# KMMLU-Hard leaderboard

korean benchmark

> Every figure below is reproduced as its upstream source published it: nothing is modelled, estimated, interpolated or converted. `Unavailable` means no source published the value — it is never a zero. Each value carries its evidence state and the date it was observed.

Page: https://modelchoice.dev/leaderboards/benchmarks/korean-kmmlu-hard

Every model the catalog carries a published KMMLU-Hard value for, ranked by that value.

## Benchmark record

| Field | Value |
| --- | --- |
| Category | korean |
| Measure | Multiple choice questions |
| Tasks | ~5,000 questions |
| Difficulty | Advanced Korean reasoning |
| Published by | [Evaluating LLMs on Hard Korean Queries](https://github.com/daekeun-ml/evaluate-llm-on-korean-dataset) |

A filtered hard subset of KMMLU containing ~5,000 questions that most models get wrong.

## KMMLU-Hard ranking

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.

Rows are ordered by the value the source published, highest first. The source does not state whether a higher value is the better result, so this document does not either: for a benchmark that measures a rate of failure, read the table from the bottom.
