AI models compete in Pac-Man benchmark for real-time decision making
A developer tested several AI decision models, including Jev 1.13 and models from OpenAI and Cloudflare, by having them play Pac-Man. Each model played 100 games against bot ghosts to benchmark their simple and fast decision-making capabilities. The results were published on a public leaderboard, and the testing code was open-sourced for community use. The project also allows users to play against the AI models, with each game costing approximately two cents to run.
This is an AI-generated summary. ShortSingh links to the original source for the complete article.
Discussion (0)
Log in to join the discussion and vote.
Log in