List your company

Video Understanding on VideoMME (Accuracy Delta Reporting)

65.6Accuracy (Base)AKS
51.45655.12858.862.472Feb 28, 2026

Evaluation results

MethodLinks
AKSModel=InternVL-3 [47], Size=8B, Frame=322026.0265.666.30.7
MDP3Model=InternVL-3 [47], Size=8B, Frame=322026.0265.666.81.2
A.I.R.Model=InternVL-3 [47], Size=8B, Frame=≤32§2026.0265.668.22.6
WFS-SBModel=InternVL-3 [47], Size=8B, Frame=322026.0265.667.41.8
AKSModel=Qwen2.5-VL [2], Size=7B, Frame=322026.0261.2642.8
WFS-SBModel=Qwen2.5-VL [2], Size=7B, Frame=322026.0261.264.43.2
MDP3Model=Qwen2.5-VL [2], Size=7B, Frame=322026.0260.863.83
A.I.R.Model=Qwen2.5-VL [2], Size=7B, Frame=≤32§2026.0260.8654.2
AKSModel=LLaVA-Video [44], Size=7B, Frame=82026.0256.260.13.9
WFS-SBModel=LLaVA-Video [44], Size=7B, Frame=82026.0256.261.75.5
BOLTModel=LLaVA-Video [44], Size=7B, Frame=82026.025658.62.6
KFCModel=LLaVA-Video [44], Size=7B, Frame=82026.0255.957.61.7
FrameOracleModel=LLaVA-Video [44], Size=7B, Frame=82026.0255.958.93
KFCModel=Qwen2-VL-7B [34], Size=7B, Frame=82026.025556.71.7
AKSModel=LLaVA-OV [10], Size=7B, Frame=82026.0254.158.24.1
WFS-SBModel=LLaVA-OV [10], Size=7B, Frame=82026.0254.159.35.2
BOLTModel=LLaVA-OV [10], Size=7B, Frame=82026.0253.856.12.3
FrameOracleModel=LLaVA-OV [10], Size=7B, Frame=82026.0253.857.53.7
Q-FrameModel=Qwen2-VL-7B [34], Size=7B, Frame=8 (4+8+32)∗2026.0253.758.34.6
Frame-VoyagerModel=LLaVA-OV [10], Size=7B, Frame=82026.0253.357.54.2
KFCModel=LLaVA-OV [10], Size=7B, Frame=82026.0253.355.42.1
WFS-SBModel=Qwen2-VL-7B [34], Size=7B, Frame=82026.025256.44.4