List your company

Research

Benchmarks

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

309,131 benchmarksPage 648 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
Membership Inference AttackHackerNews Pythiaadversarial safety security36Feb 26, 2026
Membership Inference AttackDM Math Pythiaadversarial safety security36Feb 26, 2026
Membership Inference AttackarXiv Pythiaadversarial safety security36Feb 26, 2026
Membership Inference AttackPubMed Pythiaadversarial safety security36Feb 26, 2026
Membership Inference AttackPile CC Pythiaadversarial safety security36Feb 26, 2026
Membership Inference AttackGitHub Pythiaadversarial safety security36Feb 26, 2026
Membership Inference AttackWikipedia Pythiaadversarial safety security36Feb 26, 2026
Membership InferenceGitHub Pythia (train)adversarial safety security36Feb 26, 2026
Membership InferenceWikipedia Pythia (train)adversarial safety security36Feb 26, 2026
Semantic Hallucination DetectionPAWSnlpadversarial safety security36Feb 26, 2026
Maximum CliqueRB500 MC instances (static)graph36Feb 26, 2026
General Knowledge ReasoningMMLU-Prollm chat instructionnlp36Apr 8, 2026
Contributor AttributionArtBench Post-Impressionismcomputer vision36Feb 26, 2026
SAE steeringNeutral prefixes datasetllm chat instruction36Feb 26, 2026
Knowledge RecoveryWMDP-Bio 100-sample subsetnlp36Feb 26, 2026
Pricing optimizationPhilippines cocoa liquor dataset (test)tabular time series36Feb 26, 2026
Safety AlignmentPKU-SafeRLHF 30K (IID)adversarial safety security36Feb 26, 2026
Safety EvaluationXSTest (test)adversarial safety security36Jun 11, 2026
OOD detectionImageNet (OOD) with CIFAR10 (ID)computer visiontabular time series36Feb 26, 2026
Causal DiscoverySynthetic (n=100, |E|=400, sample size=1000)tabular time series36Feb 26, 2026
Human Activity RecognitionCMDFallcomputer vision36Feb 26, 2026
Variational Quantum EigensolverNoisy Transverse-Field Ising Hamiltoniansmiscellaneous36Feb 26, 2026
Image ClassificationCINIC-10 Dir(0.01), 50 clients, 20% participationcomputer vision36Feb 26, 2026
Language Model Alignment EvaluationArena-Hard v0.1llm chat instructionadversarial safety security36Feb 26, 2026
Learning Curve ExtrapolationLCBench (test)tabular time series36Feb 26, 2026