ResearchTasksDiagnostic report generationFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedMIMIC-CXR 14 (test)CPO++16.5BLEU-427Apr 20, 2026PPGLPPGL-Swarm3.6Diagnostic Accuracy8Mar 24, 2026Human-Eval 12-language (120 items)MADE7.41Human Mean Score3Jun 8, 2026