Among Us
Among AIs: Social deduction benchmark where AI models play Among Us - testing deception, persuasion, and coordination
- Domain
- rl-env
- License
- unknown
- Published
- Feb 2026
Cite
Notes
Only stored in your browser.
Top score 14 by Qwen3 30B A3B Instruct 2507 - 1 model reporting
Top models
1
Related tools
1Implementations, trainers, datasets and scaffolds linked to this eval.
FAQ
- What is Among Us?
- Among AIs: Social deduction benchmark where AI models play Among Us - testing deception, persuasion, and coordination
- What is the current top score on Among Us?
- The top reported score is 14 by Qwen3 30B A3B Instruct 2507, across 1 model reporting.
- How can a model improve its Among Us score?
- Tools linked to Among Us on Sophon include Among US RL Env (Community) - RL environments, datasets, and scaffolds that target this eval.
- What license is Among Us under?
- Among Us is available under unknown.