As for poker, Google DeepMind selected heads-up no-Restrict Texas Hold’em as its benchmark for this experiment. Game Arena is operating like a heads-up poker tournament in between top AI models, with success feeding into a general public leaderboard. Google DeepMind is increasing its Game Arena System to benchmark AI versions https://gamearena41505.dm-blog.com/40098880/getting-my-game-arena-to-work