ResearchTasksLanguage AdherenceLanguage AdherenceFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedGSM8K (cross)SFT99.72RPR5Apr 30, 2026MMMLU (target)TLPO99.49RPR5Apr 30, 2026MIF (target)SFT99.54RPR5Apr 30, 2026LCB monolingualSFT99.9RPR5Apr 30, 2026LCB cross-lingualTLPO97.68RPR5Apr 30, 2026