Fig. 2 | Scientific Reports

Fig. 2

From: Performance evaluation of generative pre-trained transformer on the National Veterinary Licensing Examination in Japan

Fig. 2

The model comparison tests. (A) The Normal solving prompt used in the model comparison tests. (B) Scores achieved by each model on the 74th NVLE in Japan. The yellow shading indicates the minimum passing scoring rate for each section (70% for the essential section and 60% for the other sections). Values are expressed as mean ± SD of triplicate samples. Statistical significance across three related groups was assessed using Cochran’s Q test, and pairwise comparisons were performed using McNemar’s test with Bonferroni correction. *p < 0.05, **p < 0.01. (C) Overall average score for each model and percentage of correct answers, out of 330 questions.

Back to article page