List your company

Research

Benchmarks

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

309,131 benchmarksPage 1156 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
Inductive Query AnsweringFB15k-237 Ratio 175%graph24Jul 9, 2026
Secure Aggregation PerformanceFederated Learning Workload Relaxed L∞ defenseadversarial safety security24Jul 9, 2026
Base-to-novel generalizationFood200computer vision24Jul 8, 2026
Manifold LearningSwiss roll uniform samplingmiscellaneous24Jul 8, 2026
Robot ThrowingSneaker (unseen)robotics embodied ai24Jul 8, 2026
Robot ThrowingCoke Can (unseen)robotics embodied ai24Jul 8, 2026
Robot ThrowingBanana (unseen)robotics embodied ai24Jul 8, 2026
Robot ThrowingMilk (seen)robotics embodied ai24Jul 8, 2026
Image ClassificationCIFAR-10 (test)computer vision24Jul 8, 2026
Backdoor Poisoning Sample IsolationTiny-ImageNet (train)adversarial safety security24Jul 8, 2026
External Data Extraction AttackHealthcareMagic-101adversarial safety securitybio medical24Jul 8, 2026
Data Extraction AttackHealthcareMagic-101adversarial safety security24Jul 8, 2026
Data Extraction AttackEnron Mail naive defensesadversarial safety security24Jul 8, 2026
Data Extraction AttackEnron Mailadversarial safety security24Jul 8, 2026
3D ReconstructionPix3D3d vision geometry24Jul 7, 2026
Multiobjective OptimizationSMOP8miscellaneous24Jul 7, 2026
Multiobjective OptimizationSMOP7miscellaneous24Jul 7, 2026
Multiobjective OptimizationSMOP 6miscellaneous24Jul 7, 2026
Multiobjective OptimizationSMOP5miscellaneous24Jul 7, 2026
Multiobjective OptimizationSMOP4miscellaneous24Jul 7, 2026
Multiobjective OptimizationSMOP3miscellaneous24Jul 7, 2026
Unknown entity vs. Visual evidence failure ClassificationPopVQA and iNaturalist Attribution Treecomputer visionmultimodal24Jul 7, 2026
Recognized vs. Unrecognized ClassificationPopVQA and iNaturalist Attribution Treecomputer visionnlp24Jul 7, 2026
User-level depression detectioneRisk25 (test)bio medicalnlp24Jul 7, 2026
User-level depression detectionTwitter (test)bio medicalnlp24Jul 7, 2026