List your company

Research

Benchmarks

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

309,131 benchmarksPage 1966 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
CalibrationGLD InD-domains v2tabular time series18Feb 26, 2026
CalibrationWILDS-RxRx1 (OOD-domains)tabular time series18Feb 26, 2026
CalibrationWILDS-RxRx1 (InD-domains)tabular time series18Feb 26, 2026
Image ClassificationSmall-ImageNet-127computer vision18Jun 16, 2026
Biomedical Knowledge ProbingMedLAMA Full Set 1.0bio medicalnlp18Feb 27, 2026
Zero-shot performance predictionUDPOSnlp18Feb 26, 2026
Zero-shot performance predictionWikiANNnlp18Feb 26, 2026
Zero-shot performance predictionXNLInlp18Feb 26, 2026
Image ClassificationImageNet 2012 (val)computer vision18Feb 26, 2026
3D Shape RetrievalModelNet-403d vision geometry18Feb 26, 2026
Tweet ClassificationTweetEval 1.0 (test)nlp18Feb 26, 2026
Out-of-distribution DetectionISUNcomputer visiontabular time series18Feb 26, 2026
Multi-Image Super-ResolutionSynthetic 15 images (test)computer vision18Feb 26, 2026
Binary ClassificationTABFACT (test)tabular time series18Feb 26, 2026
Image ClassificationCIFAR-10-LT Imbalance Ratio 50 (test)computer vision18Feb 26, 2026
Behavior ClassificationCalMS21 (test)computer vision18Mar 11, 2026
Line Segment DetectionWireframecomputer vision18Feb 26, 2026
Image ClassificationGBCU (test)computer vision18Feb 26, 2026
Semantic SegmentationCityscapes 1/4 subset (val)computer vision18Feb 26, 2026
Saliency DetectionDUT-LFcomputer vision18Feb 26, 2026
Burst Super-resolutionSyntheticBurst (val)computer vision18Feb 26, 2026
Offline Task-Incremental Continual LearningCIFAR-100 Sequentialcomputer vision18Feb 26, 2026
Offline Class-Incremental Continual LearningCIFAR-100 Sequentialcomputer visiontabular time series18Feb 26, 2026
Offline Task-Incremental Continual LearningSequential CIFAR-10computer vision18Feb 26, 2026
Offline Class-Incremental Continual LearningCIFAR-10 Sequentialcomputer visiontabular time series18Feb 26, 2026