List your company

Research

Benchmarks

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

309,131 benchmarksPage 699 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
Referring Expression SegmentationRefCOCO+ UMD (testB)computer visionmultimodal34May 28, 2026
Referring Expression SegmentationRefCOCO+ UMD (testA)computer visionmultimodal34May 28, 2026
Referring Expression SegmentationRefCOCO+ UMD (val)computer visionmultimodal34May 28, 2026
Referring Expression SegmentationRefCOCO UMD (testB)computer visionmultimodal34May 28, 2026
Mathematical ReasoningDeepScaleRllm chat instructionnlp34Jun 30, 2026
Image ClassificationMNIST (test)computer vision34Jul 7, 2026
Overall PerformanceAggregate 9 benchmarksnlp34Jul 3, 2026
ClassificationOCTMNISTcomputer visionnlp+334May 27, 2026
ClassificationLC25000computer visionnlp+334May 27, 2026
ClassificationCTKIDNEYcomputer visionnlp+334May 27, 2026
Proactive Action PredictionABCD+tabular time series34May 26, 2026
Multi-turn DialogueMT-Benchllm chat instruction34May 26, 2026
Joint Entity and Relation ExtractionWebNLGnlp34May 25, 2026
DialogueIFEvalllm chat instructionnlp34May 22, 2026
DialogueAlpacaEval 2llm chat instructionnlp34May 22, 2026
Myocardial Infarction LocalizationMyocardial Infarction Localization (internal)bio medicalcomputer vision34May 22, 2026
Text-to-Image GenerationInitNOimage generation editing34May 20, 2026
Multi-task Unlearning InterferenceNYU v2computer visionadversarial safety security34May 20, 2026
Continual LearningKQA → Math → Code → MQA Task-level streammiscellaneous34May 19, 2026
Continual LearningMulti-hop QA Domain-level streammiscellaneous34May 19, 2026
Continual LearningCode Domain-level streammiscellaneous34May 19, 2026
Continual LearningMath Domain-level streammiscellaneous34May 19, 2026
Continual LearningKnowledge QA Domain-level streammiscellaneous34May 19, 2026
Visual Question AnsweringMMStar (test)multimodalcomputer vision+134Jun 9, 2026
Text-to-Video GenerationEvalCraftervideo generation editing34May 19, 2026