List your company

Research

Benchmarks

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

309,131 benchmarksPage 1264 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
News topic classification20 Newsgroups 20% Instance-Dependent Noisenlp24Feb 26, 2026
News topic classification20 Newsgroups 40% Asymmetric Noisenlp24Feb 26, 2026
News topic classification20 Newsgroups 20% Asymmetric Noisenlp24Feb 26, 2026
News topic classification20 Newsgroups 40% Symmetric Noisenlp24Feb 26, 2026
News topic classification20 Newsgroups 20% Symmetric Noisenlp24Feb 26, 2026
3D Object DetectionKITTI (val)3d vision geometrycomputer vision24Jun 2, 2026
Co-Salient Object DetectioniCoSegcomputer vision24Mar 11, 2026
Video Quality AssessmentKVQcomputer vision24May 19, 2026
Patch-Level ClassificationPrivate-Breastcomputer visionbio medical24Feb 26, 2026
Patch-level searchPrivate-Breastretrieval search ragbio medical+124Feb 26, 2026
Highlight DetectionYouTube Highlights (YouTubeHL) (full)computer vision24Feb 26, 2026
Open-vocabulary semantic segmentationPascal Context-59 (test)computer vision24Feb 26, 2026
Frame-level Face Forgery DetectionWild Deepfakecomputer vision24Feb 26, 2026
Time Series ForecastingETTh2 -> ETTm2 (test)tabular time series24Feb 26, 2026
Long-term forecastingILI (test)tabular time series24Mar 10, 2026
InterpolationPhysioNet 1 min quantization 2012 (test)tabular time series24Feb 26, 2026
RegressionProtein (test)tabular time series24Mar 31, 2026
Multimodal Question AnsweringMM-Vetmultimodalnlp+1Multimodal Question Answering on MM-Vet performance trend24Feb 26, 2026
Image ClassificationFood-101 (val)computer vision24Apr 3, 2026
Semantic SegmentationBIG dataset (test)computer vision24Feb 26, 2026
Univariate Time Series Forecastingillnesstabular time series24Feb 26, 2026
Novel View SynthesisLLFF (P2)3d vision geometry24Feb 26, 2026
Synthetic image detectionGlide 100-10computer visionimage generation editing24May 1, 2026
Synthetic image detectionGlide 100-27computer visionimage generation editing24May 1, 2026
Novel View SynthesisRealEstate 10k (RE10k) (test)3d vision geometryNovel View Synthesis on RealEstate 10k (test) performance trend24Apr 2, 2026