SWE-bench Multimodal
Score distribution
Where models cluster
Correlated benchmarks
Pearson r · original research
Frequently asked
About SWE-bench Multimodal
What does SWE-bench Multimodal measure?
SWE-bench Multimodal is a knowledge benchmark in the BenchGecko catalog. 1 AI models have been tested on it. Scores range from 59.0 to 59.0 out of 100.
Which model leads on SWE-bench Multimodal?
Claude Mythos Preview from Anthropic leads SWE-bench Multimodal with a score of 59.0. The median score across 1 tested models is 59.0.
Is SWE-bench Multimodal saturated?
No · the top score is 59.0 out of 100 (59%). There is still meaningful room for improvement on SWE-bench Multimodal.
What makes SWE-bench Multimodal distinctive?
SWE-bench Multimodal 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 Multimodal data refreshed?
BenchGecko pulls updates daily. New model scores on SWE-bench Multimodal appear as soon as they are published by Epoch AI or the model provider.
- Category
- Knowledge
- Max score
- 100
- Models
- 1
- Updated
- 2026-04-07
Top on SWE-bench Multimodal
Claude Mythos Preview · 59.0Related topics
Knowledge categoryAll benchmarksModel leaderboardCompare matrixPricingMethodologyDevelopersCompare models
Claude Mythos Preview vs Claude Mythos PreviewMore knowledge benchmarks
Same category · related evaluations