List your company

Correctness Prediction on GPQA (WP-AUC)

0.703WP-AUCOp-XGB
0.518920.566710.61450.66229May 28, 2026

Evaluation results

MethodLinks
Op-XGBEvaluation Protocol=ID2026.050.703
OSTEvaluation Protocol=CD2026.050.691
OSTEvaluation Protocol=ID2026.050.691
Op-XGBEvaluation Protocol=CD2026.050.682
WaitEvaluation Protocol=CD2026.050.602
WaitEvaluation Protocol=ID2026.050.602
LengthEvaluation Protocol=CD2026.050.591
LengthEvaluation Protocol=ID2026.050.591
BacktrackEvaluation Protocol=CD2026.050.591
BacktrackEvaluation Protocol=ID2026.050.591
SelfCheckEvaluation Protocol=CD2026.050.526
SelfCheckEvaluation Protocol=ID2026.050.526