Table 2.
comparative correlation analysis of chatbot and medical student performance.
| Chatbots | Word count | Format | Type | Modality | Language |
|---|---|---|---|---|---|
| ChatGPT-5 | 0.067 (0.646) | 0.094 (0.516) | 0.306 (0.031*) | −0.082 (0.570) | −0.107 (0.460) |
| Gemini 3 | 0.078 (0.592) | 0.064 (0.660) | 0.246 (0.086) | −0.096 (0.509) | 0.101 (0.487) |
| Copilot | 0.105 (0.469) | 0.176 (0.222) | 0.345 (0.014*) | 0.239 (0.095) | 0.203 (0.157) |
| Perplexity | 0.015 (0.917) | 0.145 (0.313) | 0.309 (0.029*) | 0.100 (0.490) | 0.014 (0.921) |
| Chatbots (combined) | 0.098 (0.500) | 0.187 (0.193) | 0.470 (0.001**) | 0.060 (0.681) | 0.077 (0.594) |
*indicates significance at p < 0.05; ** indicates significance at p < 0.01.