List your company

Surgical Debridement on Debridement subtask

90Task Success RateClean
-3.620.74569.3Jun 10, 2026

Evaluation results

MethodLinks
CleanPolicy Architecture=ACT2026.0690————
CleanPolicy Architecture=Diffusion Policy2026.0690————
RandomPolicy Architecture=ACT, Attack Objective=Disruptive2026.06900.19798.9—
RandomPolicy Architecture=Diffusion Policy, Attack Objective=Disruptive2026.06800.19798.9—
UAPPolicy Architecture=ACT, Attack Objective=Steering2026.06800.19698.90.2
CleanPolicy Architecture=π02026.0670————
RandomPolicy Architecture=π0, Attack Objective=Disruptive2026.06600.19699.2—
UAPPolicy Architecture=ACT, Attack Objective=Disruptive2026.06600.19599—
UAPPolicy Architecture=Diffusion Policy, Attack Objective=Disruptive2026.06500.19598.9—
UAPPolicy Architecture=Diffusion Policy, Attack Objective=Steering2026.06500.194990.7
UAPPolicy Architecture=π0, Attack Objective=Steering2026.06300.19499.30.7
PGDPolicy Architecture=ACT, Attack Objective=Steering2026.062087.29796.10.8
TPAPolicy Architecture=ACT, Attack Objective=Steering2026.06103.69098.84.6
UAPPolicy Architecture=π0, Attack Objective=Disruptive2026.0600.19499.3—
PGDPolicy Architecture=ACT, Attack Objective=Disruptive2026.06084.39795.1—
PGDPolicy Architecture=Diffusion Policy, Attack Objective=Disruptive2026.0604,6429693.6—
PGDPolicy Architecture=π0, Attack Objective=Disruptive2026.0603,0509799.1—
TPAPolicy Architecture=ACT, Attack Objective=Disruptive2026.0603.98198.7—
TPAPolicy Architecture=Diffusion Policy, Attack Objective=Disruptive2026.0607.46898.6—
TPAPolicy Architecture=π0, Attack Objective=Disruptive2026.0607.87698.7—
PGDPolicy Architecture=Diffusion Policy, Attack Objective=Steering2026.0605,0249696.3-1.1
PGDPolicy Architecture=π0, Attack Objective=Steering2026.0603,3149793.8-0.6
TPAPolicy Architecture=Diffusion Policy, Attack Objective=Steering2026.06013.58398.61.9
TPAPolicy Architecture=π0, Attack Objective=Steering2026.0606.68898.83.1