List your company

Research

Benchmarks

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

309,131 benchmarksPage 267 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
Video CompressionHEVC Class Bvideo generation editing63Mar 11, 2026
Video Polyp SegmentationSUN-SEG Easy (Seen)computer vision63Jun 19, 2026
Causal ReasoningCOPAnlp63Jun 4, 2026
Node ClassificationACMgraph63Jun 8, 2026
Argument ClassificationACE05-E (test)nlp63Feb 26, 2026
Optical FlowMPI Sintel (train)computer vision63Feb 26, 2026
Image ClassificationCIFAR100 (test)computer vision63May 12, 2026
Facial Expression RecognitionAffectNet 7 classescomputer vision63Jun 9, 2026
3D instance segmentationScanNet2003d vision geometrycomputer vision63Apr 15, 2026
Time Series ClassificationEthanolConcentrationtabular time series63May 4, 2026
Domain GeneralizationOffice-Homecomputer vision63Feb 26, 2026
3D Object DetectionONCE (val)3d vision geometrycomputer vision63May 18, 2026
Vision-and-Language NavigationR2R-CE (test-unseen)robotics embodied aimultimodal63Mar 17, 2026
ClassificationCreditcomputer visionnlp+363May 28, 2026
Text-to-Video RetrievalMSRVTT 1k (test)multimodalretrieval search ragText-to-Video Retrieval on MSRVTT 1k (test) performance trend63Feb 26, 2026
Action ClassificationKinetics-400 (val)computer vision63Feb 26, 2026
Question AnsweringSQuADnlp63May 6, 2026
Double JPEG Image RestorationLIVE1 grayscale (test)computer vision63Feb 26, 2026
Offline Reinforcement LearningD4RL Gym walker2d mediumrobotics embodied ai63May 29, 2026
Extreme Multi-label ClassificationAmazon-670Knlptabular time series63Jun 2, 2026
Text-to-image RetrievalFlickr30k (1K)multimodalretrieval search rag63Apr 13, 2026
Document rankingTREC DL Track 2020 (test)retrieval search rag63Apr 13, 2026
Video-to-Text RetrievalActivityNet (test)multimodalVideo-to-Text Retrieval on ActivityNet (test) performance trend63Feb 26, 2026
Fine-Grained Sketch-Based Image Retrieval (FG-SBIR)Shoe V2 (test)computer visionmultimodal63Feb 26, 2026
Image GenerationCIFAR100image generation editing63Apr 2, 2026