List your company

Research

Benchmarks

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

309,131 benchmarksPage 2086 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
Climate ForecastingICAR-ENSO (test)tabular time series17Feb 26, 2026
Generalized Few-Shot Object DetectionMS-COCO 5-shot (test)computer vision17Feb 26, 2026
Raw Image ReconstructionAdobeFiveK (test)computer vision17Jun 24, 2026
Semantic SegmentationnuImagescomputer vision17Feb 26, 2026
Per-segment sleep apnea detectionApnea-ECGbio medicaltabular time series17Feb 26, 2026
Object DetectionPASCAL VOC 07+12 (trainval)computer vision17Feb 26, 2026
Offline Reinforcement LearningD4RL HalfCheetah medium-expert v2robotics embodied ai17Jun 2, 2026
Object DetectionV100 GPU (test)computer vision17Feb 26, 2026
Sign Language RecognitionWLASL (test)computer visionspeech audio17Feb 26, 2026
Snitch LocalizationCATER Snitch localization 1.0 (test)computer vision17Feb 26, 2026
Named Entity RecognitionNER Average over all languages (test)nlp17Jun 2, 2026
ClassificationMMLU (test)computer visionnlp+317Feb 26, 2026
GenerationBig-Bench Hard (test)llm chat instruction17Feb 26, 2026
Multi-Person Pose EstimationCOCO 2017 (mini-val)computer vision17Feb 26, 2026
Text-to-Audio GenerationClotho (test)speech audioimage generation editing17Feb 26, 2026
3D Lane DetectionOpenLane3d vision geometrycomputer vision17Feb 26, 2026
Image ClassificationImageNet original (val)computer vision17Feb 26, 2026
Speech RecognitionCommon Voicespeech audio17Feb 26, 2026
Video Super-ResolutionRealMCVSR (test)video generation editingcomputer vision17Feb 26, 2026
Autonomous DrivingCARLA 42 routesrobotics embodied aicomputer vision17Feb 26, 2026
Code GenerationARCADE New Taskscode developer ai17Feb 26, 2026
Code GenerationARCADE Existing Taskscode developer ai17Feb 26, 2026
Automatic Speech RecognitionAISHELL-2 iOS (test)speech audio17Mar 27, 2026
Video GenerationUCF101 128x128 16 framesvideo generation editing17Feb 26, 2026
Video Question AnsweringMSRVTT Open Ended (OE)multimodalcomputer vision17Feb 26, 2026