List your company

Research

Benchmarks

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

309,131 benchmarksPage 1174 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
Knowledge ReasoningKnowledge Reasoning Benchmarks (MATH, GPQA, MMLU, GSM8K) (test)nlpgraph24Jun 2, 2026
Compositional RetrievalKITTI-360 Apples-to-apples intersection (original & expansion compounds)retrieval search ragnlp24Jun 2, 2026
Fair Conformal PredictionFitzpatricktabular time series24Jun 2, 2026
Activity RecognitionOrange (day-based chronological)computer vision24Jun 2, 2026
Activity RecognitionKyoto (day-based chronological)computer vision24Jun 2, 2026
Activity RecognitionAruba (day-based chronological)computer vision24Jun 2, 2026
Activity RecognitionMilan (day-based chronological)computer vision24Jun 2, 2026
Motion CorrectionHCP T2w contrastbio medicalcomputer vision24Jun 2, 2026
Motion CorrectionHCP T1w contrastbio medicalcomputer vision24Jun 2, 2026
Motion CorrectionIXI PDw contrastbio medicalcomputer vision24Jun 2, 2026
Motion CorrectionIXI T2w contrastbio medicalcomputer vision24Jun 2, 2026
Motion CorrectionIXI T1w contrastbio medicalcomputer vision24Jun 2, 2026
Wind Farm Layout OptimizationWind Farm Layout 30 independent runsmiscellaneous24Jun 2, 2026
Genetic perturbation representation learningRPE1, HEPG2, and Jurkat Overallbio medical24Jun 1, 2026
Genetic perturbation representation learningJurkat cell linebio medical24Jun 1, 2026
Genetic perturbation representation learningHEPG2 cell linebio medical24Jun 1, 2026
Genetic perturbation representation learningRPE1 cell linebio medical24Jun 1, 2026
Audio EditingAudioCapsspeech audio24Jun 1, 2026
RegressionQM7 Low resolutiontabular time series24Jun 1, 2026
RegressionQM7 High resolutiontabular time series24Jun 1, 2026
Non-targeted Black-box AttackImageNetadversarial safety security24Jun 1, 2026
Targeted Black-box Adversarial AttackImageNet (test)adversarial safety securitycomputer vision24Jun 1, 2026
Non-targeted Black-box Adversarial AttackImageNet (test)adversarial safety security24Jun 1, 2026
In-Context Object LocalizationLaSOT ICLcomputer vision24Jun 1, 2026
In-Context Object LocalizationGOT-10kcomputer vision24Jun 1, 2026