ResearchTasksGeneral LLM accelerationGeneral LLM accelerationFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedLongBench, InfiniteBench, RULER, AIME, MATH500 AveragePRR1.56Average Decoding Speedup12Jun 30, 2026