ScarfBench: Cross-Framework Application Migration in Enterprise Java

IBM Research's benchmark for coding agents that migrate complete enterprise Java applications between Jakarta EE, Quarkus and Spring while keeping them working.

ModelsModels with a result.11
Top resultBest result on this benchmark.75.2%Gemini 4 Argon
Top-3 spreadPoints from first to third.5.4 pts
YearYear of release.2026

Result and price

9 of 11 results

Results

11 results
#ModelResultThe score from the source.
09Kimi K361.3%