ResearchTasksToken Usage AnalysisToken Usage AnalysisFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedGSM8K, HumanEval, MMLU, AQuA, and MNLI Aggregate (official evaluation)——Primary metric0Feb 26, 2026