List your company

Research

Benchmarks

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

309,131 benchmarksPage 2085 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
ClassificationImageNet-9 Backgrounds Challengecomputer visionnlp+317Apr 2, 2026
Image ClassificationImageNet-1K (val)computer vision17Feb 26, 2026
Co-saliency DetectionCoCA (test)computer vision17Feb 26, 2026
Movie Audio Description generationMAD-eval-Named v2 (test)multimodalspeech audio17Feb 26, 2026
Zero-Shot Sketch-Based Image RetrievalSketchycomputer visionretrieval search rag17Feb 26, 2026
NavigationD4RL antmaze-large-diverse (antmaze-l-d)robotics embodied ai17Feb 26, 2026
NavigationD4RL antmaze-large-play (antmaze-l-p)robotics embodied ai17Feb 26, 2026
Sketch-Based Image RetrievalSketchy Extcomputer visionmultimodal17Feb 26, 2026
Sketch-Based Image RetrievalTU-Berlin Extcomputer visionmultimodal17Feb 26, 2026
Depth-from-DefocusNYUv2 (test)3d vision geometrycomputer vision17Feb 26, 2026
Novel view synthesisZJUMocap unseen identity3d vision geometry17Feb 26, 2026
Manipulation detectionFakeAVCeleb (AVG-FV)computer vision17Feb 26, 2026
Manipulation detectionFakeAVCeleb FVFA-WLcomputer vision17Feb 26, 2026
Manipulation detectionFakeAVCeleb FVFA-GANcomputer vision17Feb 26, 2026
Manipulation detectionFakeAVCeleb (FVFA-FS)computer vision17Feb 26, 2026
Manipulation detectionFakeAVCeleb FVRA-WLcomputer vision17Feb 26, 2026
Object DetectionOCHuman (test)computer vision17Feb 26, 2026
Object DetectionOCHuman (val)computer vision17Feb 26, 2026
ClassificationBDGPcomputer visionnlp+317Feb 26, 2026
Video Quality AssessmentDIVIDE-3kcomputer vision17Feb 26, 2026
Novel View SynthesisMonoCap (test)3d vision geometry17Feb 26, 2026
Blind Image Quality AssessmentBID (test)computer vision17Feb 26, 2026
Accuracy PredictionNAS-Bench-101 depth=2~7, Test Samples=all 1.0miscellaneous17Feb 27, 2026
Deepfake DetectionFaceForensics++ LQcomputer visionadversarial safety security17Apr 15, 2026
Slide-Level ClassificationTCGA-BRCA (10-fold cross-validation)bio medicalcomputer vision17Feb 26, 2026