List your company

Research

Benchmarks

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

309,131 benchmarksPage 1806 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
Area SearchArea Search Scenariorobotics embodied ai18Jun 5, 2026
SearchSimulated Search Environmentretrieval search rag18Jun 5, 2026
Blur PredictionRadiographs SOD 24.8mmcomputer vision18Jun 5, 2026
Scientific ReasoningSciKnowEval L3nlp18Jun 4, 2026
Graph ClassificationPascalVOC-SP (test)graph18Jun 4, 2026
Graph ClassificationCOCO-SP (test)graph18Jun 4, 2026
Node ClassificationRoman-empiregraph18Jun 4, 2026
Node ClassificationQuestionsgraph18Jun 4, 2026
Node ClassificationQuestionsgraph18Jun 4, 2026
Anomaly DetectionHDFStabular time series18Jun 9, 2026
Object RecognitionOffice-31computer vision18Jun 4, 2026
Landmark DetectionShenzhen (test)computer vision18Jun 4, 2026
Person understanding and persistent memoryCUPIDllm chat instruction18Jun 4, 2026
Person understanding and persistent memoryRealPrefllm chat instruction18Jun 4, 2026
Person understanding and persistent memoryKnowMellm chat instruction18Jun 4, 2026
Downstream EvaluationSEA-HELMllm chat instructionnlp+1418Jun 4, 2026
Collaborative 3D Object DetectionOPV2V-H (test)3d vision geometrycomputer vision18Jun 4, 2026
Collaborative 3D Object DetectionV2X-Real (test)3d vision geometrycomputer vision18Jun 4, 2026
Multi-hop Question AnsweringBamboogle out-of-domainnlpretrieval search rag18Jun 4, 2026
Multi-hop Question AnsweringMuSiQue (out-of-domain)nlpretrieval search rag18Jun 4, 2026
Question AnsweringPopQA out-of-domainnlp18Jun 4, 2026
Image CaptioningCOCO full (val)multimodalcomputer vision+118Jun 4, 2026
Visual Question AnsweringOK-VQA full (val)multimodalcomputer vision+118Jun 4, 2026
Time Series ForecastingBeijing PM2.5 (test)tabular time series18Jun 4, 2026
ClusteringCCV20tabular time series18Jun 4, 2026