ResearchDatasetsTask 3FollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsDisease PredictionTask 3 Crohn's Disease (test)100AUROC10Report writingTask 3 Cross-domain8.23LLM-as-Judge Score5Report writingTask 3 Single-domain8.31LLM-as-Judge Score5Topology OptimizationTask 3 Boundary Conditions144.96Minimum Compliance3