Benchmarking LLM decision support in inflammatory aneurysms: DeepSeek-R1, DeepSeek-V3 and ChatGPT-4o.

Clin Exp Med · 2026 · PMC13199189 · PMID 41931161

Europe PMC DOI

hedged sentence

0.0520

closest p · 1.0× alpha

0.0520

boldest claim

The sentences

reached borderline significancep = 0.052so close (0.05 < p ≤ 0.1)

Across practice sub‐domains, differences were modest and directionally consistent (R1 ≥ 4o > V3); the Diagnostics sub‐domain reached borderline significance driven by V3’s lower scores (F(2,12) = 3.82, p = 0.052; Tukey R1 vs.

also in 370 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.