List your company

Research

Benchmarks

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

309,131 benchmarksPage 2239 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
Adversarial AttackImageNet Target: Inc-v3adversarial safety securitycomputer vision16Feb 26, 2026
Stereo Pose EstimationIMC 2020 (test)3d vision geometrycomputer vision16Feb 26, 2026
Image ClassificationCIFAR-10 (val)computer vision16Feb 26, 2026
Text FluencyCHED and CounterFactnlp16Feb 26, 2026
General Language UnderstandingGeneral Ability Suite (C-QA, T-QA, LAM, MMLU, L-Code)nlp16Feb 26, 2026
Text SummarizationCNN/DMnlp16Feb 26, 2026
Time Series ForecastingWind Power (test)tabular time series16Feb 26, 2026
Univariate time series forecastingCluster-Ctabular time series16Feb 26, 2026
Univariate time series forecastingCluster Btabular time series16Feb 26, 2026
Univariate time series forecastingCluster-Atabular time series16Feb 26, 2026
Backdoor Sample DetectionAgnewsadversarial safety security16Feb 26, 2026
Backdoor Sample DetectionHSOLadversarial safety security16Feb 26, 2026
Backdoor Sample DetectionYELPadversarial safety security16Feb 26, 2026
Grammatical Error CorrectionIceEC dyslexicnlp16Feb 26, 2026
Grammatical Error CorrectionIceEC (test)nlp16Feb 26, 2026
Semantic RelatednessBEIR Semantic Relatedness Tasks (test)nlp16Mar 27, 2026
Named Entity RecognitionBC4CHEMDnlp16Feb 26, 2026
Domain AdaptationUSPS to MNIST (test)computer visionnlp+116Feb 26, 2026
Classificationcommunitiescomputer visionnlp+316Jun 11, 2026
Offline-to-Online Reinforcement LearningD4RL 6 environments min-max normalized (averaged)robotics embodied ai16Feb 26, 2026
Human Intervention PredictionCOWCORPUS (All Data)robotics embodied ai16Feb 26, 2026
Quality ImprovingRETOUCHEVAL 1.0 (test)image generation editing16Feb 26, 2026
Strategy-based Question AnsweringStrategyQAnlpllm chat instruction16Apr 23, 2026
Personal Data AssociationFamous datasetnlp16Mar 13, 2026
Recommender Systems Framework EvaluationRecommender System Frameworks Comparison 2024tabular time series16Feb 26, 2026