ResearchDatasetsSO-BenchFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsComplex Reasoning and SemanticsSO-Bench45.16CM Score16Spatial Relation UnderstandingSO-Bench64.26IS-DoA16Basic Detection and EstimationSO-Bench53.97DS Score16