List your company

Research

Benchmarks

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

309,131 benchmarksPage 2104 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
Categorical Data Imputationmushroom (test)tabular time series16Jul 9, 2026
Categorical Data Imputationcar (test)tabular time series16Jul 9, 2026
Fine-grained Image ClassificationFGVC (CUB-200, Stanford Dogs, Stanford Cars, NABirds) (test)computer vision16Jul 9, 2026
Hallucination AttributionRePOPEmultimodalcomputer vision+116Jul 9, 2026
Hallucination AttributionPOPEmultimodalcomputer vision+116Jul 9, 2026
Harmonization → Light EnhancementLoL (test)image generation editingcomputer vision16Jul 9, 2026
Numeric PlanningIPC Numeric & Custom Planning Domains 2023 (Evaluation set)miscellaneous16Jul 9, 2026
Classification25 UCI Datasets Aggregatedcomputer visionnlp+316Jul 9, 2026
Unconditional Image GenerationAFHQ v2image generation editing16Jul 9, 2026
Image ClassificationDog Breedcomputer vision16Jul 8, 2026
Image ClassificationCUB200computer vision16Jul 8, 2026
Image ClassificationFood500 base-to-novel generalizationcomputer vision16Jul 8, 2026
Image ClassificationWeb Cars base-to-novelcomputer vision16Jul 8, 2026
Image ClassificationAverage across 5 datasetscomputer vision16Jul 8, 2026
Image ClassificationWebcarcomputer vision16Jul 8, 2026
Image ClassificationVeg200computer vision16Jul 8, 2026
Image ClassificationFruit92computer vision16Jul 8, 2026
Video Face RestorationCelebV-HQ (test)video generation editingcomputer vision16Jul 8, 2026
Multi-Hop Question AnsweringMuSiQuenlpretrieval search rag16Jul 8, 2026
Artwork OutpaintingLandscape Artwork Images Cleveland Museum of Art & Art Institute of Chicago (400 images)image generation editingcomputer vision16Jul 8, 2026
Multi-turn Decision Makingtau2-Bench held-out (test)agents tool userobotics embodied ai16Jul 8, 2026
Function CallingBFCL held-out V4 (test)llm chat instructionagents tool use16Jul 8, 2026
Agentic Task PerformanceACEBench Agent (test)agents tool use16Jul 8, 2026
Utility PreservationStandard Benign Promptsmiscellaneous16Jul 8, 2026
Safety AlignmentVSA Violence (visual synonym attack prompts)adversarial safety security16Jul 8, 2026