List your company

Research

Benchmarks

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

309,131 benchmarksPage 2116 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
Medical Image ClassificationOrganSMNIST v2 (test)bio medicalcomputer vision16Jun 23, 2026
Math Mistake RemediationMath Mistake Remediation Datasetllm chat instructionnlp16Jun 23, 2026
Speech EnhancementDNS blind (real recordings) 2020 (test)speech audio16Jun 23, 2026
Speech EnhancementDNS blind synthetic with reverb 2020 (test)speech audio16Jun 23, 2026
Vision-Language CompositionalityVisMin Hard (test)multimodalcomputer vision+116Jun 23, 2026
Compositional ReasoningVisMin Easy (test)computer visionnlp16Jun 23, 2026
Mathematical ReasoningMinerva-Mathllm chat instructionnlp16Jun 30, 2026
Overall Performance EvaluationAggregate All Domainsmultimodalllm chat instruction+216Jun 23, 2026
Knowledge Question AnsweringHLEnlpretrieval search rag16Jun 23, 2026
Air Quality RegressionAir Quality R-212 → R-69, NO2tabular time series16Jun 23, 2026
Time-series Anomaly DetectionMixture 8.9tabular time series16Jun 23, 2026
Time-series Anomaly DetectionShapelet 7.4tabular time series16Jun 23, 2026
Time-series Anomaly DetectionShapelet 4.9tabular time series16Jun 23, 2026
Time-series Anomaly DetectionSeasonal 4.8tabular time series16Jun 23, 2026
Time-series Anomaly DetectionContextual 4.9tabular time series16Jun 23, 2026
Time-series Anomaly DetectionASDtabular time series16Jun 23, 2026
Time-series Anomaly DetectionSMAPtabular time series16Jun 23, 2026
Time-series Anomaly DetectionSWATtabular time series16Jun 23, 2026
Time-series Anomaly DetectionSMDtabular time series16Jun 23, 2026
Time-series Anomaly DetectionPSMtabular time series16Jun 23, 2026
Time-series Anomaly DetectionNYCtabular time series16Jun 23, 2026
Time-series Anomaly DetectionGenesistabular time series16Jun 23, 2026
Time-series Anomaly DetectionGECCOtabular time series16Jun 23, 2026
Time-series Anomaly DetectionCalIt2tabular time series16Jun 23, 2026
Time-series Anomaly DetectionCICIDStabular time series16Jun 23, 2026