Data as of Jul 25, 2026 · Based on 2,718,867 AI responses across 9,511 prompts · See how Parse measures this
GSM8Kgithub.comGSM8K is a dataset of 8,500 high-quality, linguistically diverse grade school math word problems created by human problem writers. It is designed to diagnose failures in multi-step mathematical reasoning in large language models and support research in this area.
Parse Score
