List your company

Research

Benchmarks

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

309,131 benchmarksPage 2075 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
DesnowingRealisticcomputer vision17Feb 26, 2026
Grammatical Error CorrectionFCGEC (test)nlp17Feb 26, 2026
Natural Language UnderstandingSuperGLUE RoBERTa-large (test)nlp17Feb 26, 2026
ClassificationHumSet XLM-RBASE (test)computer visionnlp+317Feb 26, 2026
Multilingual Multi-label Text ClassificationHumSet (test)nlp17Feb 26, 2026
Arithmetic Tree Generation128-bit Addercode developer ai17Feb 26, 2026
Sleep Stage ClassificationSleep-EDFX from SHHSbio medicaltabular time series17May 11, 2026
Sign Language RecognitionPhoenix 2014 (test)computer visionspeech audio17Feb 26, 2026
Multi-label ClassificationMIRFLICKRcomputer visionnlp+217Mar 4, 2026
Vision-Language ProbingVL-CheckList (test)multimodalcomputer vision+117Feb 26, 2026
Super-ResolutionAIM (val)computer vision17Feb 26, 2026
Offline Reinforcement LearningD4RL MuJoCo walker2d medium v2robotics embodied ai17Mar 10, 2026
Offline Reinforcement LearningD4RL MuJoCo walker2d random v2robotics embodied ai17Mar 10, 2026
Knowledge Graph ReasoningUMLS (test)graph17Feb 26, 2026
Interactive SegmentationPartImageNetcomputer vision17Feb 26, 2026
Interactive SegmentationPascalPartcomputer vision17Feb 26, 2026
Trajectory PredictionGTA-1M (test)robotics embodied aitabular time series17Feb 26, 2026
Trajectory PredictionGIMO (test)robotics embodied aitabular time series17Feb 26, 2026
Landmark DetectionISBI Challenge 2015 (test)computer vision17May 6, 2026
Object DetectionHRSC2016computer vision17Mar 16, 2026
Human Dance GenerationTikTok (test)video generation editing17Feb 26, 2026
Multi-instance Point Cloud RegistrationScan2CAD (test)3d vision geometry17Feb 26, 2026
Multi-instance Point Cloud RegistrationScan2CAD single-frame3d vision geometry17Feb 26, 2026
Semantic SegmentationSynthia to {Cityscapes (C), BDD (B), Mapillary (M)}computer vision17Feb 26, 2026
Vision-and-Language NavigationCVDN (val-unseen)robotics embodied aimultimodal17Jun 19, 2026