ResearchTasksFactual Knowledge EvaluationFactual Knowledge EvaluationFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedPopQACorVer35.3Accuracy56May 29, 2026DyKnow 130 time-sensitive facts Wikidata-derivedGPT-480Correctness24Mar 18, 2026Wikidata knowledge infusionPretrainRL64.69Accuracy18Feb 26, 2026Factual Evaluation Suite HHEM, PopQA, TriviaQASEAL96.22HHEM Accuracy12Apr 3, 2026WikiBenchGenius28.75WikiBench Score3Feb 26, 2026