ResearchTasksContext-aware Instruction FollowingContext-aware Instruction FollowingFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedContext-aware Instructions (test)GPT-4-turbo8.85Overlap (with context)18Feb 26, 2026Academic Paper Abstracts (test)GPT-4-turbo8.64Overlap (w)2Feb 26, 2026Avocado Emails (test)GPT-4-turbo8.31Overlap (with context)2Feb 26, 2026