ResearchTasksMulti-task model alignment and mixingMulti-task model alignment and mixingFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedMath, Chat, IF, and General QA tasks Llama-3.1-8B (test)Mod. Surgery36Math Accuracy3Feb 26, 2026