Skip to main content

Table 2 The concordance of answers to the test items across prompts

From: Assessment of the capacity of ChatGPT as a self-learning tool in medical pharmacology: a study using MCQs

Answers across prompts

The number of test items

%

Concordance

 All correct

49

62.8

 All incorrect

11

14.1

Discordancea

 Partially correct

18

23.1

Total

78

100.0

  1. aDiscordant responses are inconsistent or conflicting set of answers to the same test item for repeated inquiries with different prompts
Back to article page

BMC Medical Education

ISSN: 1472-6920

Contact us