ResearchBenchmarksTopic Relevance Evaluation on MCQ Quality Assessment Dataset N=200Follow3.36MeanReQUESTA1.86242.25122.643.0288Feb 3, 2026Evaluation ResultsMethodMethodLinksMeanStandard ErrorF-Statistic (df=1, 191)Eta SquaredReQUESTA2026.023.360.084.542GPT-52026.023.120.084.542ReQUESTA2026.022.280.115.593GPT-52026.021.920.115.593