Dataset

MMLU Benchmark

The MMLU (Massive Multitask Language Understanding) benchmark is a prominent example of how complex reasoning tasks are structured in a question-answering format. Each problem within this benchmark is presented as a multiple-choice question, requiring a Large Language Model to choose the single correct answer from a list of options.

0

1

Updated 2026-09-07

Contributors are:

Who are from:

Tags

Ch.3 Prompting - Foundations of Large Language Models

Foundations of Large Language Models

Computing Sciences

Foundations of Large Language Models Course

Prep Sessions

Transformer Architecture and Large Language Model Capabilities @ University of Michigan - Ann Arbor

Ch.2 Model Scaling and Capability Evaluation - Transformer Architecture and Large Language Model Capabilities @ University of Michigan - Ann Arbor

Multilingual Language Understanding on MMLU - Transformer Architecture and Large Language Model Capabilities @ University of Michigan - Ann Arbor

Ch.3 Model Alignment and Safety - Transformer Architecture and Large Language Model Capabilities @ University of Michigan - Ann Arbor

Model Calibration and Confidence Degradation - Transformer Architecture and Large Language Model Capabilities @ University of Michigan - Ann Arbor