MMMLU · Swahili
Full rankings
2 models tested · sorted by score
| # | Model | Score |
|---|---|---|
| 1 | 37.5 | |
| 2 | 34.3 |
Score distribution
Where models cluster
Correlated benchmarks
Pearson r · original research
Frequently asked
About MMMLU · Swahili
What does MMMLU · Swahili measure?
MMMLU · Swahili is a knowledge benchmark in the BenchGecko catalog. 2 AI models have been tested on it. Scores range from 34.3 to 37.5 out of 100.
Which model leads on MMMLU · Swahili?
Meta Llama 3 8B Instruct from Meta leads MMMLU · Swahili with a score of 37.5. The median score across 2 tested models is 35.9.
Is MMMLU · Swahili saturated?
No · the top score is 37.5 out of 100 (38%). There is still meaningful room for improvement on MMMLU · Swahili.
What makes MMMLU · Swahili distinctive?
MMMLU · Swahili 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 · Swahili data refreshed?
BenchGecko pulls updates daily. New model scores on MMMLU · Swahili 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