As for poker, Google DeepMind selected heads-up no-limit Texas Keep’em as its benchmark for this experiment. Game Arena is working to be a heads-up poker tournament amongst primary AI versions, with results feeding into a general public leaderboard. Google DeepMind is expanding its Game Arena System to benchmark AI models https://fernandouoaoa.ampedpages.com/getting-my-game-arena-to-work-66889236