List your company

Mathematical Reasoning on MATH OOD (Component Breakdown)

89.9Algebra222 AccuracyCausalRM
81.26883.50985.7587.991Jan 29, 2026

Evaluation results

MethodLinks
CausalRM2026.0189.966.289.992.289.685.6
Standard RM2026.0183.660.890.591.588.683
InfoRM2026.0182.763.588.989.987.682.5
GoalRM2026.0181.664.489.589.186.482.2