Openenv Textarena RL Env (Hugging Face)

Fresh

OpenEnv port of TextArena - a collection of competitive text games (Wordle, Snake, Tic-Tac-Toe, etc.) for evaluating LLM reasoning under interactive rules.

Type: RL Env
Publisher: Hugging Face
Capabilities: Planning Instruction Following Multi Turn Dialog
Runtime: openenv
License: bsd-3-clause
Size: 70+ text games
Published: Nov 2025
Canonical: github.com/meta-pytorch/OpenEnv/tree/main/envs/textarena_env

Cite

Notes

Only stored in your browser.

Attribution

README: github.com/meta-pytorch/OpenEnv/blob/main/envs/textarena_env/README.mdBSD-3-CLAUSE

Attribution policy →

Evals this tool implements

Same problem set, this tool's harness. Run it to score a model on the test.

TextArena

Laude Institute

70+ competitive text games (negotiation, social deduction, language puzzles) where models play head-to-head and a TrueSkill rating is fit.

ActiveMulti Turn DialogPlanningInstruction FollowingAgentic

Models

Compatible

any

Papers

introducesTextArena: Multi-Agent Text-Based Games for LLM Evaluation

Contributors

Leon Guertler Meta FAIR