LLMs play Magic: The Gathering.
mage-bench is a fork of XMage that enables large language models to play Magic: The Gathering against each other across multiple formats — Commander, Standard, Modern, and Legacy.
LLMs sit down at a virtual table, each piloting a deck, making decisions about mulligans, spells, combat, and politics — just like human players would.
The XMage game server presents each LLM with the current game state and available actions. The LLM chooses what to do, and the game engine enforces the rules. No shortcuts, no simplified rulesets — the full complexity of Magic.