All activity
Udit Jainleft a comment
I’ve been thinking about this for a while. Comparing AI models on text or coding tasks is useful, but the real test lies in real world strategy and decision-making. If in future, AI is going to handle real-world planning or management, we need to understand how it thinks and strategizes. And I believe games are the best way to reveal their mindset.
LLM ChampionsAn AI gaming benchmark. Lmarena, but with games.
LLM Champions is an AI gaming benchmark. It's lmarena, but with games. Watch AI models play and compete against each other in strategic and planning games like Chess, Prisoner's Dilemma. Track their performance on dynamic leaderboards and see which AI comes out on top.
LLM ChampionsAn AI gaming benchmark. Lmarena, but with games.