List your company

Research

Benchmarks

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

309,131 benchmarksPage 622 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
PDE SolvingHelmholtz equationmiscellaneous37Jun 16, 2026
Domain GeneralizationDomainNet DomainBed (test)computer vision37Feb 27, 2026
Machine TranslationWMT En-De 2019 (test)nlp37Feb 26, 2026
Liver SegmentationLiTScomputer visionbio medical37Jun 16, 2026
Multilingual text-centric visual question answeringMTVQAmultimodalnlp37Apr 15, 2026
Fine-grained classificationDescribable Textures Dataset (DTD)computer vision37May 18, 2026
Point Cloud CompletionPCN3d vision geometry37Mar 24, 2026
GenerationMLLMU-Bench (Forget Set)llm chat instruction37Jun 2, 2026
Fine grained classificationOxford-IIIT Petscomputer vision37May 13, 2026
Phase recognitionCholec80 (test)bio medicalcomputer vision37Jul 1, 2026
Video Instance SegmentationYouTube-VIS 2022 (val)computer vision37Jun 19, 2026
Conversational PerformanceREDIAL (test)llm chat instructionnlp37Feb 26, 2026
Long document summarizationBookSum (test)nlp37Feb 26, 2026
Audio-Visual SegmentationAVSBench MS3 v1 (test)multimodalspeech audio+137Feb 26, 2026
Visual Question AnsweringScienceVQAmultimodalcomputer vision+137Jun 12, 2026
SegmentationCityscapescomputer vision37Mar 20, 2026
Inductive Link PredictionFB15k-237 inductive (test)graph37Feb 26, 2026
Hyperspectral Image ClassificationPavia Universitycomputer vision37Jun 4, 2026
Image ClassificationImageNet-100 original (test)computer vision36Jul 9, 2026
PDE SolvingBurgers' nu=0.001 1D (test)miscellaneous36Jul 9, 2026
Visual Question AnsweringIR-VQA 9,720-sample (test)multimodalcomputer vision+136Jul 8, 2026
3D Dense CaptioningScanRefer3d vision geometrycomputer vision+136Jul 8, 2026
Source Code Watermark Extraction RobustnessCodeNet D152 (evaluation)code developer ai36Jul 8, 2026
Source Code Watermark Extraction RobustnessCodeNet D88 (evaluation)code developer ai36Jul 8, 2026
Source Code Watermark Extraction RobustnessCodeNet D56 (evaluation)code developer ai36Jul 8, 2026