SWE-bench Multilingual
Distribution
Where models cluster
Correlated benchmarks
Pearson r · original research
Full rankings
1 models tested · sorted by score
| # | Model | Score |
|---|---|---|
| 1 |  Claude Mythos Preview | 87.3 |
Frequently asked
Pulled from the SWE-bench Multilingual dataset · updated daily
What does SWE-bench Multilingual measure?
SWE-bench Multilingual is a knowledge benchmark in the BenchGecko catalog. 1 AI models have been tested on it. Scores range from 87.3 to 87.3 out of 100.
Which model leads on SWE-bench Multilingual?
Claude Mythos Preview from Anthropic leads SWE-bench Multilingual with a score of 87.3. The median score across 1 tested models is 87.3.
Is SWE-bench Multilingual saturated?
No · the top score is 87.3 out of 100 (87%). There is still meaningful room for improvement on SWE-bench Multilingual.
What makes SWE-bench Multilingual distinctive?
SWE-bench Multilingual 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 SWE-bench Multilingual data refreshed?
BenchGecko pulls updates daily. New model scores on SWE-bench Multilingual appear as soon as they are published by Epoch AI or the model provider.
Top on SWE-bench Multilingual
Claude Mythos Preview · 87.3Compare models
Claude Mythos Preview vs Claude Mythos PreviewMore knowledge benchmarks
Same category · related evaluations