List your company

Egocentric Video Understanding on EgoSchema Subset 2023

72.2AccuracyGPT-4o
35.38444.94254.564.058Aug 28, 2025

Evaluation results

MethodLinks
GPT-4oSize=-, Frames=0.5 fps / 3842025.0872.2
Gemini-1.5-ProSize=-, Frames=0.5 fps2025.0871.1
Video-MTRSize=7B, Frames=802025.0868.8
DrVideo(GPT-4)Size=-, Frames=0.2/0.5 fps2025.0866.4
Qwen2.5-VL-7BSize=7B, Frames=7682025.0865
Qwen2.5-VL-7BSize=7B, Frames=802025.0863.5
Video-MTRSize=7B, Frames=642025.0863.4
VideoMemAgentSize=-, Frames=722025.0862.8
Qwen2.5-VL-7BSize=7B, Frames=642025.0862.6
Video-MTRSize=7B, Frames=322025.0862.4
VideoAgentSize=-, Frames=872025.0860.2
LLaVA-OneVisionSize=7B, Frames=322025.0860.1
Qwen2.5-VL-7BSize=7B, Frames=322025.0859.4
VideoLLaMA2Size=8×7B, Frames=82025.0853.3
Video-R1Size=7B, Frames=642025.0851.8
Video-R1Size=7B, Frames=322025.0848.8
Video-LLaVASize=7B, Frames=82025.0836.8