ResearchTasksFactuality and ReasoningFactuality and ReasoningFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedMMLUSpIEL55.8MMLU Accuracy12Feb 26, 2026GPT4AllFullFT0.659HellaSwag Accuracy12Feb 26, 2026