Skip to main content

Table 3 Evaluation of the accuracy of AI models performance in medical sciences by department and field

From: The role of artificial intelligence in medical education: an evaluation of Large Language Models (LLMs) on the Turkish Medical Specialty Training Entrance Exam

Department/Field

#number Questions

#total ChatGPT 4 Correct

#total Llama 3 70B Correct

#total Gemini 1.5 Pro Correct

#total Command R + Correct

Basic Medical Sciences

 Pharmacology

22

19

18

17

13

 Pathology

22

18

18

16

7

 Biochemistry

22

20

13

16

11

 Microbiology

22

19

17

15

10

 Anatomy

14

10

8

9

4

 Physiology

10

10

8

8

6

 Histology and Embryology

8

7

6

8

5

Clinical Medical Sciences

 Pediatrics

30

27

26

24

13

 Internal Medicine

29

26

23

25

15

 General Surgery

24

22

20

19

12

 Gynecology

12

12

9

10

4

 Anesthesiology and Reanimation

3

3

3

2

3

 Emergency Medicine

3

3

3

3

3

 Neurology

3

3

3

3

3

 Dermatology

2

2

2

2

2

 Psychiatry

2

2

2

1

1

 Radiology

2

1

2

1

2

 Ear, Nose & Throat

1

1

1

1

0

 Brain Surgery

1

0

0

0

1

 Plastic Surgery

1

1

1

1

0

 PTR

1

1

1

1

1

 Ophthalmology

1

1

1

0

0

 Thoracic Surgery

1

1

1

1

1

 Orthopedics

1

1

1

1

0

 Urology

1

1

1

1

1

 Pediatric Surgery

1

1

1

1

1

 Cardiovascular Surgery

1

1

1

1

1

Total

240

213

190

187

120