Benchmark evaluation of video large language models in quality assessment of science popularization videos for dry eye.

Sci Rep · 2026 · PMC12982513 · PMID 41688579

Europe PMC DOI

hedged sentences

—

closest p

—

boldest claim

The sentences

an interesting trendno p-value reported

2 , an interesting trend emerged: VideoLLaMA’s mean scores consistently fell between those of Researcher A and Researcher B, QwenVL tended to assign higher ratings than both experts, while InternVL produced consistently lower scores.

also in 1,783 other papers

failed to achieve significanceno p-value reported

For VIQI II (information accuracy), both VideoLLaMA and InternVL presented significant agreement with both experts ( p < 0.05), whereas QwenVL again failed to achieve significance.

also in 299 other papers

did not reach statistical significanceno p-value reported

InternVL also showed statistical significance with Researcher B, while QwenVL did not reach statistical significance with either rater.

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.