List your company

Research

Benchmarks

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

309,131 benchmarksPage 1010 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
Edge ClassificationFB15K237 5 way Encyclopedic KG (test)graph27Mar 17, 2026
Inductive dynamic link predictionEnron Inductivegraph27May 29, 2026
Machine UnlearningTOFU Forget 5%adversarial safety security27Mar 16, 2026
Image ClassificationFACETcomputer vision27Mar 16, 2026
Spectral Risk OptimisationDGP2miscellaneous27Mar 16, 2026
Text-to-Image GenerationDrawBenchimage generation editing27Mar 16, 2026
Character-Level Language ModelingShakespeare (val)nlp27Apr 2, 2026
OptimizationSynthetic quartic functionmiscellaneous27Mar 16, 2026
Object-Centric Representation LearningCOCOcomputer vision27Mar 13, 2026
Domain names classificationTI Density sequencing 2016nlp27Mar 13, 2026
Domain names classificationTI Time sequencing 2016nlp27Mar 13, 2026
Domain names classificationTI Fixed sequencing 2016nlp27Mar 13, 2026
Open-Set Test-Time AdaptationTiny-ImageNet-Ccomputer vision27Apr 3, 2026
Compositional Multi-taskingCompositional Multi-tasking Summarization, Tone Adjustment, Translation (test)llm chat instructionnlp27Mar 13, 2026
Synthetic Graph GenerationPlanar Datasetgraph27Mar 31, 2026
Injection AttackInput Reconstruction (All)adversarial safety security27Mar 12, 2026
Collision AttackInput Reconstruction (Mid)adversarial safety security27Mar 12, 2026
Collision AttackInput Reconstruction (First split)adversarial safety security27Mar 12, 2026
Inversion AttackInput Reconstruction (First split)adversarial safety security27Mar 12, 2026
PET/CT Report Impression GenerationPET F2I 41Kbio medicalnlp27Mar 12, 2026
Speech-to-Speech Question AnsweringLlama Questionsspeech audionlp27Apr 21, 2026
Visual Discrepancy DetectionOddGridBenchcomputer visionmultimodal27Mar 11, 2026
Content ModerationMMDS (test)nlpcomputer vision+127Mar 11, 2026
Mathematical ReasoningAMCllm chat instructionnlp27Apr 16, 2026
Precise MovementNavSpacerobotics embodied ai27Mar 11, 2026