A comparison of human, GPT-3.5, and GPT-4 performance in a university-level coding course.

Sci Rep · 2024 · PMC11458605 · PMID 39375385

Europe PMC DOI

hedged sentence

—

closest p

—

boldest claim

The sentences

a positive trendno p-value reported

This test resulted in a p -value of 0.025 and a positive trend of 0.302, statistically verifying that as we move from ‘Definitely AI’ to ‘Definitely Human’ on the scale, the proportion of human-authored submissions increases.

also in 11,005 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.