OOD Quality Estimation on Mathematical Reasoning OOD (Near-shift)
0.159Kendall Tau
TV Score
Updated 4d ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
2024.05 | 0.159 | 0.158 | |
2024.05 | 0.131 | 0.146 | |
2024.05 | 0.123 | 0.154 | |
2024.05 | 0.113 | 0.134 | |
2024.05 | 0.074 | 0.05 | |
2024.05 | 0.059 | 0.098 | |
2024.05 | 0.057 | 0.057 | |
2024.05 | 0.038 | 0.026 | |
2024.05 | 0.038 | 0.012 | |
2024.05 | 0.036 | 0.115 | |
2024.05 | 0.036 | 0.029 | |
2024.05 | 0.035 | 0.058 |