MMMLU · Korean
Full rankings
2 models tested · sorted by score
| # | Model | Score |
|---|---|---|
| 1 | 54.0 | |
| 2 | 46.5 |
Score distribution
Where models cluster
Correlated benchmarks
Pearson r · original research
Frequently asked
About MMMLU · Korean
What does MMMLU · Korean measure?
MMMLU · Korean is a knowledge benchmark in the BenchGecko catalog. 2 AI models have been tested on it. Scores range from 46.5 to 54.0 out of 100.
Which model leads on MMMLU · Korean?
Qwen2 7B Instruct from Alibaba leads MMMLU · Korean with a score of 54.0. The median score across 2 tested models is 50.3.
Is MMMLU · Korean saturated?
No · the top score is 54.0 out of 100 (54%). There is still meaningful room for improvement on MMMLU · Korean.
What makes MMMLU · Korean distinctive?
MMMLU · Korean is a knowledge benchmark with limited overlap to the rest of the catalog · it measures capabilities that are not well-covered by other benchmarks we track.
How often is MMMLU · Korean data refreshed?
BenchGecko pulls updates daily. New model scores on MMMLU · Korean appear as soon as they are published by Epoch AI or the model provider.
- Category
- Knowledge
- Max score
- 100
- Models
- 2
- Updated
- 2024-06-04
More knowledge benchmarks
Same category · related evaluations