List your company

Research

Benchmarks

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

309,131 benchmarksPage 1256 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
Image ClassificationCombined Classification Suite Averagecomputer vision24Feb 26, 2026
Biomedical Image ClassificationOpenSRH 1.0 (test)bio medicalcomputer vision24Feb 26, 2026
Video UnderstandingMLVU (dev)computer vision24Jun 9, 2026
Video Compression1920 x 1080 videosvideo generation editing24Feb 26, 2026
Video RecognitionSomething-Something V2computer vision24Jun 25, 2026
Survival PredictionTCGA-STAD (test)bio medicaltabular time series24Feb 26, 2026
Multitask Language UnderstandingMMLUnlpllm chat instruction24Feb 26, 2026
Drug trafficking detectionTwitter-HetDrug 40% label setting (train)bio medicalnlp24Feb 26, 2026
Drug trafficking detectionTwitter-HetDrug 20% label setting (train)bio medicalnlp24Feb 26, 2026
Drug trafficking detectionTwitter-HetDrug 10% label setting (train)bio medicalnlp24Feb 26, 2026
Anomaly DetectionBrainMRItabular time series24Feb 26, 2026
Workflow ExtractionSynthABCDnlp24Feb 26, 2026
Workflow ExtractionABCDnlp24Feb 26, 2026
Offline Reinforcement Learningwalker2d Mixed Datasetrobotics embodied ai24Feb 26, 2026
Offline Reinforcement Learninghopper Mixed Datasetrobotics embodied ai24Feb 26, 2026
Offline Reinforcement Learninghalfcheetah Mixed Datasetrobotics embodied ai24Feb 26, 2026
Domain AdaptationImageNet Domain Adaptationcomputer visionnlp+124Feb 26, 2026
Image ClassificationCIFAR-100 VTAB-1Kcomputer vision24Feb 26, 2026
Explanation FaithfulnessEmotioncomputer vision24Feb 26, 2026
Explanation FaithfulnessSNLIcomputer vision24Feb 26, 2026
Explanation FaithfulnessMed-BIOScomputer vision24Feb 26, 2026
Explanation FaithfulnessSST-2computer vision24Feb 26, 2026
Video CompressionUVG standard (full)video generation editing24Feb 26, 2026
Anomaly detectionFacebooktabular time series24May 27, 2026
Context-faithful Question AnsweringConFiQAretrieval search ragnlp24Feb 26, 2026