ResearchTasksNarrative UnderstandingFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedMC-TZephyr-7B93.3First-Token Accuracy24Apr 6, 2026HSPhi-4-14B87.8First-Token Accuracy24Apr 6, 2026SCPhi-4-14B98.7First-Token Accuracy24Apr 6, 2026