ResearchTasksGoal-conditioned GeneralizationFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedGSR-bench Difficult 1.0 (test)RoBoSR-8B-FT13.1Task Progress7Jun 24, 2026GSR-bench Medium 1.0 (test)RoBoSR-8B-FT29.1Task Progress7Jun 24, 2026GSR-bench Easy 1.0 (test)RoBoSR-8B-FT89.1Task Progress7Jun 24, 2026