Common-sense Reasoning on WinoGrande S In-Distribution Llama-3.1-8B (train test)
78.09Accuracy
PoLAR-MLE
Updated 12d ago
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
2026.04 | 78.09 | 20.48 | 1.97 | |
2026.04 | 78.09 | 15.19 | 0.61 | |
2026.04 | 78.09 | 15.06 | 0.76 | |
2026.04 | 77.92 | 21.11 | 2.23 | |
2026.04 | 77.92 | 16.41 | 0.57 | |
2026.04 | 77.32 | 20.87 | 2.12 | |
2026.04 | 77.26 | 8.19 | 0.61 | |
2026.04 | 77.26 | 3.89 | 0.58 | |
2026.04 | 77.16 | 18.31 | 0.85 | |
2026.04 | 77 | 18.89 | 1.42 | |
2026.04 | 76.92 | 21.58 | 2.24 | |
2026.04 | 76.49 | 5.21 | 0.67 | |
2026.04 | 76.25 | 12.34 | 0.59 | |
2026.04 | 73.53 | 5.9 | 0.59 | |
2026.04 | 72.36 | 5.78 | 0.58 |