LLM Judgement Confidence Estimation on AlpacaEval (test)
0.4367Rank Correlation (RK)
Verbalized Confidence
Updated 16d ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
2026.05 | 0.4367 | 56.25 | |
2026.05 | 0.4321 | 56.71 | |
2026.05 | 0.4214 | 57.95 | |
2026.05 | 0.4177 | 58.16 | |
2026.05 | 0.4025 | 59.85 | |
2026.05 | 0.4022 | 59.87 | |
2026.05 | 0.3922 | 60.96 | |
2026.05 | 0.392 | 60.84 | |
2026.05 | 0.3867 | 61.44 | |
| 0.3865 | 61.79 | ||
2026.05 | 0.3839 | 61.62 | |
| 0.3393 | 66.72 | ||
| 0.337 | 65.89 | ||
| 0.3236 | 67.3 | ||
| 0.2776 | 70.48 | ||
| 0.2707 | 70.64 |