Performance Evaluation of GPT-5, Grok 4, and DeepSeek R1 in Interpreting Complete Blood Count Reports for Hematologic Diseases: Retrospective Comparative Study.

J Med Internet Res · 2026 · PMC13240632 · PMID 42247415

Europe PMC DOI

hedged sentence

0.9400

closest p · 18.8× alpha

0.9400

boldest claim

The sentences

did not reach statistical significanceP =.94not close (p > 0.1)

In the safety dimension, DeepSeek R1 achieved a median consensus score of 4.0 (IQR 4.0‐4.5), which was lower than that of GPT-5 (median consensus score 4.25, IQR 4.0‐4.5), although this difference did not reach statistical significance ( P =.94).

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.