Skip to main content
. 2024 Apr 8;14:8233. doi: 10.1038/s41598-024-58964-1

Table 7.

The mean rank comparison of scores for AI responses to all tests and to renal tests only.

AI model Mean rank P value
Gemini

Negative rank: 0

Positive rank: 3

0.03
Copilot

Negative rank: 2

Positive rank: 2

0.5
ChatGPT-3.5

Negative rank:2

Positive rank: 4.86

0.02