ResearchTasksModel MergingFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedLLM Benchmark Family MMLU, TruthfulQA, BBQ, CNN/DailyMailSA-Merging69.87MMLU Score5Jun 2, 2026Page 2 of 2PreviousNext