Arithmetic Reasoning on MAWPS (5-fold cross val)
94.3Accuracy
MSAT-DEDUCTREASONER
Updated 3d ago
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
2023.06 | 94.3 | - | 2.3 | |
| 93.3 | - | - | ||
2022.12 | 93 | 93.66 | - | |
2023.06 | 92 | - | - | |
2023.06 | 91.6 | - | 3.2 | |
2023.06 | 91.6 | - | -0.4 | |
2023.06 | 88.4 | - | - | |
2023.06 | 84.1 | - | -4.3 | |
2022.12 | 70.41 | 88.22 | - | |
2022.12 | 54.15 | - | - |