Welcome to ML Square Garden, here in Neural York for the inaugural March Model Madness!

This annual spectacle brings 16 of the top Foundational Models (FM) and Large Language Models (LLM) together in a clash of computational capabilities. In a grand tournament format these giants of GenAI will compete across four categories: Chat, Instruct, Code, and Image Creation.

To add some extra spice, this is a blind contest; the winning model proceeds to the next round, while the defeated model is revealed.

To make this monumental model match-up magnificent, we need your involvement over two stages:

• Pre-game prep – before we even tip-off, help us craft challenging prompts for the models by submitting your own and upvoting the ones you believe will push their capabilities to the buzzer.
• Game-time – we’re underway in the 2024 tournament. For each matchup, you pick which response is best: was it an air-ball or a slam dunk? Vote now on the best responses to ensure your preferred models advance to the next round.