ResearchTasksGeneral Knowledge AssessmentGeneral Knowledge AssessmentFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedC-EvalKimi-K2 Base92.5Accuracy46Apr 6, 2026MMLUAlignment Gating (Gating Inversion)79.8Sycophancy Accuracy (Medicine)2Jun 9, 2026