List your company

Research

Benchmarks

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

309,131 benchmarksPage 764 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
Code GenerationMBPPcode developer ai32Apr 16, 2026
Traveling Salesman ProblemTSP5K generatedmiscellaneous32Jun 4, 2026
Knowledge Base Question AnsweringCWQ (ComplexWebQuestions)nlpretrieval search rag32Apr 15, 2026
Mathematical ReasoningDeepMath 2025 (test)llm chat instructionnlp32Apr 15, 2026
Mathematical ReasoningMATH 2021 (test)llm chat instructionnlp32Apr 15, 2026
Single-ingredient odor classificationSMELLNET BASEbio medicalcomputer vision32Apr 15, 2026
Utility EvaluationAgentDojomultimodalcomputer vision+132Apr 14, 2026
Attack Success RateInjecAgentcomputer visionadversarial safety security32Apr 14, 2026
Multi-task Language UnderstandingMMLU Pro (test)nlpllm chat instruction32Jul 1, 2026
Referring Camouflaged Object DetectionR2C7Kcomputer vision32Apr 14, 2026
Polish Board Certification Examinationsspeakleash/PES 2018-2022nlp32Apr 14, 2026
Link PredictionUS Legis. (inductive)graph32Jun 4, 2026
Novel View SynthesisRE10K large overlap3d vision geometry32Jul 1, 2026
Novel View SynthesisRE10K (small overlap)3d vision geometry32Jul 1, 2026
Far OOD DetectionTexture (test)computer visiontabular time series32Apr 14, 2026
Far OOD DetectionPlacescomputer visiontabular time series32Apr 14, 2026
OOD DetectionImageNet protocol datasets averaged over 4 (test)computer visiontabular time series32Apr 14, 2026
Far Out-of-Distribution DetectionTexturecomputer vision32Apr 14, 2026
Far Out-of-Distribution DetectionSUNcomputer vision32Apr 14, 2026
Far OOD detectioniNaturalist (test)computer visiontabular time series32Apr 14, 2026
Data Extraction AttackRAPadversarial safety security32May 25, 2026
Image ClassificationOxford-IIITcomputer vision32Apr 14, 2026
Image ClassificationImageNet-1kcomputer vision32Apr 15, 2026
Multimodal UnderstandingStandard Multimodal Evaluation Suite (GQA, MMBench, MME, TextVQA, ScienceQA, VQA v2) 1.5 (test val)multimodal32Apr 13, 2026
Membership ProofingSynthetic Membership Proof Setsadversarial safety security32Apr 13, 2026