List your company
ResearchFormerly WizWand

Arithmetic Reasoning on GSM8K (n=200 test subset)

95.5AccuracyChain-of-Thought Prompting
19.0638.90558.7578.595Apr 29, 2025
Updated 8mo ago

Evaluation results

MethodLinks
Chain-of-Thought PromptingBase Model=GPT-4, Prompting Type=Zero-Shot2025.0495.5
Plan & Solve PromptingBase Model=GPT-4, Prompting Type=Zero-Shot2025.0495.5
Trace-of-Thought PromptingBase Model=GPT-4, Teacher Model=GPT-4, Prompting Type=Zero-Shot2025.0495
Standard PromptingBase Model=GPT-4, Prompting Type=Zero-Shot2025.0494.5
Trace-of-Thought PromptingBase Model=Llama 3 Chat 8B, Teacher Model=GPT-4, Prompting Type=Zero-Shot2025.0488
Trace-of-Thought PromptingBase Model=GPT-3.5-Turbo, Teacher Model=GPT-4, Prompting Type=Zero-Shot2025.0486.5
Trace-of-Thought PromptingBase Model=GPT-4, Teacher Model=Llama 3 8B, Prompting Type=Zero-Shot2025.0483
Plan & Solve PromptingBase Model=WizardMath-7B, Prompting Type=Zero-Shot2025.0482.5
Trace-of-Thought PromptingBase Model=WizardMath-7B, Teacher Model=GPT-4, Prompting Type=Zero-Shot2025.0481.5
Standard PromptingBase Model=GPT-3.5-Turbo, Prompting Type=Zero-Shot2025.0475.5
Plan & Solve PromptingBase Model=GPT-3.5-Turbo, Prompting Type=Zero-Shot2025.0474.5
Chain-of-Thought PromptingBase Model=GPT-3.5-Turbo, Prompting Type=Zero-Shot2025.0473.5
Chain-of-Thought PromptingBase Model=WizardMath-7B, Prompting Type=Zero-Shot2025.0473.5
Standard PromptingBase Model=Llama 3 Chat 8B, Prompting Type=Zero-Shot2025.0473
Chain-of-Thought PromptingBase Model=Llama 3 Chat 8B, Prompting Type=Zero-Shot2025.0473
Trace-of-Thought PromptingBase Model=WizardMath-7B, Teacher Model=Llama 3 8B, Prompting Type=Zero-Shot2025.0470.5
Standard PromptingBase Model=WizardMath-7B, Prompting Type=Zero-Shot2025.0469
Plan & Solve PromptingBase Model=Llama 3 Chat 8B, Prompting Type=Zero-Shot2025.0468.5
Trace-of-Thought PromptingBase Model=GPT-3.5-Turbo, Teacher Model=Llama 3 8B, Prompting Type=Zero-Shot2025.0464.5
Trace-of-Thought PromptingBase Model=Llama 3 Chat 8B, Teacher Model=Llama 3 8B, Prompting Type=Zero-Shot2025.0463.5
Trace-of-Thought PromptingBase Model=Zephyr, Teacher Model=GPT-4, Prompting Type=Zero-Shot2025.0455
Trace-of-Thought PromptingBase Model=Llama 2 Chat 7B, Teacher Model=GPT-4, Prompting Type=Zero-Shot2025.0450
Trace-of-Thought PromptingBase Model=Zephyr, Teacher Model=Llama 3 8B, Prompting Type=Zero-Shot2025.0443
Trace-of-Thought PromptingBase Model=Llama 2 Chat 7B, Teacher Model=Llama 3 8B, Prompting Type=Zero-Shot2025.0437.5
Plan & Solve PromptingBase Model=Zephyr, Prompting Type=Zero-Shot2025.0430
Standard PromptingBase Model=Zephyr, Prompting Type=Zero-Shot2025.0426
Chain-of-Thought PromptingBase Model=Llama 2 Chat 7B, Prompting Type=Zero-Shot2025.0423.5
Chain-of-Thought PromptingBase Model=Zephyr, Prompting Type=Zero-Shot2025.0423.5
Plan & Solve PromptingBase Model=Llama 2 Chat 7B, Prompting Type=Zero-Shot2025.0423
Standard PromptingBase Model=Llama 2 Chat 7B, Prompting Type=Zero-Shot2025.0422