MMLU: Machine Learning

Accuracy on MMLU's machine learning questions, one of 57 subject tests of academic and professional knowledge.

Also known as: machine_learning

unassessed

What it measures

Core machine-learning concepts at an introductory-course level: supervised and unsupervised learning, model evaluation, overfitting, and common algorithms. Framed as four-option multiple-choice questions and scored zero-shot or few-shot by exact match against the labelled option, as one of the 57 subject subsets that make up the MMLU benchmark.

Task format

Four-option multiple-choice question answering (A-D), one correct answer, zero-shot or few-shot.

Models reporting this benchmark

Data

This page as JSON · Edit on GitHub