List your company

Medical Reasoning on RaR Medicine

57.6WR vs BaseFull DRO
46.26449.20752.1555.093Jun 16, 2025

Evaluation results

MethodLinks
Full DROReward=DRO, Rollout-Group Rejection (Rubric)=true, Rollout-Group Rejection (Variance)=true2025.0657.6
R3Reward=R3, Rollout-Group Rejection (Rubric)=true, Rollout-Group Rejection (Variance)=false2025.0656.1
R3Reward=R3, Rollout-Group Rejection (Rubric)=false, Rollout-Group Rejection (Variance)=false2025.0654.2
Rubric (RLER)Reward=Rubric (RLER), Rollout-Group Rejection (Rubric)=false, Rollout-Group Rejection (Variance)=false2025.0653.4
Avg Prob (RLPR)Reward=Avg Prob (RLPR), Rollout-Group Rejection (Rubric)=false, Rollout-Group Rejection (Variance)=false2025.0652.3
BaseReward=Base2025.0650
Avg Logprob (VeriFree)Reward=Avg Logprob (VeriFree), Rollout-Group Rejection (Rubric)=false, Rollout-Group Rejection (Variance)=false2025.0648
RL-F1Reward=RL-F1, Rollout-Group Rejection (Rubric)=false, Rollout-Group Rejection (Variance)=false2025.0646.7