Common-sense reasoning on Chem OOD Large Shift
49.3Accuracy
PoLAR-VBLL (w/o LA)
Updated 12d ago
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
2026.04 | 49.3 | 15.05 | 1.21 | |
2026.04 | 49.3 | 10.3 | 1.16 | |
2026.04 | 49.3 | 10.3 | 1.16 | |
2026.04 | 48.33 | 26.33 | 1.56 | |
2026.04 | 48.33 | 11.48 | 1.18 | |
2026.04 | 48.33 | 14.89 | 1.42 | |
2026.04 | 48 | 28.73 | 1.75 | |
2026.04 | 48 | 11.69 | 1.19 | |
2026.04 | 48 | 28.73 | 1.75 | |
2026.04 | 47.67 | 27.99 | 1.69 | |
2026.04 | 47.33 | 18.75 | 1.27 | |
2026.04 | 46.87 | 17.83 | 1.23 | |
2026.04 | 46.18 | 20.29 | 1.26 | |
2026.04 | 45.67 | 13.23 | 1.18 |