Reasoning on BBH (Brier Score)
9.26Brier Score (BBH)CAGE-CAL
Evaluation Results
| Method | Links | |
|---|---|---|
| CAGE-CALCalibration category=Trained calibrators2026.05 | 9.26 | |
| DiscoUQ-LLMCalibration category=Trained calibrators2026.05 | 17.57 | |
| + IsotonicCalibration category=Post-hoc plurality calibrators2026.05 | 17.73 | |
| + PlattCalibration category=Post-hoc plurality calibrators2026.05 | 17.97 | |
| + Scaling-bin.Calibration category=Post-hoc plurality calibrators2026.05 | 17.98 | |
| Scalar + GBTCalibration category=Trained calibrators2026.05 | 18.11 | |
| Collab. Cal.Calibration category=LLM-elicited confidence estimators2026.05 | 18.26 | |
| LLM-Cal (no topo)Calibration category=LLM-elicited confidence estimators2026.05 | 19.37 | |
| LLM-Cal (+topo)Calibration category=LLM-elicited confidence estimators2026.05 | 19.4 | |
| GraphCalCalibration category=Trained calibrators2026.05 | 20.18 | |
| Plurality shareCalibration category=Post-hoc plurality calibrators2026.05 | 23.89 |