List your company

Research

Benchmarks

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

309,131 benchmarksPage 1627 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
Multimodal RecommendationBeauty & Personal Caremultimodalnlp20Feb 26, 2026
Multimodal RecommendationToys & Gamesmultimodalnlp20Feb 26, 2026
Multimodal RecommendationSports & Outdoorsmultimodalnlp20Feb 26, 2026
RetrievalBRIGHT 12 datasets aggregate (test)retrieval search rag20Feb 26, 2026
Rank Correlation AnalysisAcross-dataset aggregate 96 datasets (test)tabular time series20Feb 26, 2026
Joint Video Super-Resolution and DeblurringREDS4-ME 5:5 exposure level (test)computer vision20Feb 26, 2026
Joint Video Super-Resolution and DeblurringREDS4-ME 5:4 exposure level (test)computer vision20Feb 26, 2026
Image EditingGEdit-Bench ENimage generation editing20May 19, 2026
Action-Conditioned Person Grounded ReasoningKnow-Show (test)computer visionnlp20Feb 26, 2026
Multimodal Sentiment ClassificationCH-SIMS 1.0 (test)multimodalnlp20May 21, 2026
Low-light Image EnhancementDICMcomputer vision20Jul 7, 2026
Jailbreak attackSafebench (test)adversarial safety security20Feb 26, 2026
Jailbreak AttackSafety Evaluation Benchmark Harmful Categoriesadversarial safety security20Feb 26, 2026
Visual Question AnsweringTextVQAmultimodalcomputer vision+120Mar 30, 2026
Image ClassificationOffice-31 Amazon domain (test)computer vision20Feb 26, 2026
Fine-grained Visual PerceptionV-Starcomputer vision20Apr 15, 2026
Depth EstimationNYU3d vision geometry20Feb 26, 2026
Identity SimilarityFFHQ Transformations (train)computer vision20Feb 26, 2026
Visual Question AnsweringVQA v2multimodalcomputer vision+120Mar 17, 2026
Artistic Style RenderingS24 (test)image generation editing20Feb 26, 2026
3D Visual Question AnsweringOMNI3D BENCH3d vision geometrycomputer vision+120Mar 24, 2026
3D Visual GroundingNr3D (val)3d vision geometrycomputer vision20Jul 7, 2026
UHD EnhancementUHD-LLcomputer vision20Mar 16, 2026
Error DetectionCoSPlannlp20Feb 26, 2026
Step CompletionCoSPlanrobotics embodied ai20Feb 26, 2026