Uncertainty Quantification on Countdown, GSM8K, MATH500, SVAMP Combined
63.7Average ROC-AUC
DiSE
Updated 1mo ago
Evaluation Results
| Method | Links | |
|---|---|---|
2026.03 | 63.7 | |
2026.03 | 59.2 | |
2026.03 | 57.8 | |
2026.03 | 57.3 | |
2026.03 | 57.2 | |
2026.03 | 56.7 | |
2026.03 | 53.5 | |
2026.03 | 53.2 |
DiSE
| Method | Links | |
|---|---|---|
2026.03 | 63.7 | |
2026.03 | 59.2 | |
2026.03 | 57.8 | |
2026.03 | 57.3 | |
2026.03 | 57.2 | |
2026.03 | 56.7 | |
2026.03 | 53.5 | |
2026.03 | 53.2 |