MMLU

CAIS / Dan Hendrycks
View on Hugging Face
TextMITpublicTrusted116K rows

57-subject multiple-choice benchmark — the de-facto exam for LLM knowledge.

57-subject multiple-choice benchmark — the de-facto exam for LLM knowledge.

At a glance

  • Modality: Text
  • Use case: Evaluation
  • Rows: 116K
  • License: MIT (commercial use OK)
  • Format: parquet