List your company

Research

Benchmarks

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

309,131 benchmarksPage 316 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
Density EstimationBanana-shaped distributions scenario Bananatabular time series56May 14, 2026
Density EstimationGaussian mixture distributions pre-training family F GMDF+tabular time series56May 14, 2026
Density EstimationGaussian mixture distributions pre-training family F GMDFtabular time series56May 14, 2026
Data Contamination DetectionSeen vs. Unseen Datasets (dataset-level)code developer aiadversarial safety security56May 13, 2026
Language ModelingWikiText-103 v1 (test)nlp56May 13, 2026
Multilingual EvaluationTAXI1500nlp56May 13, 2026
Multilingual EvaluationSIB200nlp56May 13, 2026
Membership AuditingMath Reasoning Tasksadversarial safety securityllm chat instruction56May 12, 2026
ReasoningARC Challengellm chat instructionnlp56Jun 23, 2026
Scientific ReasoningSciKnowEvalnlp56Jul 3, 2026
Claim VerificationMed Claimnlp56May 8, 2026
Action Category ClassificationCLIPcomputer vision56May 8, 2026
Dynamic Link PredictionEnron (transductive)graph56Jun 4, 2026
Safety EvaluationJailbreakBench (JBB) (test)adversarial safety security56May 7, 2026
Safety EvaluationRefusal Signal Scoreadversarial safety security56May 7, 2026
Safety EvaluationSecureBreakadversarial safety security56May 7, 2026
Safety EvaluationLlama-Guard 3-8Badversarial safety security56May 7, 2026
User response predictionWorldValuesBench (held-out users)nlp56May 4, 2026
Response PredictionWorldValuesBench (held-out)tabular time series56May 4, 2026
Ordinal response predictionSynthetic users N=20,000 (test)tabular time series56May 4, 2026
Ordinal PredictionWorldValuesBench (held-out users)tabular time series56May 4, 2026
Adaptive QueryingSynthetic users N = 20,000 (test)retrieval search rag56May 4, 2026
Question AnsweringARC Challengenlp56Jun 18, 2026
Sentence SimilaritySICKnlp56Apr 28, 2026
Harmfulness EvaluationDirectHarmadversarial safety security56Apr 24, 2026