Evaluating GPT-4o in high-stakes medical assessments: performance and error analysis on a Chilean anesthesiology exam.

BMC Med Educ · 2025 · PMC12560382 · PMID 41146119

Europe PMC DOI

hedged sentence

0.0521

closest p · 1.0× alpha

0.0521

boldest claim

The sentences

did not reach statistical significancep = 0.0521so close (0.05 < p ≤ 0.1)

Although reasonable responses —defined as plausible but ultimately incorrect answers—showed a pattern of higher occurrence within the Application domain (χ2 = 11.98, p = 0.0074), this difference did not reach statistical significance after correction for multiple comparisons (corrected p = 0.0521), despite showing a medium effect size (Cramér’s V = 0.316).

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.