Confidence Calibration on GPQA (test)
0.102ECE
HTC
Updated 1mo ago
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
2026.01 | 0.102 | 0.213 | 0.706 | |
2026.01 | 0.124 | 0.219 | 0.704 | |
2026.01 | 0.136 | 0.257 | 0.643 | |
2026.01 | 0.139 | 0.258 | 0.61 | |
2026.01 | 0.414 | 0.402 | 0.649 | |
2026.01 | 0.424 | 0.413 | 0.614 | |
2026.01 | 0.454 | 0.523 | 0.593 |