ResearchDatasetsHLE-VLFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsMultimodal Deep SearchHLE-VL19Accuracy (HLE-VL)18Multimodal long-horizon complex reasoningHLE-VL25.1Score13Multimodal SearchHLE-VL36Score8Vision Agent CapacityHLE-VL39.2Score6Visual SearchHLE-VL36Pass@14