List your company

Mathematical Reasoning on MATH In-Distribution (test)

56.1Final Answer AccuracyCausalRM
23.65232.07640.548.924Jan 29, 2026

Evaluation results

MethodLinks
CausalRMEvaluation Type=Downstream RLHF2026.0156.1
GoalRMEvaluation Type=Downstream RLHF2026.0155.6
SFTEvaluation Type=Downstream RLHF2026.0153.3
Standard RMEvaluation Type=Downstream RLHF2026.0150.1
InfoRMEvaluation Type=Downstream RLHF2026.0124.9