ResearchTasksModel MergingModel MergingFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedLLM Benchmark Family MMLU, TruthfulQA, BBQ, CNN/DailyMailSA-Merging69.87MMLU Score5Jun 2, 2026PreviousPage 2 of 2Next