ResearchBenchmarksPut corn in pot on WidowX real-worldFollow65Success RatePOSTBC1326.54053.5Dec 18, 2025Evaluation ResultsMethodMethodLinksSuccess RatePOSTBCEvaluation Protocol=Be...Evaluation Protocol=Best-of-N, Sampling Rollouts (N)=1002025.1265POSTBCEvaluation Protocol=Pr...Evaluation Protocol=Pretrained2025.1235BCEvaluation Protocol=Be...Evaluation Protocol=Best-of-N, Sampling Rollouts (N)=1002025.1225BCEvaluation Protocol=Pr...Evaluation Protocol=Pretrained2025.1215