stalkermustang/llm-bulls-and-cows-benchmark

A mini-framework for evaluating LLM performance on the Bulls and Cows number guessing game, supporting multiple LLM providers.

28
/ 100
Experimental

This project helps evaluate how well different large language models (LLMs) can play the classic number-guessing game 'Bulls and Cows'. You input a list of LLMs you want to test, and it outputs detailed performance metrics like success rates, how many turns each model takes to win, and how often they fail to follow formatting rules. This is for researchers or practitioners who need to compare the reasoning and in-context learning abilities of various LLMs for decision-making tasks.

237 stars. No commits in the last 6 months.

Use this if you need to systematically benchmark and compare the logical reasoning and memory recall capabilities of different LLMs using a standardized, interactive game.

Not ideal if you are looking for a general-purpose LLM evaluation tool for a wide range of tasks beyond number-guessing games.

LLM evaluation AI model benchmarking reasoning assessment game AI cognitive science
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 2 / 25

How are scores calculated?

Stars

237

Forks

1

Language

HTML

License

MIT

Last pushed

Jan 31, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/stalkermustang/llm-bulls-and-cows-benchmark"

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