# huybery/Awesome-Code-LLM

👨‍💻 An awesome and curated list of best code-LLM for research.

Repository: https://github.com/huybery/Awesome-Code-LLM
Canonical: https://ross.abutalabs.com/products/huybery-awesome-code-llm
License: MIT
License Family: permissive
Topics: awesome, code-generation, large-language-models
Last push: 2024-12-10T08:10:54+00:00

## Health v2 (maintenance only)
Score: 29/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 82
- inputs: {"age_days": 1155, "days_push": 631, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1289, forks 74 (observed 2026-08-28T04:04:15.284974+00:00)

## What it is
A curated awesome-list of code large language models, including model rankings, evaluation toolkits, leaderboards, and research papers on pre-training, instruction tuning, alignment, prompting, and benchmarking. It serves as a research reference hub for tracking the state of the art in code LLMs.

## Use cases
- find the best open-source code generation LLM
- compare code LLMs on HumanEval and MBPP benchmarks
- discover research papers on code model training and evaluation
- track new releases of code LLMs like Qwen2.5-Coder
- find evaluation toolkits for code models
- research code LLM pre-training and instruction tuning techniques

## When to choose
- you need a curated, regularly updated survey of code LLMs and papers
- you want benchmark comparisons to pick a code model
- you are doing research on code generation with LLMs

## When to avoid
- you need runnable software or a library rather than a reference list
- you need real-time leaderboard data rather than periodically updated rankings

## Facets
- artifact type: learning-resource
- maturity: active
- function: documentation, llm-inference
- domain: large-language-models, awesome-lists, developer-tools
- platform: -
- tags: awesome-list, code-generation, code-llm, research-papers, benchmarks, leaderboard, natural-language-processing, web-server

## Member repositories
- huybery/Awesome-Code-LLM (main) score 29

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:15.284974+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T04:55:44.580942+00:00, confidence not recorded.
  - readme: https://github.com/huybery/Awesome-Code-LLM (fetched 2026-08-28T04:04:15.284974+00:00, sha 921c1f362b0d)
- Data as of 2026-08-30T08:39:29.467469+00:00.