Commonsense Reasoning on BoolQ (Inter/Intra-Layer Filtering)
67Accuracy (Inter-Layer Filtering)
CRFT
Updated 4d ago
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
2025.07 | 67 | 67.9 | - | |
2025.07 | 64 | 66.6 | - | |
2025.07 | 63 | 66.4 | - | |
2025.07 | 63 | 66.5 | - | |
2025.07 | 62.5 | 62.5 | - | |
2025.07 | 62.5 | 65 | - | |
2025.07 | 62.4 | 66.2 | - | |
2025.07 | 62.3 | 64.8 | - | |
2025.07 | 62.1 | 62.1 | - | |
2025.07 | 62.1 | 60.8 | - | |
2025.07 | 62 | 54.3 | - | |
2025.07 | 60.5 | 61.8 | - | |
2025.07 | 60 | 53.7 | - | |
2025.07 | 60 | 59.7 | - | |
2025.07 | 50.7 | 50.7 | - | |
2025.05 | - | - | 81.47 | |
2025.05 | - | - | 63.39 | |
2025.05 | - | - | 80.89 | |
2025.05 | - | - | 80 | |
2025.05 | - | - | 81.96 | |
2025.05 | - | - | 82.01 | |
2025.05 | - | - | 82.11 | |
2025.05 | - | - | 82.45 |