lechmazur/elimination_game

A multi-player tournament benchmark that tests LLMs in social reasoning, strategy, and deception. Players engage in public and private conversations, form alliances, and vote to eliminate each other

33
/ 100
Emerging

This project helps AI researchers and developers evaluate how well different large language models (LLMs) handle complex social interactions, strategy, and deception. It takes various LLMs as input and simulates a multi-player 'elimination game' where they communicate, form alliances, and vote each other out. The output includes detailed analytics on conversation logs, voting patterns, and final rankings, revealing how models manage public personas versus hidden agendas.

302 stars.

Use this if you need to benchmark the social reasoning, strategic planning, and deceptive capabilities of LLMs in a dynamic, multi-agent environment.

Not ideal if you are looking to evaluate LLMs purely on factual recall, simple dialogue generation, or task-specific instruction following.

LLM evaluation social AI multi-agent systems AI ethics strategic AI
No License No Package No Dependents
Maintenance 6 / 25
Adoption 10 / 25
Maturity 8 / 25
Community 9 / 25

How are scores calculated?

Stars

302

Forks

11

Language

License

Last pushed

Jan 07, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/agents/lechmazur/elimination_game"

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