ResearchBenchmarksPsychometric Item Evaluation on Reading Comprehension MCQ DatasetFollow0.786Mean Difficulty (p)ReQUESTA0.781360.812680.8440.87532Feb 3, 2026Evaluation ResultsMethodMethodLinksMean Difficulty (p)SD Difficulty (p)Mean Discrimination (D)SD Discrimination (D)Mean Point-Biserial Correlation (rpb)SD Point-Biserial (rpb)ReQUESTASource=ReQUESTASource=ReQUESTA2026.020.7860.1330.390.1960.3230.168GPT-5Source=GPT-5Source=GPT-52026.020.9020.1120.170.1310.2750.202