List your company

Research

Benchmarks

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

309,131 benchmarksPage 1833 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
Tooth Segmentation3D-IOSSegcomputer vision18May 12, 2026
Anomaly DetectionSWaTtabular time series18May 12, 2026
Anomaly DetectionSMAPtabular time series18May 12, 2026
Anomaly DetectionMSLtabular time series18May 12, 2026
LLM Safety EvaluationBeaverTailsadversarial safety securityllm chat instruction18May 11, 2026
Video Understanding Reward ModelingVURBcomputer vision18May 11, 2026
Mathematical reasoningAIME 24/25llm chat instructionnlp18May 11, 2026
Mathematical reasoningMINERVAllm chat instructionnlp18May 11, 2026
Mathematical reasoningMATH500llm chat instructionnlp18May 11, 2026
Tool CallingBFCL (Berkeley Function Calling Leaderboard)agents tool usellm chat instruction18Jun 4, 2026
Sentiment TransferSentiment Transfer Neg2Posnlp18May 11, 2026
Sentiment TransferSentiment Transfer Pos2Negnlp18May 11, 2026
Length ControlLength Controlnlp18May 11, 2026
Keyword GenerationKeyword Generationnlp18May 11, 2026
Visual Question AnsweringOmniEarth-Bench Multiple-choice question protocol 1.0 (test)multimodalcomputer vision+118May 11, 2026
Domain-incremental LearningDomainNetmiscellaneous18Jun 24, 2026
Backdoor Attack Success RateCross-modal Backdoor Evaluation Setadversarial safety security18May 11, 2026
Statistical Significance AnalysisMultimodal Evaluation Suite (Tiny-ImageNet, CIFAR-100, FMNIST, Caltech-256, AG News, MMLU, VQA, CommonGen) (test)tabular time series18May 11, 2026
Causal DiscoveryVARtabular time series18May 11, 2026
CATE recoveryCATE Recovery sale1 -> purchase (test)tabular time series18May 11, 2026
CATE recoveryCATE Recovery push -> visit (test)tabular time series18May 11, 2026
Multimodal SearchIMEBretrieval search ragmultimodal18May 11, 2026
Multimodal SearchFVQAretrieval search ragmultimodal18May 11, 2026
Web agent task completionWebArena (test)agents tool use18May 21, 2026
Image Quality AssessmentEVAFusion source-pair-disjoint n=935 images (test)computer vision18May 11, 2026