List your company

Research

Benchmarks

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

309,131 benchmarksPage 2141 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
Continual LearningNI-Seq C2miscellaneous16Jun 2, 2026
Continual LearningNI-Seq-G2miscellaneous16Jun 2, 2026
Header PredictionMovie (test)nlp16Jun 2, 2026
Header PredictionProduct (test)nlp16Jun 2, 2026
Next-Step-Prediction Style PlanningCosmos Reasonrobotics embodied ai16Jun 2, 2026
Next-Step-Prediction Style PlanningRoboVQArobotics embodied ai16Jun 2, 2026
Next-Step-Prediction Style PlanningEgoPlan-Bench 2robotics embodied ai16Jun 2, 2026
Embodied PlanningCausal-Plan-Bench in-domainrobotics embodied ai3d vision geometry16Jun 2, 2026
MathGSM8Kllm chat instruction16Jun 2, 2026
Generative RecommendationInstruments (test)nlp16Jun 2, 2026
Generative RecommendationBeauty (test)nlp16Jun 2, 2026
Fault LocalizationLINUXFLBENCHcode developer ai16Jun 2, 2026
Image ClassificationImageNetcomputer vision16Jun 2, 2026
Common-sense ReasoningCommon-sense Reasoning Benchmarks Zero-shotnlp16Jun 2, 2026
Object UnlearningImagenette Object Unlearning Subsetcomputer visionadversarial safety security16Jun 2, 2026
Style UnlearningArtistic Styles SD v1.4 (test)image generation editing16Jun 2, 2026
Covariate selection for forecastingM5 Forecastingtabular time series16Jun 2, 2026
Covariate selection for forecastingRossmann Store Salestabular time series16Jun 2, 2026
Map AlignmentKimera-Multi Outdoor Real-world3d vision geometry16Jun 2, 2026
Mathematical ReasoningMathematics In-Distribution (AIME25, AMC23, Minerva, MATH500, Olymp.)llm chat instructionnlp16Jun 2, 2026
Target Viewpoint ReproductionTVRBench 500-task (test)3d vision geometry16Jun 2, 2026
Discourse-level opinion manipulationBlack-box RAG DPRnlp16Jun 2, 2026
Discourse-level opinion manipulationBlack-box RAG Qwen-Embeddingnlp16Jun 2, 2026
Discourse-level opinion manipulationBlack-box RAG BGEnlp16Jun 2, 2026
Molecular Conformation SamplingChignolinbio medical16Jun 2, 2026