Performance of Large Language Models (ChatGPT and Gemini Advanced) in Gastrointestinal Pathology and Clinical Review of Applications in Gastroenterology.

Cureus · 2025 · PMC12048130 · PMID 40322390

Europe PMC DOI

hedged sentence

—

closest p

—

boldest claim

The sentences

almost reached statistical significanceno p-value reported

Diagnostic accuracy Of the 20 cases, Gemini Advanced (19/20; 95%; p=0.01) performed significantly better, and ChatGPT-4.0 (18/20; 90%; p=0.05) almost reached statistical significance compared to ChatGPT-3.5 (Table 4 ).

also in 87 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.