Loading…
Glossary term
Massive Multitask Language Understanding: a benchmark of multiple-choice questions across many subjects.
Massive Multitask Language Understanding is a multiple-choice benchmark spanning 57 subjects from history and law to mathematics and medicine. It tests broad knowledge.
Top models now score so high that it no longer separates them well, and some questions contain errors.
It was among the most quoted benchmarks of the early LLM era and shows how benchmarks saturate.