List your company

Research

Benchmarks

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

309,131 benchmarksPage 2016 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
Image Quality AssessmentMin 19computer vision17Apr 14, 2026
Image Quality AssessmentLiu 13computer vision17Apr 14, 2026
Image ClassificationCO2 Farm Thermal Gas Dataset 1.0 (test)computer vision17Apr 14, 2026
Boundary DetectionCO2 Farm Thermal Gas Dataset 1.0 (test)computer vision17Apr 14, 2026
Semantic SegmentationCO2 Farm Thermal Gas Dataset 1.0 (test)computer vision17Apr 14, 2026
Temporal Knowledge Graph Entity ExtrapolationICEWS 18 short (test)graphnlp17Apr 14, 2026
Long-context Multi-modal UnderstandingMMLongBenchmultimodalllm chat instruction17Apr 13, 2026
Multi-view ClassificationLeavescomputer vision17May 26, 2026
Multi-view ClassificationLandUsecomputer vision17May 26, 2026
Multi-view ClassificationScenecomputer vision17May 26, 2026
Multivariate Time Series ClassificationUEA 10tabular time series17Apr 13, 2026
Face Anti-SpoofingDG-FAS Average protocolcomputer vision17Apr 13, 2026
Face Anti-SpoofingDG-FAS ICM to O protocolcomputer vision17Apr 13, 2026
Face Anti-SpoofingDG-FAS OCM to I protocolcomputer vision17Apr 13, 2026
Face Anti-SpoofingDG-FAS OMI to C protocolcomputer vision17Apr 13, 2026
Face Anti-SpoofingDG-FAS OCI to M protocolcomputer vision17Apr 13, 2026
Multi-Task LearningQM9computer vision3d vision geometry+117Apr 13, 2026
Multi-Task LearningCelebAcomputer vision3d vision geometry+117Apr 13, 2026
Verilog Code GenerationRTLLM v2.0code developer ai17Apr 13, 2026
Multi-hop Question AnsweringBamboogle (dev test)nlpretrieval search rag17Apr 10, 2026
Multi-hop Question AnsweringMusique (dev test)nlpretrieval search rag17Apr 10, 2026
Multi-hop Question Answering2WikiMultiHopQA (dev test)nlpretrieval search rag17Apr 10, 2026
Multi-hop Question AnsweringHotpotQA (dev test)nlpretrieval search rag17Apr 10, 2026
Micro-expression recognitionFullcomputer vision17Apr 10, 2026
Extra Long Video RetrievalVideoNIAHretrieval search ragcomputer vision17Apr 10, 2026