Policy Optimization on Glucose benchmark leaderboard · SOTA2 Research

Policy Optimization on Glucose

6.3True OutcomeORPO*

Evaluation Results

Method	Links
ORPO*2026.04		6.3	116.36	-8.79
Max-Min2026.04		6.3	102.66	-1.71
ORPO*2026.04		6.3	116.36	-8.79
Max-Min2026.04		6.3	102.66	-1.71
ORPO2026.04		6	100.48	-27.54
ORPO2026.04		6	100.48	-27.54