Commonsense Reasoning on CSQA (Component Scores)
84.98PIQA
Full
Updated 4d ago
Evaluation Results
| Method | Links | ||||||||
|---|---|---|---|---|---|---|---|---|---|
2026.02 | 84.98 | 87.58 | 77.94 | 82.41 | 69.54 | 81.69 | 79.4 | 80.51 | |
2026.02 | 84.66 | 84.09 | 77.38 | 83.25 | 69.62 | 79.79 | 79 | 79.68 | |
2026.02 | 83.9 | 62.92 | 78.3 | 82.28 | 69.03 | 78.93 | 78 | 76.19 | |
2026.02 | 82.97 | 85.9 | 76.36 | 81.31 | 67.49 | 77.66 | 77.2 | 78.41 | |
2026.02 | 82.37 | 62.37 | 76.56 | 80.35 | 66.21 | 75.06 | 74.8 | 73.96 | |
2026.02 | 81.12 | 86.36 | 75.59 | 80.09 | 65.27 | 76.8 | 77.6 | 77.55 | |
2026.02 | 71.06 | 62.74 | 61.72 | 69.23 | 48.81 | 66.46 | 59.6 | 62.82 | |
2026.02 | 64.64 | 79.44 | 66.38 | 67.55 | 51.96 | 65.9 | 66 | 65.98 | |
2026.02 | 64.36 | 62.56 | 57.32 | 68.43 | 47.7 | 65.9 | 51.6 | 59.7 |