Large Language Model Evaluation in Traditional Chinese Medicine for Stroke: Quantitative Benchmarking Study.

JMIR Form Res · 2025 · PMC12741655 · PMID 41380151

Europe PMC DOI

hedged sentence

—

closest p

—

boldest claim

The sentences

showed a trendno p-value reported

The test results showed a trend completely opposite to that of the short-answer and multiple-choice questions, as GPT-4o’s performance was comprehensively superior to that of DeepSeek-R1’s performance.

also in 53,322 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.