ResearchTasksInstruction-Tuning Performance EvaluationInstruction-Tuning Performance EvaluationFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedLeaderboard BBH, GPQA, IFEval, Math, MMLU-Pro, MUSRTaskPGM (PMI)52.17BBH Score12Jun 5, 2026