List your company

Mathematical Reasoning on GSM8K In-Distribution (test)

91.8AccuracyCausalRM
70.16875.78481.487.016Jan 29, 2026

Evaluation results

MethodLinks
CausalRMMethod Category=Proposed, Evaluation Type=Downstream RLHF2026.0191.8
GoalRMMethod Category=Baseline, Evaluation Type=Downstream RLHF2026.0189.4
Standard RMMethod Category=Baseline, Evaluation Type=Downstream RLHF2026.0185.5
SFTMethod Category=Reference, Evaluation Type=Downstream RLHF2026.0180.4
InfoRMMethod Category=Baseline, Evaluation Type=Downstream RLHF2026.0171