List your company

Research

Benchmarks

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

309,131 benchmarksPage 2122 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
OCR & Document UnderstandingInfoVQA pt-PTcomputer visionnlp16Jun 18, 2026
OCR & Document UnderstandingDocVQA pt-PTcomputer visionnlp16Jun 18, 2026
OCR & Document UnderstandingTxtVQA pt-PTcomputer visionnlp16Jun 18, 2026
OCR & Document UnderstandingOCR pt-PTcomputer visionnlp16Jun 18, 2026
General VQARWQA pt-PTmultimodalcomputer vision+116Jun 18, 2026
General VQAPOPE pt-PTmultimodalcomputer vision+116Jun 18, 2026
General VQASEED pt-PTmultimodalcomputer vision+116Jun 18, 2026
General VQAMMPro pt-PTmultimodalcomputer vision+116Jun 18, 2026
General VQAMMStar pt-PTmultimodalcomputer vision+116Jun 18, 2026
General VQAMMMU pt-PTmultimodalcomputer vision+116Jun 18, 2026
General VQAMME pt-PTmultimodalcomputer vision+116Jun 18, 2026
RerankingMMTEBretrieval search rag16Jun 18, 2026
Absolute Trajectory Error (ATE) EstimationAquaticVision3d vision geometry16Jun 18, 2026
Behavioral AccuracyNatural Voice and Free Generation datasetllm chat instruction16Jun 18, 2026
Anomaly DetectionSMD 28tabular time series16Jun 18, 2026
Anomaly DetectionMSLtabular time series16Jun 18, 2026
Anomaly DetectionSMAP (55)tabular time series16Jun 18, 2026
Multivariate Time Series Anomaly DetectionAll MTSAD benchmarks Overalltabular time series16Jun 18, 2026
Multivariate Time Series Anomaly DetectionMulti-trace MTSAD benchmarks SMAP MSL SMDtabular time series16Jun 18, 2026
Multivariate Time Series Anomaly DetectionSingle-trace MTSAD benchmarks (SWaT, WaDi, PSM)tabular time series16Jun 18, 2026
Multivariate Time Series Anomaly DetectionPSMtabular time series16Jun 18, 2026
Anomaly DetectionQAPPD 16 (test)tabular time series16Jun 18, 2026
Model EditingMemorized Sequences subsampled for comparability (train)llm chat instructionnlp16Jun 18, 2026
Low light image enhancementLOLcomputer vision16Jun 26, 2026
Pragmatic ReasoningMETOQAnlp16Jun 18, 2026