List your company

Video Reasoning on SEED-Bench L3 OOD R1

49.3AccuracyAPPO
24.65231.05137.4543.849Feb 27, 2026

Evaluation results

MethodLinks
APPOBackbone=Qwen2.5-VL-7B, Resolution=224x224, Sampling Rate=1 fps, Max Frames=602026.0249.3
DAPOBackbone=Qwen2.5-VL-7B, Resolution=224x224, Sampling Rate=1 fps, Max Frames=602026.0248.7
GRPOBackbone=Qwen2.5-VL-7B, Resolution=224x224, Sampling Rate=1 fps, Max Frames=602026.0248.2
SFTBackbone=Qwen2.5-VL-7B, Resolution=224x224, Sampling Rate=1 fps, Max Frames=602026.0243.9
APPOBackbone=Qwen2.5-VL-3B, Resolution=224x224, Sampling Rate=1 fps, Max Frames=602026.0235
APPOSize=7B, Training Data=34K, Resolution=224 x 224, Sampling Rate (fps)=1fps, Maximum Frames=30, Zero-shot evaluation=true2026.0234.7
DAPOBackbone=Qwen2.5-VL-3B, Resolution=224x224, Sampling Rate=1 fps, Max Frames=602026.0231.8
GRPOBackbone=Qwen2.5-VL-3B, Resolution=224x224, Sampling Rate=1 fps, Max Frames=602026.0231
Base ModelBackbone=Qwen2.5-VL-7B, Resolution=224x224, Sampling Rate=1 fps, Max Frames=602026.0229.6
Video-R1Size=7B, Training Data=260K, Resolution=224 x 224, Sampling Rate (fps)=1fps, Maximum Frames=30, Zero-shot evaluation=true2026.0228.8
SFTBackbone=Qwen2.5-VL-3B, Resolution=224x224, Sampling Rate=1 fps, Max Frames=602026.0228.6
VideoChat-R1Size=7B, Training Data=18K, Resolution=224 x 224, Sampling Rate (fps)=1fps, Maximum Frames=30, Zero-shot evaluation=true2026.0227.8
VideoRFTSize=7B, Training Data=310K, Resolution=224 x 224, Sampling Rate (fps)=1fps, Maximum Frames=30, Zero-shot evaluation=true2026.0227.7
Base ModelBackbone=Qwen2.5-VL-3B, Resolution=224x224, Sampling Rate=1 fps, Max Frames=602026.0227
GRPO-CARESize=7B, Training Data=260K, Resolution=224 x 224, Sampling Rate (fps)=1fps, Maximum Frames=30, Zero-shot evaluation=true2026.0226
TW-GRPOSize=7B, Training Data=1K, Resolution=224 x 224, Sampling Rate (fps)=1fps, Maximum Frames=30, Zero-shot evaluation=true2026.0225.6