Benchmark profile
KMMLU-Redux
Cleaned KMMLU from national technical qualification exams, with errors removed, decontaminated, and deduplicated.
Data verifiedAbout KMMLU-Redux
Tasks
~3,500 questions
Format
Technical multiple choice
Difficulty
Industrial/technical
BenchLM freshness & provenance
Version
KMMLU-Redux
Refresh cadence
Static
Staleness state
Refreshing
Question availability
Public benchmark set
BenchLM uses freshness metadata to decide whether a benchmark should still be treated as a strong differentiator, a benchmark to watch, or a display-only reference. For the full scoring policy, see the BenchLM methodology page.
FAQ
What does KMMLU-Redux measure?
Cleaned KMMLU from national technical qualification exams, with errors removed, decontaminated, and deduplicated.
Which model scores highest on KMMLU-Redux?
No models have been evaluated on KMMLU-Redux yet.
How many models are evaluated on KMMLU-Redux?
0 AI models have been evaluated on KMMLU-Redux on BenchLM.
Choose a model with this week’s evidence
Join 2,000+ readers for ranking moves, pricing changes, and the claims that still need proof.
One email each week. Unsubscribe anytime.