GameCraft-Bench tests agents' ability to build playable games in a game engine

Arxiv CS.CL (NLP/language models)

New benchmark evaluates coding agents on transforming natural-language specs into playable games within a game engine. It includes tasks across multiple genres and measures playability and completeness.

gamecraft-bench

See 1 more source

GameCraft-Bench: Can Agents Build Playable Games End-to-End in a Real Game Engine?4 days agopmttyjiDiscuss

Arxiv CS.CL (NLP/language models)·Tongxu LuoRongsheng WangJiaxi BiChenming XuZhengyang TangJianlong ChenJuhao LiangKe JiShuqi GuoYuhao DuFan BuWenyu DuXiaotong ZhangKyle LiShaobo WangLinfeng ZhangYuxuan LiuXin LaiChenxin LiYiduo GuoZhexin ZhangXiny

Jun 17, 4:00 AM