terryyz/ice-score

[EACL 2024] ICE-Score: Instructing Large Language Models to Evaluate Code

38
/ 100
Emerging

This tool helps evaluate the quality of computer code snippets generated by large language models. You provide a coding problem, the generated code, and optionally, a reference solution. The tool then outputs an evaluation score, assessing aspects like usefulness. This is for developers working with AI code generation, who need to systematically grade the output of different models.

No commits in the last 6 months.

Use this if you are a developer or researcher who needs an automated and consistent way to assess the quality of code produced by AI models for code generation tasks.

Not ideal if you need a code evaluation system that performs full static analysis, dynamic testing, or comprehensive security vulnerability checks beyond simple scoring.

AI-code-generation developer-tools code-evaluation LLM-development software-engineering
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 13 / 25

How are scores calculated?

Stars

80

Forks

10

Language

Python

License

MIT

Last pushed

Jun 16, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/terryyz/ice-score"

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