Math Word Problem Solving On Paramawps
Metriken
Accuracy (%)
Ergebnisse
Leistungsergebnisse verschiedener Modelle zu diesem Benchmark
| Paper Title | ||
|---|---|---|
| DeBERTa (VM) | 79.1 | Math Word Problem Solving by Generating Linguistic Variants of Problem Statements |
| DeBERTa | 74.1 | DeBERTa: Decoding-enhanced BERT with Disentangled Attention |
| GPT-3.5 Turbo (175B) | 73.0 | Math Word Problem Solving by Generating Linguistic Variants of Problem Statements |
| GPT-J (6B) | 5.9 | Math Word Problem Solving by Generating Linguistic Variants of Problem Statements |
| GPT-3 text-curie-001 (13B) | 4.20 | Math Word Problem Solving by Generating Linguistic Variants of Problem Statements |
| GPT-3 text-babbage-001 (6.7B) | 3.21 | Math Word Problem Solving by Generating Linguistic Variants of Problem Statements |
0 of 6 row(s) selected.