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
Incorporates structured multi-round gameplay with public/private message separation, preference-based pairing, and anonymous voting with tie-break mechanics that escalate from statements to cumulative vote tallies. Generates rich behavioral analytics including TrueSkill ratings, betrayal rates, wordiness metrics, and jury persuasion success rates to quantify how models balance information asymmetry and social manipulation. Built for systematic LLM evaluation across dozens of models with reproducible tournament brackets and frame-by-frame replay visualization.
302 stars.
Stars
302
Forks
11
Language
—
License
—
Category
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.
Featured in
Higher-rated alternatives
StonyBrookNLP/appworld
🌍 AppWorld: A Controllable World of Apps and People for Benchmarking Function Calling and...
qualifire-dev/rogue
AI Agent Evaluator & Red Team Platform
future-agi/ai-evaluation
Evaluation Framework for all your AI related Workflows
microsoft/WindowsAgentArena
Windows Agent Arena (WAA) 🪟 is a scalable OS platform for testing and benchmarking of...
agentscope-ai/OpenJudge
OpenJudge: A Unified Framework for Holistic Evaluation and Quality Rewards