lechmazur/nyt-connections

Benchmark that evaluates LLMs using 759 NYT Connections puzzles extended with extra trick words

37
/ 100
Emerging

This project provides a comprehensive benchmark for evaluating large language models (LLMs) on their ability to solve NYT Connections puzzles. It takes a list of words from Connections puzzles, including 'trick' words, and outputs a score indicating how well different LLMs perform. This is primarily useful for AI researchers, language model developers, and data scientists who need to compare and improve reasoning capabilities of different LLMs.

199 stars.

Use this if you need to rigorously test and compare the word association and categorical reasoning skills of various large language models using a challenging, expanded dataset.

Not ideal if you are looking for an interactive tool to play NYT Connections, as this is a benchmark, not a game.

AI-evaluation language-model-benchmarking reasoning-assessment NLP-benchmarks generative-AI-testing
No License No Package No Dependents
Maintenance 10 / 25
Adoption 10 / 25
Maturity 8 / 25
Community 9 / 25

How are scores calculated?

Stars

199

Forks

8

Language

Python

License

Last pushed

Mar 06, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/lechmazur/nyt-connections"

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