Benchmarking Large Language Models for ABAP Code Generation (BLLM_ABAP)

Projektleitung

Projektwebseite

https://blogs.gm.fh-koeln.de/westenberger/research/projects/

The project will investigate how to build a robust benchmark platform for algorithmic research on ABAP code generation. It aims to automate the evaluation process so that the performance of different coding agents can be compared with minimal effort.

Download
RDF/XML-Format
JSON-LD-Format
Turtle-Format
N3-Format

The project will investigate how to build a robust benchmark platform for algorithmic research on ABAP code generation. It aims to automate the evaluation process so that the performance of different coding agents can be compared with minimal effort.

Download
RDF/XML-Format
JSON-LD-Format
Turtle-Format
N3-Format