List your company

Research

Benchmarks

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

309,131 benchmarksPage 832 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
Face ReconstructionORL face database (second subject)3d vision geometrycomputer vision30Jun 5, 2026
Deontic ReasoningDeonticBench USCIS-AAOnlp30Jun 4, 2026
Deontic ReasoningDeonticBench SARA-Binnlp30Jun 4, 2026
Deontic ReasoningDeonticBench Airlinenlp30Jun 4, 2026
Deontic ReasoningDeonticBench SARA-Numnlp30Jun 4, 2026
Jailbreak defense and Utility evaluationImplicit risk dataset Managementadversarial safety security30Jun 4, 2026
Jailbreak defense and Utility evaluationImplicit risk dataset Financeadversarial safety security30Jun 4, 2026
Jailbreak defense and Utility evaluationImplicit risk dataset Educationadversarial safety security30Jun 4, 2026
Mathematical problem solvingGSM8K (test)nlpagents tool use30Jun 4, 2026
Python program synthesisMBPP (test)code developer ai30Jun 4, 2026
Cross-model transfer attack accuracyCIFAR-10 (test)adversarial safety securitycomputer vision30Jun 4, 2026
Survival AnalysisFLCHAINtabular time series30Jun 15, 2026
Image RecognitionAsirracomputer vision30Jun 4, 2026
Face RecognitionKDEFcomputer vision30Jun 4, 2026
Face RecognitionCASIA-Face V5computer vision30Jun 4, 2026
Scientific ReasoningGPQAnlp30Jun 30, 2026
Preference AlignmentOpenRLHF Mixturellm chat instructionadversarial safety security30Jun 4, 2026
Preference AlignmentArgillallm chat instructionadversarial safety security30Jun 4, 2026
3D Bin Packing Problem3D-BPP ID-Small Discretemiscellaneous30Jun 4, 2026
3D Bin Packing Problem3D-BPP ID-Large Discretemiscellaneous30Jun 4, 2026
Classificationlabelmecomputer visionnlp+330Jul 7, 2026
Multi-hop reasoningMuSiQue Open Book (test)nlpllm chat instruction30Jun 4, 2026
Random Field ReconstructionRandom Field Model Example 3 Eq. (29) (test)miscellaneous30Jun 4, 2026
Language Model Downstream EvaluationLM Evaluation Harness zero-shot and five-shotllm chat instructionnlp30Jun 2, 2026
LLM Safety EvaluationHARMAMP Benign instancesadversarial safety securityllm chat instruction30Jun 2, 2026