ResearchTasksPremise GenerationPremise GenerationFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedRule Distillation Dataset LLM evaluation 1.0GPT-42.77Accuracy3Feb 26, 2026Crafted Rules Dataset (test)Engine0.411BLEU3Feb 26, 2026