ResearchDatasetsIndependently ConstructedFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsScientific Method Comparative Reasoning ForecastingIndependently Constructed 2025 (test)67.49Accuracy11
Scientific Method Comparative Reasoning ForecastingIndependently Constructed 2025 (test)67.49Accuracy11