As for poker, Google DeepMind selected heads-up no-Restrict Texas Maintain’em as its benchmark for this experiment. Game Arena is managing being a heads-up poker tournament between primary AI models, with success feeding into a general public leaderboard. Google DeepMind is expanding its Game Arena platform to benchmark AI models in https://game-arena26048.theisblog.com/40432150/an-unbiased-view-of-game-arena