List your company

Overall Evaluation on Demo-ICL-Bench

80.1Average ScoreHuman
19.67635.36351.0566.737Feb 9, 2026

Evaluation results

MethodLinks
Human2026.0280.1
Gemini-2.5-Pro2026.0238.9
GPT-4o2026.0234.9
Demo-ICLSize=7B, Frame=322026.0233.1
Demo-ICL (SFT)Size=7B, Frame=322026.0229.8
Qwen2.5-VLSize=72B, Frame=322026.0229.5
LLaVA-VideoSize=7B, Frame=322026.0227.2
VideoChat-R1Size=7B, Frame=322026.0227
Qwen2.5-VLSize=7B, Frame=322026.0226.3
Video-R1Size=7B, Frame=322026.0226.2
InternVL-3Size=8B, Frame=322026.0225
Ola-Video (Base)Size=7B, Frame=322026.0224.8
OlaSize=7B, Frame=322026.0224.3
Qwen2-VLSize=7B, Frame=322026.0222