List your company

Research

Benchmarks

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

309,131 benchmarksPage 2019 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
Instrument SegmentationEndoVis 2017 (t=1) & 2018 (t=2) (test)computer visionbio medical17Apr 6, 2026
Instrument SegmentationCholecSeg8k M2CAI-Seg (last episode)computer visionbio medical17Apr 6, 2026
3D Visual Question AnsweringScanQA3d vision geometrycomputer vision+117May 7, 2026
Medical Visual Question AnsweringSLAKE Closedmultimodalbio medical17Apr 6, 2026
Revenue Uplift ModelingSynthetic Datasettabular time series17Apr 6, 2026
Action UnderstandingMMT-47 Action Understandingcomputer vision17Apr 6, 2026
Object Motion and Spatial ReasoningMMT-47 Object Motion & Spatialcomputer visionmultimodal17Apr 6, 2026
High Level ReasoningMMT-47 High Level Reasoningllm chat instruction17Apr 6, 2026
Natural Language UnderstandingGLUEnlp17Apr 6, 2026
Commonsense ReasoningMMT-47 Commonsense Reasoningnlp17Apr 6, 2026
Image ClassificationMMT-47computer vision17Apr 6, 2026
Vision UnderstandingMMT-47 Vision Benchmarkcomputer visionmultimodal17Apr 6, 2026
OS agent GUI interactionVeriOS-Benchagents tool userobotics embodied ai17Apr 6, 2026
Textual Emotion AnalysisDFEC internally curated 2025 (test)nlp17Apr 6, 2026
Visual Spatial PlanningVSP (test)robotics embodied aicomputer vision+117Jun 4, 2026
Node classificationSquirrel Poisonedgraph17Apr 3, 2026
Node classificationChameleon Poisonedgraph17Apr 3, 2026
Node classificationActor Poisonedgraph17Apr 3, 2026
Node classificationPubmed Poisonedgraph17May 8, 2026
Node classificationCiteseer Poisonedgraph17May 8, 2026
Node classificationCora Poisonedgraph17Apr 3, 2026
Referring Expression ComprehensionKVG-Benchcomputer visionnlp17Apr 3, 2026
rPPG estimationUBFC-rPPGcomputer visionbio medical17Apr 3, 2026
Label shift estimationMNIST Dirichlet shift alpha=10 (val size=2000)tabular time series17Apr 3, 2026
Label shift estimationMNIST Dirichlet shift alpha=10 size=1500 (val)tabular time series17Apr 3, 2026