Table 3.

Overview of output performance

VariableVariantCorrect outcome in (%)
GPT modelChatGPT 3.526.3
ChatGPT 4.046.3
ChatGPT 4o52.5
ChatGPT o1 preview65.0
ChatGPT 4o mini28.8
ChatGPT o1 mini25.0
Task category*Task A: Requesting specific legal references48.8
Task B: Identification of legal references in context47.5
Task C: Case-based calculation28.8
Task D: Case-based decision making65.0
Prompting techniqure*Zero-shot prompt45.0
Few-shot prompt50.0
Accounting standard*Local GAAP (Austrian GAAP)34.4
International financial reporting standards (IFRS)60.6
Note(s):

*Results without “mini”-variants

Source(s): Authors’ own work

or Create an Account

Close Modal
Close Modal