List your company

Research

Benchmarks

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

309,131 benchmarksPage 1978 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
Zero-shot classificationAwA 10-way 0-shot conventional settingnlpcomputer vision18Feb 26, 2026
Ground-to-Aerial Image SynthesisDayton 64x64image generation editing18Feb 26, 2026
Aerial-to-Ground Image SynthesisDayton 64x64image generation editing18Feb 26, 2026
11-class movement classificationEEG-EMG Inter-subjectbio medicaltabular time series18Feb 26, 2026
Human ParsingCIHPcomputer vision18Feb 26, 2026
Multi-label ClassificationMS-COCO 2014 (val)computer visionnlp+218Feb 26, 2026
Facial Beauty PredictionSCUT-FBPcomputer vision18Mar 19, 2026
Local Descriptor Matching3DMatch 1.0 (test)3d vision geometrycomputer vision18Feb 26, 2026
Question AnsweringSQuAD hidden 1.1 (test)nlp18Feb 26, 2026
Action RecognitionJIGSAWS Suturing (LOSO)computer vision18Feb 26, 2026
Gender RecognitionCelebA (test)computer vision18Feb 26, 2026
Text-to-Image GenerationCOCO (test)image generation editing18Apr 20, 2026
pixel-by-pixel classificationMNIST unpermuted pixel-by-pixel (test)computer vision18Feb 26, 2026
Gender ClassificationAdience (cross-validation)computer vision18Feb 26, 2026
Salient Object DetectionSODcomputer vision18Feb 26, 2026
Salient Object DetectionDUTS (TE)computer vision18Feb 26, 2026
Natural Language InferenceMultiNLI matched (in-domain) RepEval 2017 (test)nlp18Feb 26, 2026
3D Human Pose EstimationHumanEva-I (Walking)3d vision geometrycomputer vision18Feb 26, 2026
Shot Boundary DetectionTRECVID 2007 (test)computer vision18Feb 26, 2026
20-way Few-shot ClassificationOmniglot (test)computer visionnlp18Feb 26, 2026
Generative Question AnsweringMsMARCO (test)nlpllm chat instruction18Feb 26, 2026
Individual Treatment Effect EstimationJobs (within-sample)tabular time series18Feb 26, 2026
Semantic SegmentationSemantic3D reduced v1 (test)computer vision18Feb 26, 2026
Short Text ClusteringBiomedicalnlp18Feb 26, 2026
Individual Action RecognitionVolleyball datasetcomputer vision18Feb 27, 2026