Math Word Problem solving on SVAMP English (test)
67.8AccuracyATHENA
Evaluation Results
| Method | Links | |
|---|---|---|
| ATHENABackbone=RoBERTa-large2023.11 | 67.8 | |
| ATHENABackbone=RoBERTa-large2023.11 | 54.8 | |
| ATHENABackbone=RoBERTa-base2023.11 | 52.5 | |
| DeductReasonerBackbone=RoBERTa-large2023.11 | 51.6 | |
| DeductReasonerBackbone=RoBERTa-large2023.11 | 50.3 | |
| ATHENABackbone=RoBERTa-base2023.11 | 45.6 | |
| DeductReasonerBackbone=RoBERTa-base2023.11 | 45 | |
| R-Graph-to-TreeBackbone=RoBERTa-base2023.11 | 43.8 | |
| DeductReasonerBackbone=RoBERTa-base2023.11 | 42.5 | |
| R-GTSBackbone=RoBERTa-base2023.11 | 41 | |
| R-GTSBackbone=RoBERTa-base2023.11 | 40.9 | |
| Graph-to-TreeBackbone=Random embedding2023.11 | 36.5 | |
| R-Graph-to-TreeBackbone=RoBERTa-base2023.11 | 31.8 | |
| GTSBackbone=Random embedding2023.11 | 30.8 | |
| R-TransformerBackbone=RoBERTa-base2023.11 | 30.3 | |
| Graph-to-TreeBackbone=Random embedding2023.11 | 25.3 | |
| TransformerBackbone=Random embedding2023.11 | 20.7 | |
| R-TransformerBackbone=RoBERTa-base2023.11 | 13.5 | |
| GTSBackbone=Random embedding2023.11 | 12.2 | |
| TransformerBackbone=Random embedding2023.11 | 9.7 |