ResearchBenchmarksControl on Two-RoomFollow100Success RateDINO-WM86.4889.9993.597.01Jul 6, 2026Evaluation ResultsMethodMethodLinksSuccess RateDINO-WMEvaluation pipeline=Ma...Evaluation pipeline=Maes et al. [29]2026.07100QantaraEvaluation pipeline=Cu...Evaluation pipeline=Current paper reproduction2026.07100PLDMEvaluation pipeline=Ma...Evaluation pipeline=Maes et al. [29]2026.0797LeWMEvaluation pipeline=Cu...Evaluation pipeline=Current paper reproduction2026.0789.9LeWMEvaluation pipeline=Ma...Evaluation pipeline=Maes et al. [29]2026.0787