Math Word Problem Solving On Mawps
Metriken
Accuracy (%)
Ergebnisse
Leistungsergebnisse verschiedener Modelle zu diesem Benchmark
Vergleichstabelle
| Modellname | Accuracy (%) |
|---|---|
| Modell 1 | 9.3 |
| are-nlp-models-really-able-to-solve-simple | 88.5 |
| athena-mathematical-reasoning-with-thought | 92.2 |
| graph-to-tree-learning-for-solving-math-word | 83.7 |
| are-nlp-models-really-able-to-solve-simple | 88.7 |
| learning-multi-step-reasoning-from-arithmetic | 94.3 |
| math-word-problem-solving-by-generating | 80.3 |
| math-word-problem-solving-by-generating | 91.0 |
| ept-x-an-expression-pointer-transformer-model | 88.7 |
| an-expression-tree-decoding-strategy-for | 92.3 |
| athena-mathematical-reasoning-with-thought | 93 |
| ept-x-an-expression-pointer-transformer-model | 84.57 |
| Modell 13 | 7.9 |
| Modell 14 | 19.8 |
| openmathinstruct-1-a-1-8-million-math | 95.7 |
| math-word-problem-solving-by-generating | 9.9 |
| point-to-the-expression-solving-algebraic | 84.51 |
| learning-to-reason-deductively-math-word | 92 |
| math-word-problem-solving-by-generating | 2.76 |
| Modell 20 | 44.0 |
| multi-view-reasoning-consistent-contrastive | 92.3 |
| math-word-problem-solving-by-generating | 4.09 |
| llama-2-open-foundation-and-fine-tuned-chat | 82.4 |
| Modell 24 | 15.0 |
| generating-equation-by-utilizing-operators | 85.1 |