List your company

Research

Benchmarks

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

309,131 benchmarksPage 1791 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
SIS Dynamics PredictionHSBM Graphongraph18Jun 26, 2026
SIS Dynamics PredictionTent Graphongraph18Jun 26, 2026
Linear Heat Dynamics PredictionHSBM Graphongraphtabular time series18Jun 26, 2026
Linear Heat Dynamics PredictionTent Graphongraphtabular time series18Jun 26, 2026
Biometric AuthenticationBlowLive Datasetadversarial safety security18Jun 25, 2026
Photographer-side guidanceCaptureGuide-Bench photographer-side guidancecomputer vision18Jun 25, 2026
RetrievalSTaRK-Prime 1.0 (test)retrieval search rag18Jun 25, 2026
Directed-arm ReclaimSession-2 memory (logic)robotics embodied ai18Jun 25, 2026
Directed-arm ReclaimMemory Arithmetic Session-2robotics embodied ai18Jun 25, 2026
RetrievalNeedle-in-a-Haystack Inductionretrieval search rag18Jun 25, 2026
Image ClassificationTiny-ImageNetcomputer vision18Jun 25, 2026
3D Object DetectionKITTI (test)3d vision geometrycomputer vision18Jun 24, 2026
Light field image denoisingEPFL (test)computer vision18Jun 24, 2026
Light field image denoisingSTFLytro (test)computer vision18Jun 24, 2026
Information RetrievalRTEBretrieval search rag18Jun 24, 2026
Factual Knowledge RecallCLIKE 1.0 (test)llm chat instructionnlp18Jun 24, 2026
Stereo MatchingDrivingStereo Weather Overall3d vision geometrycomputer vision18Jun 24, 2026
Stereo MatchingDrivingStereo Weather Sunny3d vision geometrycomputer vision18Jun 24, 2026
Visual Object TrackingVOT20computer vision18Jun 24, 2026
Feature MatchingScanNet3d vision geometrycomputer vision18Jun 24, 2026
Feature MatchingMegaDepth3d vision geometrycomputer vision18Jun 24, 2026
Multiple ClusteringCardgraph18Jun 24, 2026
Stair TraversalSimulated Stairs 20cm Heightrobotics embodied ai18Jun 24, 2026
Stair TraversalSimulated Stairs 18cm Heightrobotics embodied ai18Jun 24, 2026
Stair TraversalSimulated Stairs 16cm Heightrobotics embodied ai18Jun 24, 2026