korean benchmark
KMMLU-Hard leaderboard
Every model the catalog carries a published KMMLU-Hard value for, ranked by that value.
Categorykorean
MeasureMultiple choice questions
Tasks~5,000 questions
DifficultyAdvanced Korean reasoning
Published byEvaluating LLMs on Hard Korean Queries
A filtered hard subset of KMMLU containing ~5,000 questions that most models get wrong.
No model in the catalog has a published KMMLU-Hard score.
The benchmark is defined by Evaluating LLMs on Hard Korean Queries, but the catalog carries no value for it yet. An absent value is shown as absent here rather than as a zero.