Math Word Problem solving on MAWPS English (test)
93AccuracyATHENA
Evaluation Results
| Method | Links | |
|---|---|---|
| ATHENABackbone=RoBERTa-large2023.11 | 93 | |
| DeductReasonerBackbone=RoBERTa-large2023.11 | 92.6 | |
| ATHENABackbone=RoBERTa-base2023.11 | 92.2 | |
| DeductReasonerBackbone=RoBERTa-base2023.11 | 92 | |
| R-Graph-to-TreeBackbone=RoBERTa-base2023.11 | 88.7 | |
| R-GTSBackbone=RoBERTa-base2023.11 | 88.5 | |
| R-TransformerBackbone=RoBERTa-base2023.11 | 88.4 | |
| TransformerBackbone=Random embedding2023.11 | 85.6 | |
| Graph-to-TreeBackbone=Random embedding2023.11 | 83.7 | |
| GTSBackbone=Random embedding2023.11 | 82.6 |