List your company

Research

Benchmarks

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

309,131 benchmarksPage 672 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
Image ClassificationAggregate of 9 benchmarks (CIFAR10, CIFAR100, EuroSAT, OxfordPet, Flowers102, Food101, SUN397, DTD, Caltech101) Few-shotcomputer vision35May 28, 2026
Graph Anomaly DetectionYelpChigraph35May 28, 2026
Graph Anomaly DetectionAmazongraph35May 28, 2026
Commonsense ReasoningCommonsense Reasoning Suite (ARC-c, BoolQ, PIQA, HellaSwag, WinoGrande) zero-shotnlp35May 27, 2026
Personalized generationMemoryCD Booksllm chat instruction35May 27, 2026
Bivariate scaling behavior extrapolationImagenettabular time series35May 27, 2026
Bivariate scaling behavior extrapolationCarstabular time series35May 27, 2026
Bivariate scaling behavior extrapolationBirdstabular time series35May 27, 2026
Graph Anomaly DetectionCiteseergraph35May 26, 2026
ForecastingETTm2tabular time series35Jul 3, 2026
Image RestorationSimulation Datasetcomputer vision35May 26, 2026
Image DenoisingW2Scomputer vision35Jun 23, 2026
PlanningBlocksworld (test)robotics embodied ai35Jul 7, 2026
Language ModelingShakespeare 1M params (val)nlp35May 25, 2026
Question AnsweringNQ Poison Attack (test)nlp35May 25, 2026
3D Reconstruction50-scene evaluation benchmark (CO3Dv2, DL3DV-10K, GTA-SfM, ScanNet++, TartanAir) v2 (held-out evaluation views)3d vision geometry35May 22, 2026
Mathematical ReasoningGSM8kllm chat instructionnlp35May 22, 2026
Composed Image RetrievalFashion-IQ Averagecomputer visionnlp35Jul 3, 2026
Task ClassificationAWA Incmiscellaneous35May 21, 2026
Task ClassificationCUB Incmiscellaneous35May 21, 2026
Task ClassificationAWAmiscellaneous35May 21, 2026
Aerodynamic Shape OptimizationShapeBench All tasksmiscellaneous35May 21, 2026
Infrared Small-Target DetectionSIRST 3computer vision35May 21, 2026
Question AnsweringNQnlp35May 20, 2026
Question AnsweringSQuADnlp35May 20, 2026