lmgame-Bench: How Good are LLMs at Playing Games?

Lanxiang Hu, Mingjia Huo, Yuxuan Zhang, Haoyang Yu, Eric P Xing, Ion Stoica

arXiv [cs.AI], 2025

"This paper provides the core data and results for the video's analysis, benchmarking various AI models on classic video games to evaluate their intelligence and planning abilities."