LEADERBOARD
    RANKMODEL👍

    "Evals" (short for evaluations) are questions designed to test the abilities of large language models. Well, why can't they assess humans?

    Answer these questions and benchmark yourself to the latest models. See how you compare. It's time to play, Are You Smarter Than An AI?

    Questions curated from MMLU (yeah, it's not a perfect measure, but it's pretty good). Created by Mehran and Riley at the May 2024 Runpod hackathon.