List your company

Research

Benchmarks

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

309,131 benchmarksPage 1700 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
Entity Regression (post-votes)rel-stacknlp19May 25, 2026
Subgroup DiscoveryMNIST Digit 7 (test)tabular time series19May 21, 2026
Video GenerationVBench extended promptsvideo generation editing19May 21, 2026
Video GenerationVBenchvideo generation editing19May 21, 2026
Image Classificationm-bigearthnet (test)computer vision19May 21, 2026
Industrial Anomaly DetectionMVTec, MPDD, VisA, DTD, and SDD Aggregatecomputer visiontabular time series19May 21, 2026
Industrial Anomaly DetectionSDDcomputer visiontabular time series19May 21, 2026
Industrial Anomaly DetectionDTDcomputer visiontabular time series19May 21, 2026
Industrial Anomaly DetectionVisAcomputer visiontabular time series19May 21, 2026
Industrial Anomaly DetectionMPDDcomputer visiontabular time series19May 21, 2026
Industrial Anomaly DetectionMVTec ADcomputer visiontabular time series19May 21, 2026
Action RecognitionFogAct 1.0 (test)computer vision19May 21, 2026
Object TrackingHOTC2020 (test)computer vision19May 21, 2026
Referring Video Object SegmentationMeViS v1computer visionmultimodal19May 20, 2026
Open-vocabulary 3D segmentationLERF-Mask (test)3d vision geometrycomputer vision19May 29, 2026
Graph Anomaly DetectionDBLPgraph19May 27, 2026
Mathematical ReasoningMATH 500llm chat instructionnlp19Jun 30, 2026
Visual Question AnsweringOK-VQA standard (test)multimodalcomputer vision+119May 20, 2026
Action recognitionNTU120 (5-fold)computer vision19May 20, 2026
Action recognitionFPHA (5-fold)computer vision19May 20, 2026
Action recognitionHDM05 (5-fold)computer vision19May 20, 2026
Real-world visual perceptionMME-RealWorld CNcomputer vision19May 19, 2026
Real-world visual perceptionMME-RealWorld Litecomputer vision19May 19, 2026
Zoom-dependent visual question answeringZoomBenchcomputer visionmultimodal19May 19, 2026
Visual perception of small objectsV* Benchcomputer vision19May 19, 2026