ResearchTasksFactual Knowledge Question AnsweringFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedTruthfulQADeepSeek-V383.3Accuracy7Apr 7, 2026MMLU-ProLlama4-Maverick80Accuracy (Acc)7Apr 7, 2026MMLUDeepSeek-V383.3Accuracy7Apr 7, 2026