Common-sense reasoning on WG-M (In-Distribution)
83.61Accuracy
PoLAR-MLE
Updated 12d ago
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
2026.04 | 83.61 | 18.64 | 0.9 | |
2026.04 | 83.61 | 3.16 | 0.53 | |
2026.04 | 83.61 | 8.3 | 0.55 | |
2026.04 | 83.04 | 8.79 | 0.55 | |
2026.04 | 83.04 | 3.77 | 0.53 | |
2026.04 | 82.8 | 15.46 | 1.05 | |
2026.04 | 82.8 | 8.37 | 0.56 | |
2026.04 | 82.7 | 8.02 | 0.61 | |
2026.04 | 82.29 | 7.7 | 0.61 | |
2026.04 | 82.16 | 6.22 | 0.62 | |
2026.04 | 80.71 | 3.28 | 0.55 | |
2026.04 | 79.32 | 3.91 | 0.6 |