List your company

Research

Benchmarks

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

309,131 benchmarksPage 362 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
Code Input PredictionCRUXEval-Icode developer ai52May 28, 2026
Visual GroundingRefCOCOgmultimodalcomputer vision52Jul 1, 2026
Image Super-ResolutionSet14 classic (test)computer vision52Feb 26, 2026
Mathematical ReasoningMathQA (test)llm chat instructionnlp52May 12, 2026
Code GenerationHumanEval Multilingual (test)code developer ai52Feb 26, 2026
Point Cloud ClassificationScanObjectNN OBJ-ONLY3d vision geometry52Mar 27, 2026
Univariate Time Series Forecastingtraffictabular time series52Jul 8, 2026
Spatio-temporal video groundingHCSTVG v2 (val)computer visionmultimodal52Jun 30, 2026
Hyperparameter OptimizationJAHS-C10 Bench (val)miscellaneous52Feb 26, 2026
Compositional Zero-Shot LearningUT-Zappos open worldcomputer visionnlp52Mar 18, 2026
Unsupervised Domain AdaptationUCF-HMDBcomputer visiontabular time series52May 20, 2026
Image ClassificationCIFAR-20computer vision52May 18, 2026
Age RegressionUKBcomputer vision52Jun 26, 2026
Offline Reinforcement LearningD4RL Medium-Replay Walker2drobotics embodied ai52May 11, 2026
ClassificationCovertypecomputer visionnlp+352Jul 7, 2026
Point TrackingDAVIS TAP-Vidcomputer vision52Mar 27, 2026
Question AnsweringTriviaQA Wiki (val)nlp52Mar 17, 2026
Multi-label Graph ClassificationPeptides funcgraph52May 13, 2026
Full-Reference Image Quality AssessmentCSIQ-IQAcomputer vision52Mar 17, 2026
Factual Consistency EvaluationSummaCnlp52Feb 26, 2026
Toxicity DetectionImplicit Hatenlp52Jun 2, 2026
Audio-Visual Event LocalizationAVEmultimodalspeech audio+152May 13, 2026
Image-to-Text RetrievalMS-COCO 5Kmultimodalretrieval search rag52Jul 3, 2026
Image ClassificationImageNet to 10 Target Datasets (Caltech101, OxfordPets, StanfordCars, Flowers102, Food101, FGVCAircraft, SUN397, DTD, EuroSAT, UCF101) (test)computer visionImage Classification on ImageNet to 10 Target Datasets (test) performance trend52May 7, 2026
Blind Face RestorationLFW (test)computer visionimage generation editing52Apr 1, 2026