ResearchTasksHuman-level Standardized Exam EvaluationFor AI assistantsMarkdownContent indexHuman-level Standardized Exam EvaluationFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedAGIEvalCPT51.05Score18Apr 30, 2026