Skip to main content
. 2023 Nov 22;13:20512. doi: 10.1038/s41598-023-46995-z

Table 4.

Results of the correlation analysis with Pearson correlation coefficient and obtained p-value given in the brackets along with p-value obtained from the Mann–Whitney U test comparing the values of the index of difficulty for correct and incorrect answers for temperature parameter equal to 1.

S22 A22 S23
Polish
 GPT-3.5
  Pearson correlation coefficient (p-value) 0.319 (< 0.001***) 0.301 (< 0.001***) 0.174 (0.015**)
  p-value from Mann–Whitney U test  < 0.001***  < 0.001*** 0.004**
  Cohen’s d 0.671 0.634 0.362
 GPT-4
  Pearson correlation coefficient (p-value) 0.338 (< 0.001***) 0.334 (< 0.001***) 0.299 (< 0.001***)
  p-value from Mann–Whitney U test  < 0.001***  < 0.001***  < 0.001***
  Cohen’s d 0.834 0.861 0.829
English
 GPT-3.5
  Pearson correlation coefficient (p-value) 0.229 (0.001**) 0.245 (< 0.001***) 0.219 (0.002**)
  p-value from Mann–Whitney U test  < 0.001***  < 0.001*** 0.003**
  Cohen’s d 0.474 0.511 0.453
 GPT-4
  Pearson correlation coefficient (p-value) 0.363 (< 0.001***) 0.273 (< 0.001***) 0.307 (< 0.001***)
  p-value from Mann–Whitney U test  < 0.001*** 0.001**  < 0.001***
  Cohen’s d 0.933 0.714 0.802