Skip to main content
. 2023 Aug 23;95:104770. doi: 10.1016/j.ebiom.2023.104770

Table 3.

Comprehensiveness assessment for all LLM-Chatbot responses that received ‘good’ accuracy rating.

LLM Response comprehensiveness
n Mean (SD) Median
ChatGPT-3.5 19 4.11 (0.72) 4.00
ChatGPT-4.0 25 4.23 (0.74) 4.50
Google Bard 17 4.35 (0.70) 4.50