Skip to main content
. 2025 May 28;20:531. doi: 10.1186/s13018-025-05955-1

Table 2.

ANOVA Results for Readability Metrics Across ChatGPT, Gemini, and CoPilot

Metric LLM F-Statistic P-value Significant?
Word Count ChatGPT 89.54  < 0.0001 ****
Gemini 95.87  < 0.0001 ****
CoPilot 86.89  < 0.0001 ****
Grade Level ChatGPT 36.26  < 0.0001 ****
Gemini 17.23  < 0.0001 ****
CoPilot 35.26  < 0.0001 ****
Reading Ease ChatGPT 45.38  < 0.0001 ****
Gemini 23.03  < 0.0001 ****
CoPilot 26.84  < 0.0001 ****