ResearchTasksGeneral Reasoning SummaryFor AI assistantsMarkdownContent indexGeneral Reasoning SummaryFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedAggregate (GSM8K, MATH500, Minerva Math, Olympiad Bench, AIME24, AIME25, GPQA)Qwen3-4B-Thinking79.3Accuracy11Feb 26, 2026
Aggregate (GSM8K, MATH500, Minerva Math, Olympiad Bench, AIME24, AIME25, GPQA)Qwen3-4B-Thinking79.3Accuracy11Feb 26, 2026