List your company

Research

Benchmarks

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

309,131 benchmarksPage 1818 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
Adversarial AttackMS-COCO (test)adversarial safety securitycomputer vision18May 27, 2026
Safety Alignment EvaluationHEx-PHIadversarial safety securityllm chat instruction18May 27, 2026
Safety Alignment EvaluationSorryBenchadversarial safety securityllm chat instruction18May 27, 2026
Jailbreak RobustnessJailbreak Attacksadversarial safety security18May 27, 2026
Natural Language UnderstandingEuroEval Frenchnlp18May 27, 2026
Natural Language UnderstandingEuroEval Spanishnlp18May 27, 2026
Natural Language UnderstandingEuroEval Englishnlp18May 27, 2026
Natural Language UnderstandingEuroEval Germannlp18May 27, 2026
Visual Object TrackingCOESOTcomputer vision18May 27, 2026
Image ClassificationSTL10computer vision18May 27, 2026
Image ClassificationFlowers102computer vision18May 27, 2026
Image ClassificationDTDcomputer vision18May 27, 2026
OOD GeneralizationVLCScomputer vision18May 27, 2026
Answering queries with two free variablesFB15kgraphnlp18May 26, 2026
Multimodal EvaluationMMEmultimodal18May 26, 2026
Legal Examinationlegal examination tasks Out-of-domainnlp18May 26, 2026
Legal Research and ReasoningLegalSearch In-domainnlpretrieval search rag18May 26, 2026
Merge Conflict ResolutionMerge-Bench Java (test)code developer ai18May 26, 2026
Capacitated Vehicle Routing Problem with Time WindowsCVRPTW100 1,000 instancesmiscellaneous18Jun 2, 2026
Graph ClassificationComputersgraph18May 26, 2026
Graph ClassificationCiteSeergraph18May 26, 2026
Research AutomationDRBmiscellaneous18May 26, 2026
Research AutomationMAB.researchmiscellaneous18May 26, 2026
Code GenerationMAB codecode developer ai18May 26, 2026
Bounding box classificationLVIS 1203computer vision18May 26, 2026