List your company

Research

Benchmarks

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

309,131 benchmarksPage 762 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
Membership Inference AttackIMDBadversarial safety security32Apr 24, 2026
Membership Inference AttackSSTadversarial safety security32Apr 24, 2026
Membership Inference AttackYelpadversarial safety security32Apr 24, 2026
Membership Inference AttackCoLAadversarial safety security32Apr 24, 2026
Scientific ReasoningARCcnlp32Apr 23, 2026
Reading ComprehensionBelebele cnlp32Apr 23, 2026
Talking Head GenerationMEADvideo generation editingcomputer vision32Apr 23, 2026
Visual ReasoningMMMU-Promultimodalcomputer vision32Apr 23, 2026
Visual ReasoningVizWizmultimodalcomputer vision32Apr 23, 2026
Visual ReasoningA-OKVQAmultimodalcomputer vision32Apr 23, 2026
Multi-modal Alignment and ClassificationImageBind Target label (test)multimodalcomputer vision+132Apr 23, 2026
Multi-modal Alignment and ClassificationImageBind Original label (test)multimodalcomputer vision+132Apr 23, 2026
Toxicity MitigationToxicity promptsadversarial safety securitynlp32Apr 23, 2026
Hyperspectral Image ClassificationQingyun (test)computer vision32Jun 2, 2026
Object Detection Reliability EstimationFoggy Cityscapes OODcomputer vision32Apr 23, 2026
Object Detection Reliability EstimationCityscapes near OODcomputer vision32Apr 23, 2026
Object Detection Reliability EstimationCOCO in-distributioncomputer vision32Apr 23, 2026
STL Motion PlanningCustom-built 2D environment (test)robotics embodied ai32Apr 21, 2026
Function CallingBFCL V4llm chat instructionagents tool use32Jun 8, 2026
VLM-as-a-JudgeMLLM-as-a-Judgemultimodalllm chat instruction32Apr 21, 2026
Medical Image ClassificationRetinaMNISTbio medicalcomputer vision32May 27, 2026
Mathematical ReasoningGSM8kllm chat instructionnlp32Apr 21, 2026
Source Code WatermarkingMBJPcode developer ai32Apr 21, 2026
Source Code WatermarkingMBCPPcode developer ai32Apr 21, 2026
Multi-modal UnderstandingMMEmultimodal32Jun 24, 2026