List your company

Research

Benchmarks

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

309,131 benchmarksPage 927 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
Text Query SafetyHarmBenchadversarial safety security28Jun 23, 2026
Text Query SafetyXGuard (test)adversarial safety security28Jun 23, 2026
Text Query SafetyAegis2adversarial safety security28Jun 23, 2026
Image ClassificationOfficeHome RealWorldcomputer vision28Jun 23, 2026
Image ClassificationOfficeHome Clipart domaincomputer vision28Jun 23, 2026
Image ClassificationOfficeHome Art domaincomputer vision28Jun 23, 2026
Semantic SegmentationSBDcomputer vision28Jun 23, 2026
Mathematical ReasoningMathematical Reasoning Suite AIME24, AIME25, AMC23, HMMT24, HMMT25llm chat instructionnlp28Jun 23, 2026
Hallucination DetectionBoolQllm chat instructionnlp28Jun 23, 2026
Contextual BanditsJestertabular time series28Jun 23, 2026
Contextual BanditsMovieLens 25Mtabular time series28Jun 23, 2026
Function Callingin-house product datasetllm chat instructionagents tool use28Jun 23, 2026
Operator Learning Rollout PredictionE6 Navier-Stokes Equationtabular time series28Jun 23, 2026
Operator Learning Rollout PredictionE5 Navier-Stokes Equationtabular time series28Jun 23, 2026
Operator Learning Rollout PredictionNavier-Stokes Equation E4tabular time series28Jun 23, 2026
Operator Learning Rollout PredictionE3 Kuramoto-Sivashinsky Equationtabular time series28Jun 23, 2026
Operator Learning Rollout PredictionBurgers' Equation E1tabular time series28Jun 23, 2026
Modality MatchBili Foodmultimodal28Jul 1, 2026
Modality MatchKUmultimodal28Jul 1, 2026
Multi-task agent evaluationSkill-MAS Evaluation Suite Aggregateagents tool use28Jun 18, 2026
Multi-tool callingVitaBench held-out (test)agents tool usellm chat instruction28Jun 18, 2026
Multi-hop dynamic question answeringBrowseComp-Plus (test)retrieval search ragnlp28Jun 18, 2026
Mathematical reasoningHumanity's Last Exam Math (test)llm chat instructionnlp28Jun 18, 2026
Web-based researchDeepResearchBench (test)retrieval search ragllm chat instruction28Jun 18, 2026
Vision Classification8 vision classification tasks CLIP ViT-B-32 (test)computer vision28Jun 18, 2026