MMMLU
Distribution
Where models cluster
Correlated benchmarks
Pearson r · original research
Full rankings
1 models tested · sorted by score
| # | Model | Score |
|---|---|---|
| 1 |  Claude Mythos Preview | 92.7 |
Frequently asked
Pulled from the MMMLU dataset · updated daily
What does MMMLU measure?
MMMLU is a knowledge benchmark in the BenchGecko catalog. 1 AI models have been tested on it. Scores range from 92.7 to 92.7 out of 100.
Which model leads on MMMLU?
Claude Mythos Preview from Anthropic leads MMMLU with a score of 92.7. The median score across 1 tested models is 92.7.
Is MMMLU saturated?
No · the top score is 92.7 out of 100 (93%). There is still meaningful room for improvement on MMMLU.
What makes MMMLU distinctive?
MMMLU 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 data refreshed?
BenchGecko pulls updates daily. New model scores on MMMLU appear as soon as they are published by Epoch AI or the model provider.
Top on MMMLU
Claude Mythos Preview · 92.7Compare models
Claude Mythos Preview vs Claude Mythos PreviewMore knowledge benchmarks
Same category · related evaluations