List your company

Research

Benchmarks

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

309,131 benchmarksPage 987 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
Binary SegmentationCVC-ColonDBcomputer vision28Feb 26, 2026
Multimodal UnderstandingMMVet turbomultimodal28Feb 27, 2026
Multi-image ReasoningMantis-Evalmultimodalcomputer vision+128Feb 27, 2026
3D Object TrackingnuScenes (test)3d vision geometrycomputer vision28Feb 26, 2026
LVEF PredictionEchoNet-Dynamic (test)bio medicalcomputer vision28Feb 26, 2026
Meme ClassificationHarm-Pcomputer visionnlp28Feb 26, 2026
Continual Instruction FollowingALFREDllm chat instructionrobotics embodied ai28Feb 26, 2026
3D Object DetectionV2X-R (val)3d vision geometrycomputer vision28Feb 26, 2026
Data ImputationCancertabular time series28Feb 26, 2026
Multi-view StereoTanks and Temples (Advanced set)3d vision geometry28Feb 26, 2026
Table Fact VerificationTabFact (dev)nlptabular time series28Feb 26, 2026
Multimodal Machine Unlearning EvaluationMLLMU-Bench Real Celebritymultimodaladversarial safety security28Mar 18, 2026
Retinal Anomaly DetectionOCT 2017 (test)bio medicalcomputer vision28Feb 26, 2026
AttributionVerifiability-Granular (test)retrieval search ragnlp28Feb 26, 2026
Word SimilarityWS-353 REL (test)nlp28Feb 26, 2026
Fine-grained Visual Question AnsweringHRBench-8Kmultimodalcomputer vision28Feb 26, 2026
Fine-grained Visual Question AnsweringHRBench 4Kmultimodalcomputer vision28Feb 26, 2026
Fine-grained Visual Question AnsweringV*Benchmultimodalcomputer vision28Feb 26, 2026
AD diagnosisADNI (test)bio medical28Mar 4, 2026
Optical FlowMVSEC 1.0 (outdoor_day1)computer vision28Feb 26, 2026
WSI ClassificationCAMELYON16 (test)bio medicalcomputer vision28Feb 26, 2026
Open-Vocabulary SegmentationADE20Kcomputer vision28Jun 23, 2026
Unknown sample identificationSynthetic-to-Realcomputer vision28Feb 26, 2026
Video Question AnsweringTempCompassmultimodalcomputer vision28May 26, 2026
Safety Behavior PredictionChallenging Promptsadversarial safety securityllm chat instruction27Jul 9, 2026