ResearchTasksChain-of-Thought GenerationChain-of-Thought GenerationFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedMATHMSV68.3Latency (s)6Mar 5, 2026ANLI (test)Gold4.01GPT-4 Score6Feb 26, 2026e-SNLI (test)Gold3.49GPT-4 Score6Feb 26, 2026CQA (test)Gold4.11GPT-4 Score6Feb 26, 2026SVAMP (test)Gold4.63GPT-4 Score6Feb 26, 2026