List your company

Research

Benchmarks

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

309,131 benchmarksPage 826 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
driver-top3 classificationrel-f1computer visionadversarial safety security30Jul 9, 2026
driver-dnf classificationrel-f1computer vision30Jul 9, 2026
Multimodal Sentiment AnalysisMVSA-Single (test)multimodalnlp30Jul 9, 2026
Multimodal Action RecognitionKinetics-Sounds (KS) (test)computer visionmultimodal30Jul 9, 2026
Multimodal Emotion RecognitionCREMA-D (test)multimodalnlp+130Jul 9, 2026
Mathematical ReasoningDAPO-Math OOD average (avg of four benchmarks)llm chat instructionnlp30Jul 9, 2026
Mathematical ReasoningDAPO-Math In-Distribution (test)llm chat instructionnlp30Jul 9, 2026
Image CaptioningInfrared Image Dataset downstream (test)multimodalcomputer vision+130Jul 8, 2026
Incomplete Multi-View ClusteringFashiongraphcomputer vision+230Jul 8, 2026
Incomplete Multi-View ClusteringLandUse-21graphcomputer vision+230Jul 8, 2026
Incomplete Multi-View ClusteringHandWrittengraphcomputer vision+230Jul 8, 2026
Incomplete Multi-View ClusteringCUBgraphcomputer vision+230Jul 8, 2026
Incomplete Multi-View ClusteringSynthetic3dgraphcomputer vision+230Jul 8, 2026
Large-scale Low-shot LearningILSVRC 2012/2010 (test)computer vision30Jul 8, 2026
Worst-case Time Complexity AnalysisWISEcode developer ai30Jul 8, 2026
Multi-modal Visual ReasoningVKnowUmultimodalcomputer vision+130Jul 7, 2026
Object DetectionMODAcomputer vision30Jul 7, 2026
Facial Expression RecognitionAva265-HMCcomputer vision30Jul 7, 2026
LLM Similarity MeasurementUnrelated Modelsllm chat instructionnlp30Jul 7, 2026
LLM Similarity MeasurementModel Fine-tuningllm chat instructionnlp30Jul 7, 2026
Change DetectionSYSU (+P) (Old Memory)computer vision30Jul 3, 2026
Robotic Task PerformanceMetaWorldrobotics embodied ai30Jul 3, 2026
Class-Incremental LearningCIFAR100 B50computer visiontabular time series30Jul 3, 2026
Misalignment DetectionWorkBench (n=326)adversarial safety securityllm chat instruction30Jul 3, 2026
Misalignment DetectionAgent-SafetyBench n=35 (aligned traces)adversarial safety securityllm chat instruction30Jul 3, 2026