List your company

Research

Benchmarks

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

309,131 benchmarksPage 222 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
Speech Translation Evaluation CorrelationEuroparl-STspeech audionlp70Apr 9, 2026
Email address extractionSynthetic datasetnlp70Apr 8, 2026
Lossless video compressionXiph CIF (YUV420) (All frames)video generation editing70Apr 7, 2026
InterpolationPhysioNet Mortality 2012 (test)tabular time series70Jul 2, 2026
Novel View SynthesisMipNeRF3603d vision geometry70Jun 19, 2026
Constrained ClusteringCOL2graph70Mar 31, 2026
Multimodal ReasoningM^3CoTmultimodalnlp70Mar 24, 2026
Mathematical ReasoningGSM-Hardllm chat instructionnlp70Jun 15, 2026
Multimodal Mathematical ReasoningMathVersemultimodalnlp+170Jun 11, 2026
LocalizationImageNetcomputer vision70Mar 17, 2026
Graph Classificationobgn-Homegraph70Mar 11, 2026
Graph Classificationobgn-Techgraph70Mar 11, 2026
Claim verification9-dataset aggregate retrieval-free setting (test)nlp70Mar 6, 2026
Driver Top 3 PredictionRel F1tabular time seriesDriver Top 3 Prediction on Rel F1 performance trend70May 25, 2026
Circuit Discovery EvaluationGemma-2-2Bmiscellaneous70Mar 5, 2026
Text-to-Image RetrievalFlickr30k (val)multimodalretrieval search rag70May 12, 2026
Image-to-Text RetrievalFlickr30k (val)multimodalretrieval search rag70May 12, 2026
Light field data completionVinyl 128x128x3x303d vision geometry70Mar 4, 2026
Light field data completionMedieval2 128x128x3x303d vision geometry70Mar 4, 2026
Light field data completionMuseum 128x128x3x303d vision geometry70Mar 4, 2026
Light field data completionGreek 128x128x3x303d vision geometry70Mar 4, 2026
Realistic color video completionAkiyo 144×176×3×30video generation editing70Mar 4, 2026
Realistic color video completionGrandma 144×176×3×30video generation editing70Mar 4, 2026
Realistic color video completionClaire 144×176×3×30video generation editing70Mar 4, 2026
Realistic color video completionNews 144×176×3×30video generation editing70Mar 4, 2026