hendrycks/apps

APPS: Automated Programming Progress Standard (NeurIPS 2021)

46
/ 100
Emerging

This project provides a comprehensive dataset and tools for evaluating the ability of large language models to solve coding challenges. It takes programming problems as input and measures how well a model can generate correct, executable code. Researchers and developers working on AI that writes code would use this to benchmark and improve their models.

520 stars. No commits in the last 6 months.

Use this if you are a researcher or developer focused on training and evaluating AI models that can generate solutions to programming problems.

Not ideal if you are looking for an application that helps humans write code, or a tool for automated software testing.

AI model evaluation code generation natural language processing research programming challenge benchmarks
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 20 / 25

How are scores calculated?

Stars

520

Forks

70

Language

Python

License

MIT

Last pushed

Jun 19, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ai-coding/hendrycks/apps"

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