Fig.1

Concept

MMLU

MMLU (Massive Multitask Language Understanding) is a benchmark that measures a model's factual and reasoning knowledge across 57 subjects, from elementary math to professional law, medicine, and moral philosophy. Every question is multiple choice with four options, so…

The rest of “MMLU” is a premium feature: every concept in the library gets a precise, practitioner-focused write-up like this one, cross-linked straight from the paper summaries that use it.

Log in to unlock

← Back to the library

MMLU, explained · Fig. 1