ResearchTasksFactuality and ReasoningFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedMMLUSpIEL55.8MMLU Accuracy12Feb 26, 2026GPT4AllFullFT0.659HellaSwag Accuracy12Feb 26, 2026