List your company

Research

Benchmarks

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

309,131 benchmarksPage 1885 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
GPU kernel code generation and optimizationKernelBench Level 1 (test)code developer ai18Mar 4, 2026
Visual Mathematical ReasoningMathVista 1.0 (testmini)multimodalcomputer vision+118Mar 4, 2026
Text-to-Image GenerationGenEvalimage generation editing18Mar 4, 2026
ClusteringClusTREC-Covidtabular time series18Mar 4, 2026
ClusteringMedrxivClustering S2Stabular time series18Mar 4, 2026
ClusteringMedrxivClusteringP2P (MedP2P)tabular time series18Mar 4, 2026
ClusteringBiorxivClustering S2Stabular time series18Mar 4, 2026
Information RetrievalR2-PMCretrieval search rag18Mar 4, 2026
Information RetrievalR2-IYIretrieval search rag18Mar 4, 2026
Information RetrievalPHQAretrieval search rag18Mar 4, 2026
Response ModerationFlexBenchadversarial safety securityllm chat instruction18Mar 4, 2026
Humanoid Motion TrackingMoCap Data AMASS+LAFAN1robotics embodied aicomputer vision18Mar 4, 2026
Mathematical ReasoningTheoremQAllm chat instructionnlp18Mar 4, 2026
Mathematical ReasoningOlympiallm chat instructionnlp18Mar 4, 2026
Mathematical ReasoningDM-Mathllm chat instructionnlp18Mar 4, 2026
Correctness PredictionMedalsnlp18Mar 4, 2026
Correctness PredictionMath operationsnlp18Mar 4, 2026
Correctness PredictionCitiesnlp18Mar 4, 2026
Correctness PredictionNotable Peoplenlp18Mar 4, 2026
Multimodal UnderstandingHigh-IC tasks MMB, POPE, MME, SEED, GQA, TextVQA LLaVA-NeXT-7Bmultimodal18Mar 4, 2026
Multimodal UnderstandingLLaVA High-IC tasks (MMB, POPE, MME, SEED, GQA) 1.5-7Bmultimodal18Mar 4, 2026
Image ClassificationFashion-MNIST heterogeneous (test)computer vision18Mar 4, 2026
Image ClassificationMNIST 100 clients, highly heterog. (test)computer vision18Mar 4, 2026
Multimodal Mathematical ReasoningWeMath mini (test)multimodalnlp+118May 6, 2026
Link PredictionWikiArt MKG v2graph18Mar 4, 2026