pyda

PythonData-analysis library21 problemsView on GitHub ↗
DesignEvaluation
No libraryProduction libraryBest library
0255075100
No libProdBest
All problems
Opus 5.5 · mini-SWE · 59.5
51.458.359.5

Scores average every run and implementer. Hover a dot to see whose library it is; click a problem to see each implementer. ± is std across runs.