List your company

Reasoning Evaluation on ParaRev

63.7WR vs. BaseFull DRO
39.88446.06752.2558.433Jun 16, 2025

Evaluation results

MethodLinks
Full DROReward=DRO, Rollout-Group Rejection (Rubric)=true, Rollout-Group Rejection (Variance)=true2025.0663.7
R3Reward=R3, Rollout-Group Rejection (Rubric)=true, Rollout-Group Rejection (Variance)=false2025.0661.6
R3Reward=R3, Rollout-Group Rejection (Rubric)=false, Rollout-Group Rejection (Variance)=false2025.0657.8
Rubric (RLER)Reward=Rubric (RLER), Rollout-Group Rejection (Rubric)=false, Rollout-Group Rejection (Variance)=false2025.0655.9
Avg Prob (RLPR)Reward=Avg Prob (RLPR), Rollout-Group Rejection (Rubric)=false, Rollout-Group Rejection (Variance)=false2025.0654.3
BaseReward=Base2025.0650
Avg Logprob (VeriFree)Reward=Avg Logprob (VeriFree), Rollout-Group Rejection (Rubric)=false, Rollout-Group Rejection (Variance)=false2025.0649.5
RL-F1Reward=RL-F1, Rollout-Group Rejection (Rubric)=false, Rollout-Group Rejection (Variance)=false2025.0640.8