List your company

Research

Benchmarks

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

309,131 benchmarksPage 1090 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
Open-domain Question AnsweringTriviaQA (TQA) (test)nlpretrieval search rag26Feb 26, 2026
Video highlight detectionTVsumcomputer vision26Feb 26, 2026
Atlas BuildingOAI knee MRI NIMH Data Archive Collection ID: 2343 (test)bio medicalcomputer vision26Feb 26, 2026
Incremental Semantic SegmentationCOCOcomputer vision26Jun 4, 2026
Continuous ControlMuJoCo Antrobotics embodied ai26Mar 13, 2026
Image ClassificationCaltech-UCSD Birds (CUB-200-2011) (test)computer vision26Mar 4, 2026
Intent PredictionPhotoChat (test)nlp26Feb 26, 2026
Video Individual CountingCroHD (test)computer vision26Feb 26, 2026
Speech EnhancementDNS Challenge Without Reverb (test)speech audio26Jul 3, 2026
Super-ResolutionDIV2KRK (test)computer vision26Feb 26, 2026
Named Entity RecognitionOntoNotes to I2B2, CoNLL, WNUT, GUM 5.0 (test)nlp26Feb 26, 2026
2D Object DetectionSUN-RGBD (val)computer vision26Feb 26, 2026
Lane DetectionLLAMAS (val)computer vision26Feb 26, 2026
Hyperspectral Image ReconstructionKAIST simulation (Average test)computer vision3d vision geometry26Feb 26, 2026
Event ExtractionACE05 Evtnlp26Feb 26, 2026
Medical Image SegmentationACDC (5-fold cross-validation)bio medicalcomputer vision26Feb 26, 2026
Video Frame InterpolationXiph4Kvideo generation editingcomputer vision26Feb 26, 2026
Video Person Re-identificationDukeMTMC-VideoReIDcomputer vision26Feb 26, 2026
Question AnsweringWebSRC (dev)nlp26Feb 26, 2026
Link Predictionogbl-collab (val)graph26Feb 26, 2026
Link PredictionLastFMgraph26Apr 20, 2026
No-Reference Image Quality AssessmentLIVE 80/20 splitcomputer vision26Feb 26, 2026
Offline Reinforcement LearningD4RL antmaze-med (diverse)robotics embodied ai26Feb 26, 2026
3D Point Cloud RegistrationKITTI (test)3d vision geometry26Feb 26, 2026
Traffic Signal ControlNew York real-world (test)robotics embodied ai26Feb 26, 2026