List your company

Research

Benchmarks

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

309,131 benchmarksPage 1357 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
Long Video GenerationVBenchLong 30-secondvideo generation editing22May 29, 2026
Linear Assignment ProblemMOTmiscellaneous22May 12, 2026
Watermark Forgery DetectionMS-COCOcomputer vision22May 12, 2026
Action PredictionAndroidControl Low v2computer vision22May 27, 2026
Action PredictionAndroidControl High v2computer vision22May 12, 2026
Ethical Violation LocationETHICSCAFFadversarial safety securitynlp22May 12, 2026
Violated Principle ClassificationETHICSCAFFadversarial safety securitynlp22May 12, 2026
ClassificationSEMcomputer visionnlp+322May 12, 2026
ClassificationPIXcomputer visionnlp+322May 12, 2026
ClassificationOPTcomputer visionnlp+322May 12, 2026
ClassificationKARcomputer visionnlp+322May 12, 2026
ClassificationINCcomputer visionnlp+322May 12, 2026
ClassificationDIAcomputer visionnlp+322May 12, 2026
Indirect prompt injection defenseSQuADadversarial safety security22May 12, 2026
Molecular Function Gene Ontology classificationGO MFbio medicalnlp22May 11, 2026
Instruction Alignment EvaluationEBench 18Kllm chat instruction22May 11, 2026
Deepfake DetectionDFD Narrow-band Notchcomputer visionadversarial safety security22May 11, 2026
Deepfake DetectionDaGcomputer visionadversarial safety security22May 11, 2026
Deepfake DetectionDiFcomputer visionadversarial safety security22May 11, 2026
Object DetectionLOD (test)computer vision22May 11, 2026
Object DetectionPASCAL RAW (Dark)computer vision22May 11, 2026
Cross-view UAV Geo-localizationDenseUAV University-1652 (train)computer vision3d vision geometry22May 11, 2026
Molecular generation from mass spectraMassSpecGymbio medical22May 14, 2026
SAT instance generationSynthetic SAT instances phase transitionmiscellaneous22May 11, 2026
Sleep stage classificationSleep-EDF to SHHS-1 cross-datasetbio medicaltabular time series22May 11, 2026