Skip to content

Select language

Current language: English

LLM Guide

Edit page

Why you need an LLM guide

In code generation scenarios, models differ noticeably in stability, speed, code quality, and cost. This category provides a consistent comparison framework to help you choose a model quickly at different stages of a project.

  1. Start with Model Comparison and Evaluation in HagiCode to learn the comparison dimensions.
  2. Pick candidate models based on your project goal (quality first, cost first, or speed first).
  3. Use the update dates and scenario notes in the article to confirm that its conclusions still apply to your task.

Maintenance principles

  • Update the evaluation conclusions whenever model capabilities change noticeably.
  • Re-check the test date and the scope of the conclusions at least once a month.
  • Keep the Chinese and English pages aligned in section structure.

HagiCode

HagiCode is an agentic coding workspace. Rich, convenient UI interactions make planning, agent execution, and project work approachable and easy to navigate, creating an engaging development experience.

Explore an engaging development experience through rich, convenient UI interactions.

Visit HagiCodeRead the documentation
  • SmartOpenSpec workflows turn intent into an executable path, from proposal to design, tasks, and a shipped change.
  • EfficientMulti-agent execution keeps research, implementation, and review moving in parallel, across several repositories and the Agent CLIs you already use.
  • InterestingRich, convenient UI interactions make planning, agent execution, and project work approachable and easy to navigate.

Download for Windows

Get it from Microsoft StoreAll downloads

Turn ideas into shipped software.

HagiCode is an agentic coding workspace. OpenSpec workflows plan the change, multi-agent execution carries it out, and Hero Scenario makes the long run visible, so ideas become shipped software.

Smart
OpenSpec workflows turn intent into a path from proposal to shipped change.
Efficient
Multi-agent execution runs research, build, and review in parallel.
Fun
Rich UI interactions make planning, agent work, and projects easier to follow.