. 2024 Apr 3;48(1):38. doi: 10.1007/s10916-024-02056-0

Table 2.

Comparison of the FKRE, FKGL, EQIP, and DISCERN scores of the five different AI chatbots

	ChatGPT	Bing	Bard	Ernie Bot	Copilot	p value
Flesch Kincaid Reading Ease Minimum Maximum Mean ± SD	10.1 40.5 23.1 ± 7.8	25.1 61.9 39.1 ± 9.3	14.6 103 53.9 ± 21.5	25.7 55.2 37.5 ± 9.0	25.2 52.5 41.1 ± 10.1	0.001^a
Flesch Kincaid Grade Level Minimum Maximum Mean ± SD	11.6 18.2 14.3 ± 1.7	7.9 16 12.5 ± 1.8	1.9 15.2 9.6 ± 3.3	9.8 15.8 12.9 ± 1.7	10.4 15.3 12.5 ± 1.9	0.001^b
EQIP Score Minimum Maximum Mean ± SD	30.0 45.0 40 ± 4.2	35.0 45.0 39.5 ± 3.1	0 69.0 32.1 ± 30.4	0 72.2 53.1 ± 20.6	41.7 80.0 63.5 ± 12.7	0.001^c
DISCERN Minimum Maximum Mean ± SD	28.0 42.0 33.5 ± 4.8	28.0 42.0 33.3 ± 4.0	16.0 55.0 33.7 ± 16.7	16.0 44.0 32.7 ± 7.7	40.0 73.0 55.0 ± 10.6	0.001^d

ChatGPT

Bing

Bard

Ernie Bot

Copilot

p value

Flesch Kincaid Reading Ease

Minimum

Maximum

Mean ± SD

10.1

40.5

23.1 ± 7.8

25.1

61.9

39.1 ± 9.3

14.6

103

53.9 ± 21.5

25.7

55.2

37.5 ± 9.0

25.2

52.5

41.1 ± 10.1

0.001^a

Flesch Kincaid Grade Level

Minimum

Maximum

Mean ± SD

11.6

18.2

14.3 ± 1.7

7.9

12.5 ± 1.8

1.9

15.2

9.6 ± 3.3

9.8

15.8

12.9 ± 1.7

10.4

15.3

12.5 ± 1.9

0.001^b

EQIP Score

Minimum

Maximum

Mean ± SD

30.0

45.0

40 ± 4.2

35.0

45.0

39.5 ± 3.1

69.0

32.1 ± 30.4

72.2

53.1 ± 20.6

41.7

80.0

63.5 ± 12.7

0.001^c

DISCERN

Minimum

Maximum

Mean ± SD

28.0

42.0

33.5 ± 4.8

28.0

42.0

33.3 ± 4.0

16.0

55.0

33.7 ± 16.7

16.0

44.0

32.7 ± 7.7

40.0

73.0

55.0 ± 10.6

0.001^d

^aDifference between ChatGPT and others

^bDifference between Bard and others

^cDifferences between ChatGPT and Ernie, ChatGPT and Copilot, Bing and Ernie, Bing and Copilot, and Bard and Copilot

^dDifferences between Copilot and others