ResearchDatasetsMixed PromptsFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsReasoning Token InductionMixed Prompts (SimpleQA, SimpleBench, AIME2024, etc.) (test)24,701Mean Completion Tokens31
Reasoning Token InductionMixed Prompts (SimpleQA, SimpleBench, AIME2024, etc.) (test)24,701Mean Completion Tokens31