List your company

Research

Benchmarks

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

309,131 benchmarksPage 1277 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
Action Phase ClassificationPouringcomputer vision24Feb 26, 2026
Action Phase ClassificationIKEA ASM (Background)computer vision24Feb 26, 2026
Action Phase ClassificationIKEA ASM No Backgroundcomputer vision24Feb 26, 2026
OOD detectionSuperconductivity (test)computer visiontabular time series24Feb 26, 2026
Image ClassificationImageNet (val)computer vision24Feb 26, 2026
Targeted Adversarial AttackImageNet 1000 images (val)adversarial safety securitycomputer vision24Feb 26, 2026
Untargeted Adversarial AttackImageNet 1000 images (val)adversarial safety security24Feb 26, 2026
Adversarial RobustnessCIFAR100 1000 images (val)adversarial safety securitycomputer vision24Feb 26, 2026
Adversarial RobustnessCIFAR10 1000 images (test)adversarial safety securitycomputer vision24Feb 26, 2026
ClassificationCIFAR-10 (test)computer visionnlp+324Feb 26, 2026
Image ClassificationImageNet 10% labels 1.0 (train val)computer vision24Feb 26, 2026
Image ClassificationImageNet 1% labels 1.0 (train val)computer vision24Feb 26, 2026
Speech EnhancementVoiceBank-DEMAND Traffic 1.0 (test)speech audio24Feb 26, 2026
Speech EnhancementTIMIT Baby-cry noisespeech audio24Feb 26, 2026
Speech EnhancementTIMIT Cafeteria noisespeech audio24Feb 26, 2026
Speech EnhancementTIMIT Crowd-party noisespeech audio24Feb 26, 2026
Speech EnhancementTIMIT Helicopter noisespeech audio24Feb 26, 2026
Speech EnhancementVoiceBank-DEMAND Public squarespeech audio24Feb 26, 2026
Speech EnhancementVoiceBank-DEMAND Cafespeech audio24Feb 26, 2026
Speech EnhancementVoiceBank-DEMAND Trafficspeech audio24Feb 26, 2026
Defocus DeblurringNoisier DPD v1 (simulated noise) (test)computer vision24Feb 26, 2026
k-subset selectionBeerAdvocate Taste (val test)tabular time series24Feb 26, 2026
k-subset selectionPalate aspect data (val)tabular time series24Feb 26, 2026
k-subset selectionBeerAdvocate Aroma aspect L2X experimental setup (test)tabular time series24Feb 26, 2026
k-subset selectionAppearance aspect data (val)tabular time series24Feb 26, 2026