List your company

Multimodal Reasoning on Vision R1 (test)

58.75AccuracyGRPO
22.50631.915541.32550.7345Jun 4, 2026

Evaluation results

MethodLinks
GRPOModel Scale=8B, Distillation Strategy=GRPO, Visual Cues (ViCuR)=False2026.0658.75
OPD+ViCuRModel Scale=8B, Distillation Strategy=OPD, Visual Cues (ViCuR)=True2026.0652.07
OPDModel Scale=8B, Distillation Strategy=OPD, Visual Cues (ViCuR)=False2026.0651.09
OPSD+ViCuRModel Scale=8B, Distillation Strategy=OPSD, Visual Cues (ViCuR)=True2026.0645
OPSDModel Scale=8B, Distillation Strategy=OPSD, Visual Cues (ViCuR)=False2026.0642.2
Base ModelModel Scale=8B, Distillation Strategy=None, Visual Cues (ViCuR)=False2026.0641.22
GRPOModel Scale=2B, Distillation Strategy=GRPO, Visual Cues (ViCuR)=False2026.0628.17
OPD+ViCuRModel Scale=2B, Distillation Strategy=OPD, Visual Cues (ViCuR)=True2026.0626.83
OPSD+ViCuRModel Scale=2B, Distillation Strategy=OPSD, Visual Cues (ViCuR)=True2026.0626.58
OPDModel Scale=2B, Distillation Strategy=OPD, Visual Cues (ViCuR)=False2026.0626.34
OPSDModel Scale=2B, Distillation Strategy=OPSD, Visual Cues (ViCuR)=False2026.0625
Base ModelModel Scale=2B, Distillation Strategy=None, Visual Cues (ViCuR)=False2026.0623.9