List your company

Research

Benchmarks

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

309,131 benchmarksPage 543 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
Image-Text Alignment Evaluationnocaps out-of-domain (val)computer visionnlp+140May 1, 2026
Untargeted Adversarial AttackImageNetadversarial safety security40May 1, 2026
Out-of-Distribution DetectionCIFAR-100 ID Near-OOD Average OpenOOD v1.5computer visiontabular time series40May 27, 2026
MathMinervallm chat instruction40May 28, 2026
Question Selection and GenerationAmerica in One Room: Democratic Reform (A1R)nlp40Apr 28, 2026
Multivariate Time-series ForecastingPEMS08tabular time series40Apr 28, 2026
Multivariate Time-series ForecastingWeathertabular time series40Apr 28, 2026
Multivariate Time-series ForecastingElectricitytabular time series40Apr 28, 2026
Reading ComprehensionSQuADnlp40Apr 28, 2026
Biomedical Question AnsweringPubMedQAbio medicalnlp40Apr 28, 2026
Text-to-SQLSpidernlpcode developer ai40Apr 28, 2026
Mathematical ReasoningGSM8kllm chat instructionnlp40Apr 28, 2026
Steroid-free clinical remission (SFCR) predictionIFX arm and ADA patients cohort (SFCR outcome)bio medicaltabular time series40Apr 28, 2026
Link predictionarxivgraph40Jun 11, 2026
Medical ReasoningMedicine MedQA M-Medbio medicalnlp40Apr 27, 2026
Backdoor AttackCSTadversarial safety security40Apr 24, 2026
Deepfake DetectionCeleb-DF v1 (test)computer visionadversarial safety security40Apr 24, 2026
Bernoulli SamplingBernoulli Distributionsmiscellaneous40Apr 24, 2026
HOI Motion ImitationGRABrobotics embodied aicomputer vision40Apr 23, 2026
P2P Electricity Trading10 Prosumer Case Study (test)tabular time series40Apr 23, 2026
Usability EvaluationIDC Usability Questionnaire 1.0 (full survey)llm chat instruction40Apr 23, 2026
Vision Model Representation AlignmentImageNet 20% held-out split of 20,000 samples (val)computer vision40Apr 23, 2026
Compressed Video Super-ResolutionCVCP10 (test)computer vision40Apr 23, 2026
Object DetectionBDD100K (all)computer vision40Apr 21, 2026
Object DetectionBDD100K Day+Nightcomputer vision40Apr 21, 2026