List your company

Research

Benchmarks

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

309,131 benchmarksPage 2208 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
Multi-label ClassificationPASCAL VOC 2007/2012 (test)computer visionnlp+216Mar 24, 2026
Deepfake DetectionHydraFakecomputer visionadversarial safety security16Mar 24, 2026
Knowledge Unlearning16-task Sequential Unlearning Forgotten Data Lastnlpadversarial safety security16Mar 24, 2026
Multi-class ClassificationWinetabular time series16Apr 29, 2026
Software EngineeringSWE-benchcode developer aiSoftware Engineering on SWE-bench performance trend16May 7, 2026
3D GenerationUniLat1K3d vision geometry16Mar 24, 2026
3D GenerationToys4K3d vision geometry16Mar 24, 2026
Image ClassificationCIFAR100 LT (r=10)computer vision16Mar 24, 2026
Image EditingGIDE-Benchimage generation editing16Mar 24, 2026
Theorem-provingMathOlympiad-Benchmiscellaneous16Mar 24, 2026
Ultrasound Question AnsweringU2-Bench disease-diagnosisbio medicalcomputer vision+116Mar 24, 2026
Language ModelingProof-pile (test)nlp16Mar 24, 2026
Personalized Image GenerationCustomConcept101image generation editing16Mar 24, 2026
Fine-grained fashion image retrievalDARN (test)retrieval search ragcomputer vision16Jun 11, 2026
Fine-grained fashion image retrievalFashionAI (test)retrieval search ragcomputer vision16Jun 11, 2026
Age predictionHCP-Agebio medicalcomputer vision+116Mar 24, 2026
Sex predictionHCP Genderbio medicalcomputer vision16Mar 24, 2026
Sequential RecommendationSportstabular time series16May 12, 2026
Object DetectionDWD (Diverse Weather Dataset)computer vision16Mar 24, 2026
Group RecommendationMovieLens 100K (test)retrieval search rag16Mar 24, 2026
Edge DetectionBSDS 500 (test)computer vision16Mar 24, 2026
Nuclei SegmentationMoNuSeg transfer from TNBC (test)computer visionbio medical16Mar 24, 2026
Defense RobustnessGCG Attackadversarial safety security16Mar 24, 2026
Defense RobustnessAutoDAN Attackadversarial safety security16Mar 24, 2026
Defense RobustnessDirect Inquiry Vanillaadversarial safety security16Mar 24, 2026