List your company

Offline Video Understanding on VideoMME v1 (test)

77.2AccuracyGPT4-o
50.47257.41164.3571.289May 14, 2026

Evaluation results

MethodLinks
GPT4-oSize=–, # Frames (Max)=1fps, Budget |M|=–2026.0577.2
CoRDSSize=7B, # Frames (Max)=768, Budget |M|=6K, Backbone=Qwen2.5-VL2026.0565.7
CoRDSSize=7B, # Frames (Max)=768, Budget |M|=3K, Backbone=Qwen2.5-VL2026.0565.3
Qwen2.5-VL (Original)Size=7B, # Frames (Max)=768, Budget |M|=50K, Backbone=Qwen2.5-VL2026.0564.9
CoRDSSize=7B, # Frames (Max)=768, Budget |M|=6K, Backbone=Qwen2-VL2026.0564.8
CoRDSSize=7B, # Frames (Max)=768, Budget |M|=3K, Backbone=Qwen2-VL2026.0564.3
Qwen2-VL (Original)Size=7B, # Frames (Max)=768, Budget |M|=50K, Backbone=Qwen2-VL2026.0563.9
Qwen2-VL + InfiniPot-VSize=7B, # Frames (Max)=768, Budget |M|=6K, Backbone=Qwen2-VL2026.0562.8
LLaVA-Next-Video (Original)Size=7B, # Frames (Max)=128, Budget |M|=25K, Backbone=LLaVA-Next-Video2026.0562.8
CoRDSSize=7B, # Frames (Max)=128, Budget |M|=6K, Backbone=LLaVA-Next-Video2026.0562.5
Qwen2-VL + StreamMemSize=7B, # Frames (Max)=4.0/0.5 fps, Budget |M|=6K, Backbone=Qwen2-VL2026.0562.1
CoRDSSize=7B, # Frames (Max)=128, Budget |M|=3K, Backbone=LLaVA-Next-Video2026.0562
CoRDSSize=3B, # Frames (Max)=768, Budget |M|=3K, Backbone=Qwen2.5-VL2026.0561.7
Qwen2-VL + InfiniPot-VSize=7B, # Frames (Max)=768, Budget |M|=3K, Backbone=Qwen2-VL2026.0561.2
LLaVA-Next-Video + InfiniPot-VSize=7B, # Frames (Max)=128, Budget |M|=6K, Backbone=LLaVA-Next-Video2026.0561.1
CoRDSSize=3B, # Frames (Max)=768, Budget |M|=6K, Backbone=Qwen2.5-VL2026.0561.1
GPT4-VSize=–, # Frames (Max)=1fps, Budget |M|=–2026.0560.7
LongVUSize=7B, # Frames (Max)=1fps, Budget |M|=8K2026.0560.6
Qwen2.5-VL (Original)Size=3B, # Frames (Max)=768, Budget |M|=50K, Backbone=Qwen2.5-VL2026.0560.3
Qwen2-VL + STCSize=7B, # Frames (Max)=768, Budget |M|=6K, Backbone=Qwen2-VL2026.0560.1
Qwen2-VL + TTCSize=7B, # Frames (Max)=768, Budget |M|=6K, Backbone=Qwen2-VL2026.0559.8
Qwen2.5-VL + StreamMemSize=3B, # Frames (Max)=4.0/0.5 fps, Budget |M|=6K, Backbone=Qwen2.5-VL2026.0559.5
Qwen2.5-VL + InfiniPot-VSize=3B, # Frames (Max)=768, Budget |M|=6K, Backbone=Qwen2.5-VL2026.0559.3
LLaVA-OVSize=7B, # Frames (Max)=32, Budget |M|=8K2026.0558.2
Qwen2-VL + STCSize=7B, # Frames (Max)=768, Budget |M|=3K, Backbone=Qwen2-VL2026.0556.1
Qwen2-VL + TTCSize=7B, # Frames (Max)=768, Budget |M|=3K, Backbone=Qwen2-VL2026.0555.3
LongVUSize=3B, # Frames (Max)=1fps, Budget |M|=8K2026.0551.5