Uncertainty Estimation on GSM8K
0.675ROC-AUC (128)
LLaMA perplexity
Updated 1mo ago
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
2026.03 | 0.675 | - | 0.605 | 0.577 | |
2026.03 | 0.635 | - | 0.631 | 0.546 | |
2026.03 | 0.633 | - | 0.644 | 0.658 | |
2026.03 | 0.61 | - | 0.616 | 0.613 | |
2026.03 | 0.59 | - | 0.552 | 0.595 | |
2026.03 | 0.559 | - | 0.578 | 0.608 | |
2026.03 | 0.539 | - | 0.513 | 0.54 | |
2026.03 | 0.516 | - | 0.559 | 0.525 | |
2023.08 | - | 0.647 | - | - | |
2023.08 | - | 0.614 | - | - | |
2023.08 | - | 0.521 | - | - | |
2023.08 | - | 0.867 | - | - | |
2023.08 | - | 0.66 | - | - | |
2023.08 | - | 0.831 | - | - | |
2023.08 | - | 0.951 | - | - |