List your company

Research

Benchmarks

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

309,131 benchmarksPage 1719 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
3D Object DetectionDAIR-V2X (test)3d vision geometrycomputer vision19Mar 25, 2026
3D Object DetectionOPV2V v1 (test)3d vision geometrycomputer vision19Mar 25, 2026
Zero-shot Language ModelingStandard Language Modeling Suite WikiText-103, LAMBADAnlp19Jun 9, 2026
Multimodal Time Series ForecastingEconomytabular time seriesmultimodal19May 12, 2026
Web Agent NavigationWebArenaagents tool userobotics embodied ai19May 26, 2026
Dialectal Bias EvaluationBengali Dialectal Question Setsnlpllm chat instruction19Mar 24, 2026
Text-to-Image GenerationDrawbenchimage generation editing19Mar 24, 2026
Thyroid Nodule SegmentationThyroidXLcomputer visionbio medical19Jul 2, 2026
Theorem-provingProver-Benchmiscellaneous19Mar 24, 2026
Hierarchical Table Question AnsweringHiTabnlptabular time series19Jun 11, 2026
Depth Super-ResolutionRGB-D-D Bicubic downsampling synthetic (test)3d vision geometry19Mar 24, 2026
Semantic SegmentationPascal VOC (1/7 labeled)computer vision19Mar 24, 2026
Gaze EstimationEyeDiapcomputer vision19May 4, 2026
Time Series ClassificationHealthcare MT (test)tabular time series19Mar 24, 2026
Time Series ClassificationHealthcare TP (test)tabular time series19Mar 24, 2026
Time Series ClassificationFinance (test)tabular time series19Mar 24, 2026
Time Series ClassificationWeather (test)tabular time series19Mar 24, 2026
Time series regressionFinance dataset (test)tabular time series19Mar 24, 2026
MaxCutGSET (|V|=1K)graph19May 26, 2026
MaxCutGSET (|V|=800)graph19May 26, 2026
Point Cloud ReconstructionScanObjectNN target domain (Evaluation)3d vision geometry19Apr 6, 2026
Information Retrievalnewsretrieval search rag19Mar 24, 2026
Information Retrievalrobustretrieval search rag19Mar 24, 2026
Information Retrievalscifactretrieval search rag19Mar 24, 2026
Information Retrievalnfcorpusretrieval search rag19Mar 24, 2026