Correctness Prediction on GPQA (WP-AUC)
0.703WP-AUCOp-XGB
Evaluation Results
| Method | Links | |
|---|---|---|
| Op-XGBEvaluation Protocol=ID2026.05 | 0.703 | |
| OSTEvaluation Protocol=CD2026.05 | 0.691 | |
| OSTEvaluation Protocol=ID2026.05 | 0.691 | |
| Op-XGBEvaluation Protocol=CD2026.05 | 0.682 | |
| WaitEvaluation Protocol=CD2026.05 | 0.602 | |
| WaitEvaluation Protocol=ID2026.05 | 0.602 | |
| LengthEvaluation Protocol=CD2026.05 | 0.591 | |
| LengthEvaluation Protocol=ID2026.05 | 0.591 | |
| BacktrackEvaluation Protocol=CD2026.05 | 0.591 | |
| BacktrackEvaluation Protocol=ID2026.05 | 0.591 | |
| SelfCheckEvaluation Protocol=CD2026.05 | 0.526 | |
| SelfCheckEvaluation Protocol=ID2026.05 | 0.526 |