List your company

LLM Reasoning Factuality on MATH

97.09CoverageCF
89.34291.353593.36595.3765Apr 22, 2026

Evaluation results

MethodLinks
CFα=0.032026.0497.090.73——
DCFα=0.032026.0496.551.76141.1—
CFα=0.042026.0495.81.14——
DCFα=0.042026.0495.592.2294.7—
DCFα=0.052026.0495.552.3160.4—
CFα=0.052026.0494.851.44——
DCFα=0.062026.0494.143.56104.6—
DCFα=0.082026.0494.143.6959.7—
CFα=0.062026.0494.11.74——
DCFα=0.072026.0493.143.6380.6—
CFα=0.072026.04932.01——
CFα=0.082026.0491.822.31——
DCFα=0.092026.0490.645.57102.5—
CFα=0.092026.0490.592.75——
CFα=0.102026.0489.683.33——
DCFα=0.102026.0489.645.9979.9—