Common · Knowledge
MMLU
Language understanding across multiple domains
Measuring Massive Multitask Language Understanding (MMLU) is a popular benchmark for evaluating the capabilities of large language models. It inspired several other versions and spin-offs, such as MMLU-Pro, MMMLU and MMLU-Redux.
From Wikipedia
Measuring Massive Multitask Language Understanding (MMLU) is a popular benchmark for evaluating the capabilities of large language models. It inspired several other versions and spin-offs, such as MMLU-Pro, MMMLU and MMLU-Redux.
Text: Wikipédia, CC BY-SA 4.0. ·
Related cards
-
★
LLM-as-a-Judge
Use of large language models as automated evaluators
-
L★
Language model benchmark
Wikimedia list article
-
P★★★
PLLuM
Family of open large language models
-
★
Multiple languages
Characteristic of material that includes more than one language
-
★★★
Unified Modeling Language
Software system design modeling tool
-
L★★★★★
Large language model
Language model built with very large amounts of texts