List your company

Research

Benchmarks

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

309,131 benchmarksPage 924 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
Audio-Visual Semantic SegmentationAVSBench AVSS v1 (test)multimodalspeech audio+129Feb 26, 2026
Conditional Image GenerationCIFAR-10 class-conditionalimage generation editing29Feb 26, 2026
Zero-shot EvaluationZero-shot Evaluation Suitenlpllm chat instruction29Jun 5, 2026
3D Visual GroundingMulti3DRefer (val)3d vision geometrycomputer vision29Jun 2, 2026
Unknown sample identificationSyntheticcomputer vision29Feb 26, 2026
Attention Operator ThroughputQwen2.5 72B (64 Q-heads/8 KV-heads/128 Head-dimension)llm chat instruction29May 7, 2026
Cross-modal retrievalClotho (test)multimodalretrieval search rag29Feb 26, 2026
OOD DetectionCora Structure Manipulationcomputer visiontabular time series28Jul 9, 2026
OOD DetectionCora (Label Leave-out)computer visiontabular time series28Jul 9, 2026
6-DoF Pose TrackingYCBInEOATcomputer vision3d vision geometry28Jul 8, 2026
Imagined digit classificationMegNISTcomputer vision28Jul 7, 2026
DeconvolutionDeconvolution (test)graph28Jul 7, 2026
Cell-type deconvolutionTabula Sapiens pseudobulk (test)bio medical28Jul 7, 2026
Hallucination EvaluationStyle-CHAIR Gamellm chat instructionnlp28Jul 7, 2026
Hallucination EvaluationStyle-CHAIR Cartoonllm chat instructionnlp28Jul 7, 2026
RegressionVentricularVolume (in-distribution)tabular time series28Jul 7, 2026
Image RegressionUTKFaces Out-of-distributioncomputer vision28Jul 7, 2026
Image RegressionUTKFaces In-distributioncomputer vision28Jul 7, 2026
Node ClassificationPubmedgraph28Jul 7, 2026
Node ClassificationCora-MLgraph28Jul 7, 2026
Node ClassificationCiteseergraph28Jul 7, 2026
Image ClassificationCIFAR-100 Clean standard (test)computer vision28Jul 7, 2026
Selective Image ClassificationCIFAR-10 standard (test)computer vision28Jul 7, 2026
Image ClassificationCIFAR-10-C standard (test)computer vision28Jul 7, 2026
Image ClassificationCIFAR-10 standard (test)computer vision28Jul 7, 2026