MMMLU · Arabic
Distribution
Where models cluster
Correlated benchmarks
Pearson r · original research
Full rankings
2 models tested · sorted by score
| # | Model | Score |
|---|---|---|
| 1 |  Qwen2 7B Instruct | 50.7 |
| 2 |  Meta Llama 3 8B Instruct | 40.5 |
Frequently asked
Pulled from the MMMLU · Arabic dataset · updated daily
What does MMMLU · Arabic measure?
MMMLU · Arabic is a knowledge benchmark in the BenchGecko catalog. 2 AI models have been tested on it. Scores range from 40.5 to 50.7 out of 100.
Which model leads on MMMLU · Arabic?
Qwen2 7B Instruct from Alibaba leads MMMLU · Arabic with a score of 50.7. The median score across 2 tested models is 45.6.
Is MMMLU · Arabic saturated?
No · the top score is 50.7 out of 100 (51%). There is still meaningful room for improvement on MMMLU · Arabic.
What makes MMMLU · Arabic distinctive?
MMMLU · Arabic 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 · Arabic data refreshed?
BenchGecko pulls updates daily. New model scores on MMMLU · Arabic appear as soon as they are published by Epoch AI or the model provider.
More knowledge benchmarks
Same category · related evaluations