List your company

Research

Benchmarks

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

309,131 benchmarksPage 521 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
Ordered Pixel-by-Pixel ClassificationMNIST ordered pixels (test)computer vision42Feb 26, 2026
Character-level PredictionPTB (test)nlp42Feb 26, 2026
Point Cloud Quality AssessmentSJTU-PCQA (test)3d vision geometry42Feb 26, 2026
Semantic SegmentationMFNet nighttime (test)computer vision42Feb 26, 2026
Fine-grained classificationPets (test)computer vision42Jun 8, 2026
Vulnerability DetectionReveal (test)adversarial safety securitycode developer ai42Feb 26, 2026
Code DebuggingHumanEvalcode developer ai42Feb 26, 2026
Image ClassificationCIFAR-10N (Random 1)computer vision42May 21, 2026
RecommendationAmazon-Movie IID (test)tabular time series42Feb 26, 2026
Dichotomous Image SegmentationDIS5K TE (1-4) (test)computer vision42May 15, 2026
Continual Image ClassificationMiniImageNet Splitcomputer vision42Mar 18, 2026
Scene ClassificationRESISC-45 (TR=20%)computer vision42May 12, 2026
Object Hallucination ProbingGQA POPE Randomcomputer visionnlp42Apr 10, 2026
Attention Operator ThroughputLlama2 7B (32 Q-heads/32 KV-heads/128 Head-dimension)llm chat instruction42May 7, 2026
Multitask Language UnderstandingMMLUnlpllm chat instruction41Jul 7, 2026
Math Problem SolvingAIME 2024llm chat instructionnlp41Jun 26, 2026
Class-conditioned generationImageNet 256 × 256 (train test)image generation editing41Jun 25, 2026
Instruction FollowingIFBenchllm chat instruction41Jul 7, 2026
LocalizationCityU Constructioncomputer vision41Jun 15, 2026
Protein-Ligand Binding Affinity PredictionPDBbind core set 2013bio medical41Jun 15, 2026
Multi-label recognitionVOC 2007computer vision41Jun 12, 2026
Multi-label recognitionCOCO 2017computer vision41Jun 12, 2026
MathematicsMATH-500 (test)nlp41Jun 16, 2026
Machine-Generated Text DetectionCOLING MGT English 2025nlp41Jun 8, 2026
Multi-Criteria Decision MakingAlternative set A augmented with A11miscellaneous41Jun 8, 2026