List your company

Research

Benchmarks

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

309,131 benchmarksPage 1020 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
Open Vocabulary Semantic SegmentationPASCAL VOCcomputer vision27May 12, 2026
Visual Question AnsweringPMC-VQA (test)multimodalcomputer vision+127May 12, 2026
Image ClassificationCIFAR-100-LT (IF=200)computer vision27May 12, 2026
Infrared Small Target DetectionNUAA-SIRSTcomputer vision27Feb 26, 2026
Object Hallucination EvaluationMSCOCO CHAIRmultimodalcomputer vision27Feb 26, 2026
Mathematical ReasoningGSMllm chat instructionnlp27Feb 26, 2026
Anomaly DetectionCAAD-3K Cross-Context (test)tabular time series27Feb 26, 2026
Temporal Video GroundingTACoScomputer visionnlp27May 26, 2026
Discontinuity Set Orientation EstimationStope Point-Cloud Dataset (val)3d vision geometry27Feb 26, 2026
Abstract Visual ReasoningARC-AGI 1computer visionnlp27Apr 10, 2026
Anomaly LocalizationDTDcomputer vision27Mar 23, 2026
Multimodal ReasoningMMBench v1.1 (test)multimodalnlp27Apr 21, 2026
Vision-Language UnderstandingMMBench cnmultimodalcomputer vision+127Jun 18, 2026
Action Triplet RecognitionCholecT50computer vision27Feb 26, 2026
Visual Spatial Intelligence ReasoningVSI-Debiasedcomputer visionmultimodal27Mar 4, 2026
Open-Vocabulary SegmentationPascal VOC 21 2012 (val)computer vision27Feb 26, 2026
Closed-loop planningNAVSIM v2robotics embodied ai27Jun 5, 2026
Text-to-audioAudioCapsspeech audiomultimodal27Jul 1, 2026
Object Hallucination ProbingA-OKVQA (Adversarial split)computer visionnlp27Feb 26, 2026
Image EditingGEdit-ENimage generation editing27Mar 27, 2026
Image CaptioningFlickr8K (test)multimodalcomputer vision+127Feb 26, 2026
Road Condition ClassificationFriction (test)computer vision27Feb 26, 2026
Safety EvaluationSorry-Bench baseadversarial safety security27Feb 26, 2026
Visual Question AnsweringGQAmultimodalcomputer vision+127Feb 26, 2026
Adversarial AttackBinary N-MNISTadversarial safety securitycomputer vision27Feb 26, 2026