Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Egocentric Video Understanding on EgoSchema Subset 2023
Loading...
72.2
Accuracy
GPT-4o
35.384
44.942
54.5
64.058
Aug 28, 2025
Accuracy
Updated 2d ago
Evaluation Results
Method
Method
Links
Accuracy
GPT-4o
Size=-, Frames=0.5 fps...
2025.08
72.2
Gemini-1.5-Pro
Size=-, Frames=0.5 fps
2025.08
71.1
Video-MTR
Size=7B, Frames=80
2025.08
68.8
DrVideo(GPT-4)
Size=-, Frames=0.2/0.5...
2025.08
66.4
Qwen2.5-VL-7B
Size=7B, Frames=768
2025.08
65
Qwen2.5-VL-7B
Size=7B, Frames=80
2025.08
63.5
Video-MTR
Size=7B, Frames=64
2025.08
63.4
VideoMemAgent
Size=-, Frames=72
2025.08
62.8
Qwen2.5-VL-7B
Size=7B, Frames=64
2025.08
62.6
Video-MTR
Size=7B, Frames=32
2025.08
62.4
VideoAgent
Size=-, Frames=87
2025.08
60.2
LLaVA-OneVision
Size=7B, Frames=32
2025.08
60.1
Qwen2.5-VL-7B
Size=7B, Frames=32
2025.08
59.4
VideoLLaMA2
Size=8×7B, Frames=8
2025.08
53.3
Video-R1
Size=7B, Frames=64
2025.08
51.8
Video-R1
Size=7B, Frames=32
2025.08
48.8
Video-LLaVA
Size=7B, Frames=8
2025.08
36.8
Feedback
Search any
task
Search any
task