LARK-AI-Lab/CodeScaler

The official repo for "CodeScaler: Scaling Code LLM Training and Test-Time Inference via Execution-Free Reward Models"

23
/ 100
Experimental

This tool helps developers who are training or using large language models for code generation tasks. It takes a coding problem description and candidate code solutions, then outputs a score indicating the quality of each solution. The primary users are AI/ML engineers and researchers working on code LLMs, who need to efficiently evaluate and improve their models.

Use this if you need to quickly and efficiently score the quality of generated code solutions without running time-consuming execution-based tests.

Not ideal if your primary goal is to run traditional unit tests for correctness on fully developed software, rather than evaluating AI-generated code.

code-generation-LLM AI-model-evaluation machine-learning-engineering reinforcement-learning-from-feedback
No License No Package No Dependents
Maintenance 13 / 25
Adoption 7 / 25
Maturity 3 / 25
Community 0 / 25

How are scores calculated?

Stars

32

Forks

Language

Python

License

Last pushed

Mar 26, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/LARK-AI-Lab/CodeScaler"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.