As for poker, Google DeepMind decided on heads-up no-limit Texas Keep’em as its benchmark for this experiment. Game Arena is jogging as a heads-up poker tournament amongst main AI models, with final results feeding into a community leaderboard. Google DeepMind is increasing its Game Arena platform to benchmark AI types https://tituszfeen.tribunablog.com/the-smart-trick-of-game-arena-that-nobody-is-discussing-54520625