Commonsense Reasoning on WinoGrande (WinoG)
79.95Accuracy
AUSteer
Updated 4d ago
Evaluation Results
| Method | Links | |
|---|---|---|
2026.02 | 79.95 | |
2026.02 | 78.14 | |
2026.02 | 74.59 | |
2026.02 | 74.59 | |
2026.02 | 74.4 | |
2026.02 | 74.35 | |
2026.02 | 73.88 | |
2026.02 | 73.72 | |
2026.02 | 73.64 | |
2026.02 | 73.4 | |
2026.02 | 72.45 | |
2026.02 | 69.77 | |
2026.02 | 67.17 | |
2026.02 | 66.54 | |
2026.02 | 65.98 | |
2026.02 | 61.56 | |
2026.02 | 57.93 | |
2026.02 | 54.14 | |
2026.02 | 48.7 |