List your company

Long Video Understanding on LongVideoBench (LVB) (val)

66.7AccuracyGPT-4o
52.24455.99759.7563.503Jun 26, 2026

Evaluation results

MethodLinks
GPT-4o# Frame=384, Paradigm=Standard (w/o Tools), Adaptive keyframe retrieval=false2026.0666.7
Gemini-1.5-Pro# Frame=1 fps, Paradigm=Standard (w/o Tools), Adaptive keyframe retrieval=false2026.0664
Reflect-R1# Frame=768, Paradigm=Tool-Augmented Reasoning, Adaptive keyframe retrieval=false2026.0662.5
TimeSearch-R-7B# Frame=768, Paradigm=Tool-Augmented Reasoning, Adaptive keyframe retrieval=false2026.0661.2
Video-R1-7B# Frame=768, Paradigm=Standard (w/o Tools), Adaptive keyframe retrieval=false2026.0660.1
VL-Rethinker# Frame=768, Paradigm=Standard (w/o Tools), Adaptive keyframe retrieval=false2026.0655.58
Qwen2.5-VL-7B-Instruct# Frame=768, Paradigm=Standard (w/o Tools), Adaptive keyframe retrieval=false2026.0653.9
Vision-R1-7B# Frame=768, Paradigm=Standard (w/o Tools), Adaptive keyframe retrieval=false2026.0652.8