List your company

Commonsense Reasoning on WorldSense

42.6Overall ScoreGPT-4o
35.21637.13339.0540.967Oct 23, 2025

Evaluation results

MethodLinks
GPT-4oModel=GPT-4o2025.1042.6—
InternVL-2.5-8BModel=InternVL-2.5-8B2025.1039.638.5
VideoRFT-7BModel=VideoRFT-7B2025.1038.236.6
Open-o3-Video-7B (Ours)Model=Open-o3-Video-7B (Ours)2025.1037.536.8
VideoLLaMA3-7BModel=VideoLLaMA3-7B2025.1037.338.1
Qwen2.5-VL-7B (Base)Model=Qwen2.5-VL-7B (Base)2025.1036.133.7
VideoR1-7BModel=VideoR1-7B2025.1035.532.8