List your company

Image Reasoning on ZeroBench sub

24.4AccuracyCoPD
21.290422.097722.90523.7123Apr 29, 2026

Evaluation results

MethodLinks
CoPDTraining Strategy=Co-Evolving Policy Distillation2026.0424.4
CoPDTraining Strategy=CoPD2026.0423.35
MOPDTraining Strategy=MOPD2026.0422.75
Mixed RLVRTraining Strategy=Mixed RLVR2026.0422.6
Text-ExpertTraining Strategy=Text-Specific Expert2026.0422.01
Text-ExpertTraining Strategy=Text-Expert2026.0422.01
Video-ExpertTraining Strategy=Video-Expert2026.0422.01
Mixed RLVRTraining Strategy=Joint optimization on combined budget2026.0421.86
OPD T→VTraining Strategy=Static On-policy Policy Distillation (Text to Image)2026.0421.71
BaseTraining Strategy=Base Model2026.0421.41
Image-ExpertTraining Strategy=Image-Specific Expert2026.0421.41
OPD V→TTraining Strategy=Static On-policy Policy Distillation (Image to Text)2026.0421.41
BaseTraining Strategy=Base2026.0421.41
Image-ExpertTraining Strategy=Image-Expert2026.0421.41