List your company

Research

Benchmarks

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

309,131 benchmarksPage 1860 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
Link PredictionMKG-W (Higher split)graph18Apr 6, 2026
Link PredictionMKG-W (Entity split)graph18Apr 6, 2026
Link PredictionDB15K Equal splitgraph18Apr 6, 2026
Link PredictionDB15K Higher splitgraph18Apr 6, 2026
Link PredictionDB15K Entity splitgraph18Apr 6, 2026
Religious Bias EvaluationMultilingual CrowS-Pairs (test)nlpadversarial safety security18Apr 6, 2026
Racial Bias EvaluationMultilingual CrowS-Pairs racial biasadversarial safety securitynlp18Apr 6, 2026
Gender Bias MitigationMultilingual CrowS-Pairs gender-sensitive attributesnlp18Apr 6, 2026
Rule DiscoveryBlicket Taskllm chat instruction18Apr 6, 2026
Tempo SteeringMusicGenvideo generation editing18Apr 6, 2026
Causal Graph DiscoveryAsia causal graphgraph18Apr 6, 2026
Causal Graph DiscoveryAsia 8 nodes, 8 edgesgraph18Apr 6, 2026
CBCT segmentationInternal dataset for CBCT segmentationcomputer visionbio medical18Apr 6, 2026
Image Forgery DetectionAutoSplicecomputer vision18Jun 11, 2026
NSFW suppressionUnlearn-DiffAtkadversarial safety security18Apr 13, 2026
NSFW suppressionRing-A-Belladversarial safety security18Apr 13, 2026
Unconditional Text GenerationWikipedianlp18Apr 3, 2026
LLM-generated text detectionDetectRL Out-of-Domain Multi-Topic 1.0 (test)llm chat instructionnlp18Apr 3, 2026
Medical Image ClassificationOrganCMNISTbio medicalcomputer vision18May 27, 2026
Medical Image ClassificationBloodMNISTbio medicalcomputer vision18May 27, 2026
HOI Semantic Similarity AlignmentHOI similarity human judgment HICO-DET labels (user study average)computer visionnlp18Apr 3, 2026
Jailbreak DefenseTAPadversarial safety security18Apr 10, 2026
Multi-class ClassificationFACETtabular time series18Apr 3, 2026
LLM WatermarkingC4llm chat instructionadversarial safety security18Apr 3, 2026
Time Series Classification18 UEA datasets Average across scenariostabular time series18Apr 3, 2026