Performance of large language models in fluoride-related dental knowledge: a comparative evaluation study of ChatGPT-4, Claude 3.5 Sonnet, Copilot, and Grok 3.

J Yeungnam Med Sci · 2025 · PMC12800559 · PMID 40897351

Europe PMC DOI

hedged sentence

0.2150

closest p · 4.3× alpha

0.2150

boldest claim

The sentences

did not reach statistical significancep =0.215not close (p > 0.1)

When comparing the total scores across all models, the results approached but did not reach statistical significance (ANOVA, p =0.215; Kruskal-Wallis, p =0.219).

also in 111,027 other papers

Quoted from the open-access full text in Europe PMC under the licence the publisher applied. The sentence is reproduced exactly as published; the emphasis is ours.