List your company

Research

Benchmarks

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

309,131 benchmarksPage 1739 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
Multi-Discipline ReasoningMMMUllm chat instruction19Feb 26, 2026
Table-to-Image GenerationTableVisBench v1 (test)image generation editingnlp19Feb 26, 2026
Knowledge-based Visual Question AnsweringINFOSEEK (Unseen Entity)multimodalnlp19Apr 10, 2026
Autonomous DrivingBench2Drive base (train)robotics embodied aicomputer vision19Feb 26, 2026
Binary classificationMMADtabular time series19Feb 26, 2026
Overall Survival PredictionTCGA-LUSC Lung Squamous Cell Carcinoma N = 434 (5-fold cross-validation)bio medicaltabular time series19Feb 26, 2026
Mathematical ReasoningMathVista Mathllm chat instructionnlp19Feb 26, 2026
Embodied Question AnsweringEpisodic Memory EQA (EM-EQA)robotics embodied aicomputer vision19Apr 7, 2026
Video RecommendationMicroLens 100k (test)nlp19Feb 26, 2026
Novel View SynthesisACID 16-view (test)3d vision geometry19Mar 27, 2026
Few-shot Object CountingFSC147 1.0 (test)computer vision19Feb 26, 2026
Few-shot Object CountingFSC147 1.0 (val)computer vision19Feb 26, 2026
Image Anomaly DetectionMVTec AD Holecomputer vision19Feb 26, 2026
Ship Re-identificationHOSS-ReID (All)computer vision19Feb 26, 2026
Anomaly Detection and LocalizationMU-Glioma-Post (test)computer visiontabular time series19Feb 26, 2026
Image ClassificationCamelyon 17 (test)computer vision19Apr 27, 2026
Salient Object DetectionVT1000computer vision19Feb 26, 2026
Chart UnderstandingChartQAcomputer visionnlp19Feb 26, 2026
Image ClassificationCelebA WILDS (test)computer vision19Mar 20, 2026
Text-to-Image GenerationMS-COCO 10K prompts 2014 (val)image generation editing19Feb 26, 2026
Lifelong Person Re-identificationCUHK03computer vision19Feb 26, 2026
Lifelong Person Re-identificationMSMT17computer vision19Feb 26, 2026
Lifelong Person Re-identificationDukeMTMCcomputer vision19Feb 26, 2026
Lifelong Person Re-identificationCUHK-SYSUcomputer vision19Feb 26, 2026
Lifelong Person Re-identificationMarket1501computer vision19Feb 26, 2026