About KMMLU-Redux
Definition and scoring
- Organisation
- BenchLM registry
- Category
- Knowledge
- Version
- Not evaluated
- Direction
- higher is better
- Ranking use
- Reference
- Contamination risk
- Unknown
Cleaned KMMLU from national technical qualification exams, with errors removed, decontaminated, and deduplicated. Results stay tied to the exact model variant and evaluation system. Multiple systems for the same model use the best published score on this page; overall Lumina scoring uses the median of ranking-eligible rows.
Open benchmark source ↗