List your company

Research

Benchmarks

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

309,131 benchmarksPage 1509 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
Semantic Image EditingADE20K-Roomimage generation editingcomputer vision21Feb 26, 2026
Semantic Image EditingCityscapesimage generation editingcomputer vision21Feb 26, 2026
Question AnsweringSQuAD v2.0 (val)nlp21Feb 26, 2026
Instance SegmentationADE20K (val)computer vision21Feb 27, 2026
Novel View SynthesisDTU 9-view (test)3d vision geometry21Feb 26, 2026
Video CompressionStandard Video Compression Suite UVG, MCL-JCV, HEVC B/C/D/E/RGBvideo generation editing21Feb 26, 2026
3D Object DetectionKITTI car category (val)3d vision geometrycomputer vision21Feb 26, 2026
Video RecognitionUCF101 v1 (test)computer vision21Feb 26, 2026
Gaussian DenoisingSet12computer vision21Feb 26, 2026
Barycenter ComputationLocation-scatter population Uniform P0 = Uniform([-sqrt(3), +sqrt(3)]^D) (test)miscellaneous21Feb 26, 2026
Barycenter ComputationLocation-scatter population (Gaussian P0 = N(0, ID)) (test)miscellaneous21Feb 26, 2026
Activity DetectionCharades (val)computer vision21Feb 26, 2026
Scene ClassificationNWPU 10/90 splitcomputer vision21Feb 26, 2026
Long-form TranscriptionCORAALspeech audio21Feb 26, 2026
Speech RecognitionMultilingual LibriSpeech (MLS) (test)speech audio21Mar 13, 2026
Image ClassificationImageNet IDcomputer vision21Feb 26, 2026
Spatiotemporal Action LocalizationAVA 2.2computer vision21Feb 26, 2026
Teachable Object RecognitionORBIT CLU-VE 1.0 (test)computer vision21Feb 26, 2026
Teachable Object RecognitionORBIT CLE-VE 1.0 (test)computer vision21Feb 26, 2026
Long-text classificationHyperpartisan news detection (test)nlp21Feb 26, 2026
Video Object SegmentationLong-time Video dataset (val)computer vision21Feb 26, 2026
SimulabilityML-QE (test)miscellaneous21Feb 26, 2026
NavigationObstacle World (test)robotics embodied ai21Feb 26, 2026
RegressionWinetabular time series21May 19, 2026
RegressionPowertabular time series21Jul 9, 2026