=64
2025.12
58.6
GPT-4V
Input Frames=>=64
2025.12
56.9
NVILA
Size=8B, Input Frames=...
2025.12
54.8
Flow4Agent
Size=7B, Input Frames=...
2025.12
54.2
VideoLLaMA3
Size=7B, Input Frames=...
2025.12
54.1
Qwen2.5-VL
Size=7B, Input Frames=...
2025.12
51.6
LLaVA-video
Size=7B, Input Frames=...
2025.12
50.6
LongVA
Size=7B, Input Frames=...
2025.12
47.6
LLaVA-Onevision
Size=7B, Input Frames=...
2025.12
46.7
VideoLLaMA2
Size=7B, Input Frames=...
2025.12
43.8
Video-LLaVA
Size=7B, Input Frames=...
2025.12
38.1
ShareGPT4Video
Size=8B, Input Frames=...
2025.12
37.9
Feedback
Search any
task
Search any
task