List your company
ResearchFormerly WizWand

Video Question Answering on VNBench

77.88AccuracyBIMBA-LLaVA
8.116826.228444.3462.4516Mar 12, 2025Apr 14, 2025May 17, 2025Jun 20, 2025Jul 23, 2025Aug 25, 2025Sep 28, 2025
Updated 6mo ago

Evaluation results

MethodLinks
BIMBA-LLaVALLM=Qwen2-7B, Frames=1282025.0377.88
LLaVA-VideoLLM=Qwen2-7B, Frames=642025.0370.77
Video Panels (LLaVA-OV 72B)#frames=32, Model Context Category=Medium-context VLMs2025.0962.6
Video-XLLLM=Qwen2-7B, Frames=20482025.0361.6
LongVULLM=Qwen2-7B, Frames=1fps2025.0360.6
LLaVA-OV 72B#frames=32, Model Context Category=Medium-context VLMs2025.0959.4
Video Panels (Qwen-2.5VL 7B)#frames=32, Model Context Category=Medium-context VLMs2025.0958.5
Video Panels (LLaVA-OV 7B)#frames=32, Model Context Category=Medium-context VLMs2025.0957.7
Qwen-2.5VL 7B#frames=32, Model Context Category=Medium-context VLMs2025.0955.6
LLaVA-OV 7B#frames=32, Model Context Category=Medium-context VLMs2025.0954.8
LLaVA-OneVisionLLM=Qwen2-7B, Frames=322025.0351.8
LongVALLM=Qwen2-7B, Frames=1282025.0341.5
Video Panels (LLaVA-OV 0.5B)#frames=32, Model Context Category=Medium-context VLMs2025.0941
PLLAVALLM=Vicuna-7B, Frames=162025.0340.2
LLaVA-OV 0.5B#frames=32, Model Context Category=Medium-context VLMs2025.0939.8
Video Panels (Video-LLaVA 7B)#frames=8, Model Context Category=Small-context VLMs2025.0932
Video Panels (VideoChat2-HD)#frames=16, Model Context Category=Small-context VLMs2025.0928.5
VideoChat2-HD#frames=16, Model Context Category=Small-context VLMs2025.0927.9
Video-LLaVA 7B#frames=8, Model Context Category=Small-context VLMs2025.0927.8
Video-LLaMA2LLM=Qwen2-7B, Frames=322025.0324.9
LLaVA-NeXT-VideoLLM=Vicuna-7B, Frames=322025.0320.1
VideoChat2LLM=Vicuna-7B, Frames=162025.0312.4
LLAMA-VIDLLM=Vicuna-7B, Frames=1fps2025.0310.8