List your company

Research

Benchmarks

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

309,131 benchmarksPage 583 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
Human Activity RecognitionHHARcomputer vision39Jul 7, 2026
Binary Classificationincome IC 1995 (test)tabular time series39Feb 26, 2026
Incremental LearningCIFAR100 10 stepscomputer visiontabular time series39Feb 26, 2026
Full-Reference Image Quality AssessmentCSIQ-IQA (test)computer vision39Apr 23, 2026
HSI ReconstructionKAIST 10 scenes (Scene2)computer vision39Feb 26, 2026
Handwritten Mathematical Expression RecognitionCROHME 2019computer visionnlp39Feb 26, 2026
Image ClassificationSVHN 1000 labelscomputer vision39Mar 19, 2026
Class-Incremental Continual LearningCIFAR-10 Sequentialcomputer visiontabular time series39Feb 26, 2026
ClassificationLRA ListOps N=2000 (test)computer visionnlp+339Feb 26, 2026
Table Structure RecognitionPubTabNet (val)computer visionnlp39Jun 17, 2026
Semantic SegmentationCOCOStuff 164Kcomputer vision39Jun 4, 2026
3D Object DetectionScanNet v2 (test)3d vision geometrycomputer vision39Apr 20, 2026
Lane DetectionCULanecomputer vision39Feb 26, 2026
Semantic SegmentationStanford2D3D-Panoramic (SPan) v1 (averaged by 3 folds)computer vision39Feb 26, 2026
Simultaneous Speech TranslationMuST-C EN-DE (tst-COMMON)speech audionlp39Mar 19, 2026
Image ClassificationCIFAR-10computer vision39Feb 26, 2026
Long-tailed Visual RecognitioniNaturalist 2018 (test)computer vision39Feb 26, 2026
Out-of-distribution DetectionImageNet-1k vs iNaturalist (test)computer visiontabular time series39Feb 26, 2026
Data-to-text evaluationSFRESnlp39May 13, 2026
Commonsense GenerationCommonGen (test)nlp39May 11, 2026
Scene Graph DetectionVG150computer visionmultimodal39Apr 27, 2026
Nuclei Instance SegmentationPanNukecomputer visionbio medical39Feb 26, 2026
Anomaly detectionHyper-Kvasirtabular time series39Feb 26, 2026
5-way Few-shot Classificationtiered-ImageNetcomputer visionnlp+139Feb 26, 2026
Feature Attribution EvaluationImageNet standard (val)computer vision39Feb 26, 2026