List your company

Research

Benchmarks

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

309,131 benchmarksPage 1506 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
Anomaly DetectionOrganA (test)tabular time series21Feb 26, 2026
Frame RetrievalTennis Forehandretrieval search ragcomputer vision21Feb 26, 2026
Action Phase ClassificationTennis Forehandcomputer vision21Feb 26, 2026
Frame RetrievalPour Liquidretrieval search ragcomputer vision21Feb 26, 2026
Action Phase ClassificationPour Liquidcomputer vision21Feb 26, 2026
Frame RetrievalPour Milkretrieval search ragcomputer vision21Feb 26, 2026
Action Phase ClassificationPour Milkcomputer vision21Feb 26, 2026
Capacitated Vehicle Routing ProblemCVRP n=100 (10k instances)miscellaneous21Feb 26, 2026
Sequential RecommendationAmazon Sports and Outdoorstabular time series21Feb 26, 2026
Node classificationSynthetic homo ratio 0.9graph21Feb 26, 2026
Node classificationSynthetic homo ratio 0.8graph21Feb 26, 2026
Node classificationSynthetic homo ratio 0.5graph21Feb 26, 2026
Image GenerationLSUN-Bedroom 50k samples (test)image generation editing21Feb 26, 2026
Performance Difference EstimationAdult Subgroup #5, 1%tabular time series21Feb 26, 2026
Performance Difference EstimationAdult Subgroup #4, 1%tabular time series21Feb 26, 2026
Performance Difference EstimationAdult Subgroup #3, 3%tabular time series21Feb 26, 2026
Performance Difference EstimationAdult Subgroup #2, 9%tabular time series21Feb 26, 2026
Performance Difference EstimationAdult Subgroup #1, 86%tabular time series21Feb 26, 2026
Multimodal ClassificationUR-FUNNYmultimodalcomputer vision+121Apr 6, 2026
Question AnsweringSQuAD v1.1 & v2.0nlp21Mar 10, 2026
Visual ReasoningNLVR2 (test-P)multimodalcomputer vision21Feb 26, 2026
Question AnsweringTabMWP (test)nlp21Feb 26, 2026
Molecule GenerationIsocyanatesbio medical21Jun 4, 2026
Fine-grained Image ClassificationHerbarium (test)computer vision21Feb 26, 2026
Fine-grained Image ClassificationEuroSAT (test)computer vision21Feb 26, 2026