List your company

Research

Benchmarks

Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.

309,131 benchmarksPage 2217 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
Novel View SynthesisnuScenes low-frequency setting3d vision geometry16Mar 16, 2026
Tool Planningm&magents tool use16Mar 16, 2026
Tool PlanningGTAagents tool use16Mar 16, 2026
Clusteringpageblocktabular time series16May 22, 2026
Watermark similarity restorationWatermarked ResNet-18 and EfficientNet modelsadversarial safety security16Mar 16, 2026
Time Series ForecastingMSPG CGTSF (test)tabular time series16Mar 16, 2026
Time Series ForecastingLEU CGTSF (test)tabular time series16Mar 16, 2026
Time Series ForecastingPTF CGTSF (test)tabular time series16Mar 16, 2026
Goal-reaching PlanningPushT Long-Horizon (50 steps)robotics embodied ai16Jun 23, 2026
Forgery DetectionFakeVLM and FakeShield Forgery Detection Suitescomputer vision16Mar 13, 2026
Class-incremental classificationImageNet Sub 10 taskscomputer visiontabular time series16Mar 13, 2026
Class-incremental classificationCIFAR100 10 taskscomputer visiontabular time series16Mar 13, 2026
Object DetectionCONDIS++ (augmented)computer vision16Mar 13, 2026
Virtual Try-OnDressCode Pairedimage generation editingcomputer vision16Jul 1, 2026
Machine TranslationWMT 24++nlp16Mar 13, 2026
Polyp SegmentationPolyp Segmentation Domain Dcomputer visionbio medical16Mar 13, 2026
Polyp SegmentationPolyp Segmentation Domain Ccomputer visionbio medical16Mar 13, 2026
Polyp SegmentationPolyp Segmentation Domain Bcomputer visionbio medical16Mar 13, 2026
Polyp SegmentationPolyp Segmentation Domain Acomputer visionbio medical16Mar 13, 2026
Context-aware turn-takingSPGIspeech audionlp16Mar 13, 2026
Context-aware turn-takingFriendsspeech audionlp16Mar 13, 2026
Context-aware turn-takingAMIspeech audionlp16Mar 13, 2026
Task progression failure detectionCover Object (Combined)robotics embodied ai16Mar 13, 2026
Task progression failure detectionCover Object Policy Success Rate: 3% (Out-of-Distribution)robotics embodied ai16Mar 13, 2026
Task progression failure detectionCover Object Policy Success Rate: 98% (In-Distribution)robotics embodied ai16Mar 13, 2026