Least-to-Most Prompting Enables Complex Reasoning in Large Language Models

Open paper
Benchmark Model Rank Results
question-answering-on-strategyqaLeast-to-Most#7EM: 65.8
arithmetic-reasoning-on-gsm8kcode-davinci-002 (Least-to-Most Prompting)#203Accuracy: 68.01Parameters (Billion): 175

Rank counts only results with a code link.