Tag
作者将六个流行的决策模型（jev 1.13、Kev 4B、Clef、Clef Flash、GPT-6 Luna 和 Laya）放在《吃豆人》游戏中进行实时对决，jev 1.13 以平均 2,750 分领跑排行榜。团队已公开排行榜和开源仓库，任何人提交自己的模型即可参赛。
PacBench is a benchmark that evaluates AI models' ability to one-shot a Pac-Man game, providing source code, model labels, and performance stats from various runs.
A blog post about a small web game where you play as the ghost in Pac-Man, with AI-controlled Pac-Man and power pellet mechanics.