List your company

Research

Benchmarks

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

309,131 benchmarksPage 671 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
Kernel Ridge RegressionCENSUS (test)tabular time series35Jun 5, 2026
Audio ClassificationUrbanSound8K single-labelspeech audio35Jun 4, 2026
Sparse Logistic RegressionARCENE (test)tabular time series35Jun 4, 2026
Mathematical ReasoningAIME 24llm chat instructionnlp35Jun 30, 2026
Mathematical ReasoningAIME 25llm chat instructionnlp35Jun 30, 2026
Speech UnderstandingMMSUspeech audio35Jul 9, 2026
Text-based Visual Question AnsweringTextVQAmultimodalcomputer vision+135Jul 3, 2026
Sequential RecommendationToystabular time series35Jun 18, 2026
Sequential RecommendationSportstabular time series35Jun 18, 2026
Safety EvaluationSORRY-Benchadversarial safety security35Jun 2, 2026
Multiple-Choice QuestioningSafetyBench English (test)nlp35Jun 2, 2026
Truthfulness EvaluationTruthfulQAllm chat instructionnlp35Jun 2, 2026
RegressionEnergy Consumptiontabular time series35Jun 2, 2026
RegressionHousing Pricestabular time series35Jun 2, 2026
Aspect Sentiment Triplet ExtractionRest 2016 (test)nlp35Jun 1, 2026
Aspect Sentiment Triplet ExtractionRest 2014 (test)nlp35Jun 1, 2026
Knowledge-intensive Claim Extraction and Information Retrieval75-case (test)retrieval search ragnlp35Jun 1, 2026
Value Structure AlignmentPortrait Values Questionnaire (PVQ)nlp35May 29, 2026
Clinical Task ExecutionMedAgentBench OOD v2bio medicalagents tool use35May 29, 2026
Clinical Task ExecutionMedAgentBench v2 (test)bio medicalagents tool use35May 29, 2026
Clinical Task ExecutionMedAgentBench v2 (val)bio medicalagents tool use35May 29, 2026
Clinical Task ExecutionMedAgentBench OODbio medicalagents tool use35May 29, 2026
Clinical Task ExecutionMedAgentBench (test)bio medicalagents tool use35May 29, 2026
Clinical Task ExecutionMedAgentBench (val)bio medicalagents tool use35May 29, 2026
Image ClassificationAggregate of 9 benchmarks (CIFAR10, CIFAR100, EuroSAT, OxfordPet, Flowers102, Food101, SUN397, DTD, Caltech101) Full-datacomputer vision35May 28, 2026