List your company

Research

Benchmarks

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

309,131 benchmarksPage 1732 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
High-Resolution Multimodal ReasoningHR-Bench 8K FCPmultimodalcomputer vision19Feb 26, 2026
High-Resolution Multimodal ReasoningHR-Bench 8K FSPmultimodalcomputer vision19Feb 26, 2026
High-Resolution Multimodal ReasoningHR-Bench 4K FCPmultimodalcomputer vision19Feb 26, 2026
Multimodal ReasoningVstar Bench Spatialmultimodalnlp19Feb 26, 2026
Multimodal ReasoningVstar Bench Attrmultimodalnlp19Feb 26, 2026
Multi-step Scientific Tool-useSciAgentBench Main Results 1.0agents tool use19Feb 26, 2026
Automatic Speech RecognitionCommonVoicespeech audio19May 20, 2026
Aggregate RankingGraphLand Suite Aggregate (RL (Random Low))graph19Feb 26, 2026
Binary Classificationartnet-exp (RL Random Low)tabular time series19Feb 26, 2026
ReasoningCountriesllm chat instructionnlp19Feb 26, 2026
Text-to-ImagePartiPrompts 42 (test)image generation editing19Feb 26, 2026
Text-to-ImageGenEval 11 (test)image generation editing19Feb 26, 2026
Binary ClassificationMNIST digits 7 and 9 (test)tabular time series19Feb 26, 2026
Conformal Predictionbio (test)tabular time series19May 12, 2026
RegressionAbalone (test)tabular time series19Jun 4, 2026
Outlier DetectionALOI (test)tabular time series19Feb 26, 2026
Outlier DetectionADBench v1 (train)tabular time series19Feb 26, 2026
Anomaly DetectionALOI ADBench (test)tabular time series19Feb 26, 2026
Anomaly DetectionADBench 57 Datasets (test)tabular time series19Feb 26, 2026
Simulation-Based InferenceSBIBM Gaussian Lineartabular time series19Apr 2, 2026
Low-dimensional embeddingSynthetic Manifold Setup a n=600, p=100 1.0graph19Feb 26, 2026
Medical Image SegmentationPENGWIN (test)bio medicalcomputer vision19Feb 26, 2026
Medical Image SegmentationBraTS (test)bio medicalcomputer vision19Feb 26, 2026
Semantic SegmentationPangaea 10% (train)computer vision19Feb 26, 2026
Semantic SegmentationPangaea Aggregate (test)computer vision19Feb 26, 2026