Arithmetic Reasoning on AQuA-50 (pilot)
88AccuracyZero-shot-CoT
Evaluation Results
| Method | Links | |
|---|---|---|
| Zero-shot-CoTStrategy=Zero-shot2026.07 | 88 | |
| Zero-shot-CoT + SCStrategy=Zero-shot, Self-consistency=true2026.07 | 86 | |
| Semi-CoTStrategy=Semi-supervised Chain-of-Thought2026.07 | 86 |