ResearchTasksSimulation deck generationFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedGEOS v1 (val)X+M92.1TreeSim11Jun 9, 2026GEOS v1 (held-out-eval)Self-Evolve78.9TreeSim Score6Jun 9, 2026