ResearchDatasetsAverage across benchmarksFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsLLM RoutingAverage across Benchmarks (val)83Avg Top-1 Acc14Tool CallingAverage across 5 benchmarks88.47F1 (Name)9Surface Normal EstimationAverage across benchmarks1.58Average Rank8