Code Review: AI Model Selection Guide

Code Review

Användningsöversikt

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

Urvalskriterier

• HumanEval 得分 ≥ 70
• 上下文窗口 ≥ 32K

Utvärderingskriterier

• HumanEval 得分 ≥ 70
• 上下文窗口 ≥ 32K

Bästa praxis

• 提供系统提示以建立上下文
• 监控 token 用量与成本

Rekommenderade modeller

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