Math Word Problem Solving On Mathqa
Metrics
Answer Accuracy
Results
Performance results of various models on this benchmark
Model Name | Answer Accuracy | Paper Title | Repository |
|---|---|---|---|
| Roberta-DeductReasoner | 78.6 | Learning to Reason Deductively: Math Word Problem Solving as Complex Relation Extraction | |
| Multi-view | 80.6 | Multi-View Reasoning: Consistent Contrastive Learning for Math Word Problem | |
| Exp-Tree | 81.5 | An Expression Tree Decoding Strategy for Mathematical Equation Generation | |
| MWP-BERT | 76.6 | MWP-BERT: Numeracy-Augmented Pre-training for Math Word Problem Solving | |
| ELASTIC (RoBERTa-large) | 83.00 | ELASTIC: Numerical Reasoning with Adaptive Symbolic Compiler |
0 of 5 row(s) selected.