List your company

Research

Benchmarks

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

309,131 benchmarksPage 2083 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
Selective Visual Question AnsweringMixed ID/OOD 50% VQA v2 / 50% AdVQA (test)multimodalcomputer vision+117Feb 26, 2026
Selective Visual Question AnsweringMixed ID/OOD 66.7% VQA v2 / 33.3% AdVQA (test)multimodalcomputer vision+117Feb 26, 2026
Discriminative tasksBigBench 13 tasks (val)nlp17Feb 26, 2026
Video Question AnsweringTGIF-QA Action original (test)multimodalcomputer vision17Feb 26, 2026
Joint Optic Cup and Optic Disc SegmentationBASE3bio medicalcomputer vision17Feb 26, 2026
Joint Optic Cup and Optic Disc SegmentationBASE2bio medicalcomputer vision17Feb 26, 2026
Joint Optic Cup and Optic Disc SegmentationBASE1bio medicalcomputer vision17Feb 26, 2026
Interaction AttributionIdentity Rule languagenlp17Feb 26, 2026
ClassificationAustralian (UCI) (test)computer visionnlp+317May 18, 2026
ClassificationIonosphere (UCI) (test)computer visionnlp+317May 18, 2026
Intent ClassificationHWU64nlp17Mar 11, 2026
Intent ClassificationCLINC150nlp17Mar 11, 2026
3D MRI reconstructionHR 3D MRI 380x294x138x243d vision geometrybio medical17Feb 26, 2026
Machine TranslationWMT news Average 2010-2016 (test)nlp17Feb 26, 2026
Speech TranslationCallhome En-Es (test)speech audionlp17Feb 26, 2026
Binary classificationAdvGLUE (test)tabular time series17Feb 26, 2026
Full-Reference Image Quality AssessmentKADIDcomputer vision17Feb 26, 2026
Object DetectionM6Doc (test)computer vision17Feb 26, 2026
Relation ExtractionRETACRED (test)nlp17Feb 26, 2026
Referring Expression SegmentationG-Ref UMD (test)computer visionmultimodal17Feb 26, 2026
Math Word Problem Solution GenerationGSM8K (test)nlpllm chat instruction17Feb 26, 2026
Compositional ReasoningAROcomputer visionnlp17Jun 4, 2026
Grammatical Error CorrectionNLPCC word-level (test)nlp17Feb 26, 2026
Commonsense Fact VerificationCREAK (test)nlp17Jun 4, 2026
Source SeparationWSJ0-2mix (test)speech audio17Feb 26, 2026