Sign in to view source links and access this dataset
Description
A benchmark suite of Java applications across Jakarta EE, Quarkus, and Spring frameworks for evaluating AI agents' ability to migrate enterprise applications. The dataset was created by ibm-research and was last updated on March 25, 2026. It is designed to assess the preservation of functionality, idiomatic patterns, and architectural integrity during framework transformation.
Use Cases
Benchmarking AI agents' performance on cross-framework Java application migration based on the described suite.
Training AI models for code transformation tasks using the included enterprise application examples.
Systematically assessing the preservation of idiomatic patterns and architectural integrity during automated refactoring.
Comparing the migration capabilities of different AI agents across the Jakarta EE, Quarkus, and Spring frameworks.
Strengths
Benchmark includes applications across three major Java frameworks: Jakarta EE, Quarkus, and Spring.
Explicitly designed for systematic assessment of AI agent performance on a specific task.
Created by a named research organization (ibm-research).
Limitations
Column-level documentation is absent; field semantics must be inferred after download.
Row count and dataset size are unknown, which may limit suitability assessment.
Description metadata is limited; actual data quality requires manual inspection after download.
Provenance
Source
ibm-research
Collection Method
Likely created as a curated benchmark suite for research purposes.
Freshness
Last updated 2026-03-25 21:31:08; freshness should be verified.
License is unknown; terms of use must be verified before application.