Correctness Prediction on MMLU Pro
0.639WP-AUCOp-XGB
Evaluation Results
| Method | Links | |
|---|---|---|
| Op-XGBEvaluation Protocol=ID2026.05 | 0.639 | |
| OSTEvaluation Protocol=ID2026.05 | 0.638 | |
| Op-XGBEvaluation Protocol=CD2026.05 | 0.635 | |
| OSTEvaluation Protocol=CD2026.05 | 0.635 | |
| WaitEvaluation Protocol=CD2026.05 | 0.633 | |
| WaitEvaluation Protocol=ID2026.05 | 0.633 | |
| BacktrackEvaluation Protocol=CD2026.05 | 0.628 | |
| BacktrackEvaluation Protocol=ID2026.05 | 0.628 | |
| LengthEvaluation Protocol=CD2026.05 | 0.587 | |
| LengthEvaluation Protocol=ID2026.05 | 0.587 | |
| SelfCheckEvaluation Protocol=CD2026.05 | 0.52 | |
| SelfCheckEvaluation Protocol=ID2026.05 | 0.52 |