Table 4 Clock time taken in seconds for each LLM for each assessment

From: Results and implications for generative AI in a large introductory biomedical and health informatics course

Assessment

ChatGPT Plus (GPT-4)

Claude 3 Opus

CoPilot with Bing-Precise

Gemini Pro

Llama 3.1 405B

Mistral-Large

Unit 1

39

25

24

31

14

15

Unit 2

51

41

25

23

23

16

Unit 3

39

31

14

24

37

11

Unit 4

70

38

19

21

18

12

Unit 5

57

34

18

19

14

11

Unit 6

61

36

22

21

15

13

Unit 7

77

35

20

22

13

15

Unit 8

55

36

23

25

23

14

Unit 9

100

44

26

21

15

17

Unit 10

43

43

25

21

16

29

Final Exam

73

49

80

25

20

38

Total

665

412

296

253

208

191

Back to article page