the-crypt-keeper/can-ai-code

Self-evaluating interview for AI coders

42
/ 100
Emerging

This project helps AI developers and researchers evaluate the true reasoning ability of large language models (LLMs). It takes an LLM as input and generates unique, parametrically scaled problems to assess how far up a difficulty ramp the model can climb. The output is a multi-dimensional cognitive fingerprint showing the model's height (difficulty ceiling), efficiency (tokens used), and performance under resource constraints, helping you understand its reasoning strengths and weaknesses.

602 stars. No commits in the last 6 months.

Use this if you are a machine learning researcher or AI developer who needs to rigorously test the advanced reasoning capabilities of different LLMs beyond simple code generation or pattern matching.

Not ideal if you are only interested in whether an AI can generate syntactically correct code or perform basic tasks, as this benchmark focuses on complex, multi-step reasoning.

AI evaluation LLM benchmarking cognitive AI research reasoning assessment model comparison
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 14 / 25

How are scores calculated?

Stars

602

Forks

34

Language

Python

License

MIT

Last pushed

Jun 21, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/the-crypt-keeper/can-ai-code"

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