Habitante/gta-benchmark
GTA (Guess The Algorithm) Benchmark - A tool for testing AI reasoning capabilities
This tool helps AI researchers and developers evaluate the algorithmic reasoning abilities of their AI models. You input a Python function that you believe represents a hidden data transformation, and the system provides input-output examples for you to deduce the transformation logic. The output is an immediate score indicating how well your model's proposed function matches the actual underlying algorithm.
No commits in the last 6 months.
Use this if you need to benchmark and improve your AI models' capability to infer complex logical rules from observed data patterns, essentially 'guessing the algorithm' that produced certain outputs from given inputs.
Not ideal if you are looking for a general-purpose AI development framework or a tool for training AI models; this is specifically designed for evaluating a very particular aspect of AI reasoning.
Stars
7
Forks
—
Language
Python
License
MIT
Category
Last pushed
Jan 12, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Habitante/gta-benchmark"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
mtrebi/AI_FPS
AI system to simulate combat behaviors in a FPS game using Behavior Trees (UE4)
BenLubar/df-ai
Dwarf Fortress + Artificial Intelligence
entity12208/GD-Level-Generator
A way for AI to be able to create Geometry Dash levels using GDShare. Discontinued and replaced...
MinaPecheux/Ebook-Unity-AIProgramming
Demo Unity/C# project (code + assets) for my ebook: "Boost your Unity/C#: AI Programming"
FakeNameSE/Boids-with-obstacles-and-goals
A boids simulation with obstacles and a goal