Progressive-Hint Prompting Improves Reasoning in Large Language Models
Open paper
Benchmark
Model
Rank
Results
math-word-problem-solving-on-math
PHP (GPT-4 model)
#30
Accuracy: 53.9
math-word-problem-solving-on-svamp
GPT-4 (PHP)
#3
Execution Accuracy: 91.9
Rank counts only results with a code link.