Loading page…
Preferred languages
More languages supported by Google Translate
Open the selector to load the current language catalog.
Translations are provided by Google Translate.
Loading page…
Preferred languages
More languages supported by Google Translate
Open the selector to load the current language catalog.
Translations are provided by Google Translate.
Coding benchmark
ScarfBench: Cross-Framework Application Migration in Enterprise Java. Every model the catalog carries a published ScarfBench value for, ranked by that value.
IBM Research's benchmark for coding agents that migrate complete enterprise Java applications between Jakarta EE, Quarkus and Spring while keeping them working. 11 models in the ModelScale catalog have a published value.
Each point is a model with a published ScarfBench value and complete token prices, on the 75% input / 25% output blend. Frontier models are spaced evenly along the cost axis.
11 models with a published ScarfBench value, ordered by that value, highest first. Models the source has not scored on this benchmark are not listed — they are unmeasured, not last.
| Rank | Model | Provider | Percent of smoke tests passed after migration (Kaggle) |
|---|---|---|---|
| 1 | 75.2 | ||
| 2 | Anthropic | 70.5 | |
| 3 | Anthropic | 69.8 |
What the benchmark measures and how its value is published, from the source’s own record.
ScarfBench (ScarfBench: Cross-Framework Application Migration in Enterprise Java) is a coding benchmark published by ScarfBench: A Benchmark for 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. Its evaluation set is described by the source as 204 framework migration tasks across 34 enterprise Java applications. The source rates its difficulty as whole-application framework migration.
Each model's result is published by ScarfBench: A Benchmark for Cross-Framework Application Migration in Enterprise Java as percent of smoke tests passed after migration (Kaggle). ModelScale prints that value to 1 decimal place, exactly as published, and never converts or rescales it. This page ranks the 11 models that carry a published value, highest value first; a model the source never scored is left out rather than ranked at zero. The source does not state whether a higher value is the better result, so neither does this page.
| 4 | DeepSeek | 69.0 |
| 5 | OpenAI | 68.4 |
| 6 | 66.0 |
| 7 | OpenAI | 65.4 |
| 8 | Alibaba | 63.7 |
| 9 | Moonshot AI | 61.3 |
| 10 | 37.6 |
| 11 | 24.4 |
Evidence key: Observed
Rows are ordered by the value ScarfBench: A Benchmark for Cross-Framework Application Migration in Enterprise Java published, highest first. The source does not state whether a higher value is the better result, so this page does not either: for a benchmark that measures a rate of failure, read the table from the bottom.