As for poker, Google DeepMind selected heads-up no-Restrict Texas Hold’em as its benchmark for this experiment. Game Arena is functioning like a heads-up poker tournament in between primary AI models, with effects feeding into a community leaderboard. Google DeepMind is expanding its Game Arena System to benchmark AI models in https://fernandoxqepa.isblog.net/game-arena-things-to-know-before-you-buy-57200264