ResearchTasksTask #2Task #2FollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedSTARKGRPO94.88Accuracy6Apr 30, 2026Multi-Fashion (test)——Primary metric0Feb 26, 2026Multi-MNIST (test)——Primary metric0Feb 26, 2026Multi-Fashion+MNIST (test)——Primary metric0Feb 26, 2026