Search Articles

View query in Help articles search

Search Results (1 to 1 of 1 Results)

Download search results: CSV END BibTex RIS


Performance of GPT-3.5 and GPT-4 on the Korean Pharmacist Licensing Examination: Comparison Study

Performance of GPT-3.5 and GPT-4 on the Korean Pharmacist Licensing Examination: Comparison Study

In the 2021 KPLE, 320 (91.4%) of the 350 questions were suitable for analysis in both GPT-3.5 and GPT-4, excluding 30 image-based questions. Of these, GPT-3.5 correctly answered 200 questions, resulting in an accuracy rate of 62.5%. In contrast, GPT-4 answered 275 questions correctly, achieving an accuracy rate of 85.9%. Table 1 presents the detailed scores for each unit of the 2021 KPLE.

Hye Kyung Jin, EunYoung Kim

JMIR Med Educ 2024;10:e57451