ResearchTasksReasoning Token InductionFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedMixed Prompts (SimpleQA, SimpleBench, AIME2024, etc.) (test)ReasoningBomb24,701Mean Completion Tokens31Feb 26, 2026
Mixed Prompts (SimpleQA, SimpleBench, AIME2024, etc.) (test)ReasoningBomb24,701Mean Completion Tokens31Feb 26, 2026