Skip to main content
. 2024 Jul 12;14:1386718. doi: 10.3389/fonc.2024.1386718

Table 3.

Statistical results of AI-generated responses.

Accuracy Conciseness Readability
ChatGPT-4 Bard ChatGPT-4 Bard ChatGPT-4 Bard
Median 3 3 3 3 3 3
Mean 2.95 2.73 3.14 3.11 2.79 2.94
SD 0.671 0.732 0.659 0.679 0.408 0.243
Mean Rank 104.06 88.94 97.42 95.58 89.50 103.50
Sum of Rank 9990.0 8538.0 9352.0 9176.0 8592.0 9936.0
Mann Whitney U 3882.0 4520.0 3936.0
p value 0.27 0.798 0.003

SD, Standard Deviation.