Commonsense Reasoning on PIQA (Accuracy and Average Accuracy)
60.66Accuracy
GRASPrune
Updated 3mo ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
2026.04 | 60.66 | 44.12 | |
2026.04 | 59.47 | 43.44 | |
2026.04 | 57.34 | 40.74 | |
2026.04 | 57.34 | 41.61 | |
2026.04 | 56.91 | 38.81 | |
2026.04 | 56.64 | 40.6 | |
2026.04 | 56.42 | 39.64 | |
2026.04 | 55.22 | 38.25 | |
2026.04 | 55.06 | 38.99 | |
2026.04 | 54.95 | 38.29 | |
2026.04 | 53.65 | 36.54 | |
2026.04 | 53.26 | 37.58 | |
2026.04 | 52.18 | 37.25 | |
2026.04 | 51.63 | 36.88 | |
2026.04 | 51.36 | 36.52 | |
2026.04 | 50.71 | 35.28 |