Skip to main content

Table 6 Performance of large language models’ by topic

From: Artificial intelligence performance in answering multiple-choice oral pathology questions: a comparative analysis

 

Gemini 1.5

Gemini2

Copilot

Deepseek

Claude

ChatGPT 4o

ChatGPT 4

ChatGPT o1

p*

Topics

C       I

C       I

C        I

C         I

C       I

C        I

C        I

C         I

 

Odontogenic and Developmental Jaw Cysts

13     3

14      2

11       5

10      6

14      2

14       2

9         7

15        1

0.087

Odontogenic Tumors

11      6

12     5

9         8

15      2

14      3

11      6

12       5

17      0

0.052

Mucosal and Tongue Diseases

27     3

26    4

19      11

28      2

28     2

26       4

21     9

30      0

0.000

Salivary Gland, Bone Disease Pathology

20     0

18    2

15      5

17      3

18     2

16     4

15      5

19       1

0.194

Infectious Diseases Affecting the Oral and Perioral Tissues and Environmental Injuries

10     7

12    5

7      10

12     5

10     7

12     5

12     5

15       2

0.197

  1. *Pearson Chi Square, The statistical significance level was set at P ≤ 0.05, C: Correct, I:Incorrect