arazu · Opus 5 run 1
57.1Run score
Pass rate82.4%
Simplicity79.6
Problems $$53.58
Opus 5 uses the real production library (rapier).
ImplementerPass rateSimplicityCostScore
Opus 5 · mini-SWE82.4%79.6$53.58
ProblemOpus 5
Click a problem to see how each solution's score is built.