| math-word-problem-solving-on-mawps | DeBERTa (PM + VM) | #8 | Accuracy (%): 91.0 |
| math-word-problem-solving-on-mawps | GPT-3.5 turbo (175B) | #16 | Accuracy (%): 80.3 |
| math-word-problem-solving-on-mawps | GPT-J | #17 | Accuracy (%): 9.9 |
| math-word-problem-solving-on-mawps | GPT-3 text-curie-001 (13B) | #18 | Accuracy (%): 4.09 |
| math-word-problem-solving-on-mawps | GPT-3 text-babbage-001 (6.7B) | #19 | Accuracy (%): 2.76 |
| math-word-problem-solving-on-paramawps | DeBERTa (VM) | #1 | Accuracy (%): 79.1 |
| math-word-problem-solving-on-paramawps | GPT-3.5 Turbo (175B) | #3 | Accuracy (%): 73.0 |
| math-word-problem-solving-on-paramawps | GPT-J (6B) | #4 | Accuracy (%): 5.9 |
| math-word-problem-solving-on-paramawps | GPT-3 text-curie-001 (13B) | #5 | Accuracy (%): 4.20 |
| math-word-problem-solving-on-paramawps | GPT-3 text-babbage-001 (6.7B) | #6 | Accuracy (%): 3.21 |
| math-word-problem-solving-on-svamp | DeBERTa | #12 | Execution Accuracy: 63.5Accuracy: 63.5 |