metadata
title: Stick To Your Role! Leaderboard
emoji: 🎭
colorFrom: gray
colorTo: purple
sdk: docker
pinned: false
license: mit
short_description: Benchmarking LLMs on the stability of simulated populations
tags:
- leaderboard
- benchmark
- roleplay
- values
- stability
- modality:text
- test:public
- language:english