List your company

Research

Benchmarks

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

309,131 benchmarksPage 1965 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
Automatic Lip-ReadingLRS3 v1 (dev)speech audiocomputer vision18Feb 26, 2026
Polyp SegmentationETIS-Larib Polyp DB (test)computer visionbio medical18Feb 26, 2026
Image DenoisingFluoroscopy datasetcomputer vision18Feb 26, 2026
Single Object TrackingLaSOT 18 (test)computer vision18Feb 26, 2026
3D Human Pose and Shape EstimationAGORA3d vision geometrycomputer vision18Feb 26, 2026
Video Super-ResolutionVid4video generation editingcomputer vision18Feb 26, 2026
Multi-class Tumour SegmentationBRATSbio medicalcomputer vision18Feb 26, 2026
Metastatic region segmentationCAMELYON16 tiles (test)bio medicalcomputer vision18Feb 26, 2026
Super-ResolutionWR-SR (test)computer vision18Feb 26, 2026
Temporal Anomaly LocalizationXD-Violence (test)computer visiontabular time series18Mar 4, 2026
Image CaptioningArtEmis (test)multimodalcomputer vision+118May 26, 2026
Video RecognitionKinetics Minicomputer vision18Feb 26, 2026
Point cloud classificationModelNet40 original (test)3d vision geometry18Feb 26, 2026
Video frame interpolationSNU-FILMvideo generation editingcomputer vision18Feb 26, 2026
Retinal Image RegistrationIR-OCT-OCTA IR-OCT paircomputer visionbio medical18Feb 26, 2026
Saliency PredictionSALICON LSUN'17 competition (test)computer vision18Feb 26, 2026
Mutation PredictionTCGA-CRCbio medical18Feb 26, 2026
Shadow DetectionViSha (test)computer vision18Feb 26, 2026
Phrase groundingReferIt (test)computer visionnlp18Feb 26, 2026
Image InpaintingPlaces 512x512 (test)image generation editingcomputer vision18Feb 26, 2026
Node Classificationogbn-products standard (val)graph18Feb 26, 2026
Few-shot Image ClassificationEuroSAT (test)computer vision18Feb 26, 2026
Multi-label ClassificationCUB-200 2011 (test)computer visionnlp+218Feb 26, 2026
Colon Polyp SegmentationKvasir (5-fold cross-validation)computer visionbio medical18Feb 26, 2026
CalibrationGLD OOD-domains v2tabular time series18Feb 26, 2026