Share your thoughts, 1 month free Claude Pro on usSee more

Arithmetic Reasoning on GSM8K (n=200 test subset)

95.5Accuracy

Chain-of-Thought Prompting

Updated 1mo ago

Evaluation Results

Method	Links
Chain-of-Thought Prompting 2025.04		95.5
Plan & Solve Prompting 2025.04		95.5
Trace-of-Thought Prompting 2025.04		95
Standard Prompting 2025.04		94.5
Trace-of-Thought Prompting 2025.04		88
Trace-of-Thought Prompting 2025.04		86.5
Trace-of-Thought Prompting 2025.04		83
Plan & Solve Prompting 2025.04		82.5
Trace-of-Thought Prompting 2025.04		81.5
Standard Prompting 2025.04		75.5
Plan & Solve Prompting 2025.04		74.5
Chain-of-Thought Prompting 2025.04		73.5
Chain-of-Thought Prompting 2025.04		73.5
Standard Prompting 2025.04		73
Chain-of-Thought Prompting 2025.04		73
Trace-of-Thought Prompting 2025.04		70.5
Standard Prompting 2025.04		69
Plan & Solve Prompting 2025.04		68.5
Trace-of-Thought Prompting 2025.04		64.5
Trace-of-Thought Prompting 2025.04		63.5
Trace-of-Thought Prompting 2025.04		55
Trace-of-Thought Prompting 2025.04		50
Trace-of-Thought Prompting 2025.04		43
Trace-of-Thought Prompting 2025.04		37.5
Plan & Solve Prompting 2025.04		30
Standard Prompting 2025.04		26
Chain-of-Thought Prompting 2025.04		23.5
Chain-of-Thought Prompting 2025.04		23.5
Plan & Solve Prompting 2025.04		23
Standard Prompting 2025.04		22