Math Reasoning: AI Model Selection Guide

Math Reasoning

Overzicht gebruiksscenario

This page focuses on the Math Reasoning use case, covering core requirements, recommended models, and evaluation criteria.

Selectiecriteria

• GSM8K/MATH 得分 ≥ 70

Evaluatiecriteria

• GSM8K/MATH 得分 ≥ 70

Best practices

• 提供系统提示以建立上下文
• 监控 token 用量与成本

Aanbevolen modellen

See the recommended models list for this use case (path: /en/use-cases/math-reasoning/).