ResearchTasksSkill LearningFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedMedical and Previous Task Suite (Hellaswag, Humaneval, IFeval, MMLU, TruthfulQA, Winogrande)SDFT40.2Medical Score5Feb 27, 2026Tooluse and Previous Task Suite (Hellaswag, Humaneval, IFeval, MMLU, TruthfulQA, Winogrande)SDFT70.6Tooluse5Feb 27, 2026Science Q&A and Previous Task Suite (Hellaswag, Humaneval, IFeval, MMLU, TruthfulQA, Winogrande)SDFT70.2ScienceQA5Feb 27, 2026
Medical and Previous Task Suite (Hellaswag, Humaneval, IFeval, MMLU, TruthfulQA, Winogrande)SDFT40.2Medical Score5Feb 27, 2026
Tooluse and Previous Task Suite (Hellaswag, Humaneval, IFeval, MMLU, TruthfulQA, Winogrande)SDFT70.6Tooluse5Feb 27, 2026
Science Q&A and Previous Task Suite (Hellaswag, Humaneval, IFeval, MMLU, TruthfulQA, Winogrande)SDFT70.2ScienceQA5Feb 27, 2026