Skip to content

LLM Guide

In code generation workflows, model performance differs significantly across quality, latency, and cost. This category provides a consistent evaluation structure to help developers choose models faster.

  1. Start with Model Comparison and Evaluation in HagiCode.
  2. Pick candidates based on your priority (quality-first, cost-first, or speed-first).
  3. Check the test-time notes before applying conclusions to production use.
  • Refresh conclusions when model capability changes materially.
  • Re-validate test-time context at least once per month.
  • Keep Chinese and English pages aligned in section structure.