TextArena

Open-source benchmark project for evaluating LLMs in competitive text-based games (negotiation, social deduction, etc.).

Visit

Type: community
HQ: Distributed
Founded: 2024
Funding: Open-source / community project
Website: textarena.ai
GitHub: github.com/LeonGuertler/TextArena

Cite

Notes

Only stored in your browser.

Evals

Tools

Models

Papers

Boards

People

Tools

TextArena

Multi-agent text-game environment for evaluating and training LLMs in competitive and cooperative gameplay - 50+ games from negotiation to chess-by-prompt, with an online TrueSkill leaderboard.

RL EnvPlanningCommon SenseMulti Turn DialogAgentic