List your company

Research

Benchmarks

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

309,131 benchmarksPage 1075 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
Reward Modeling Suitability EvaluationRM Bench Safety-acceptllm chat instructionadversarial safety security26Feb 26, 2026
Reward ModelingReward Bench safety subset response perturbations 2llm chat instruction26Feb 26, 2026
Reward ModelingReward Bench safety subset prompt perturbations 2llm chat instruction26Feb 26, 2026
Reward Model Suitability AuditRM Bench Chatllm chat instructionadversarial safety security26Feb 26, 2026
Mathematical reasoningAIME 25llm chat instructionnlp26Feb 26, 2026
AlignmentIFEval strict promptllm chat instruction26May 19, 2026
Code GenerationLiveCodeBench v3code developer ai26Feb 26, 2026
Commonsense ReasoningHSwagnlp26Mar 4, 2026
Code ReasoningMBPPcode developer ainlp26May 20, 2026
Mathematical ReasoningMATH 500llm chat instructionnlp26Mar 19, 2026
Toxicity ClassificationAverage across WZ, DC, HX, ORnlp26Feb 26, 2026
Toxicity ClassificationORnlp26Feb 26, 2026
Toxicity ClassificationHXnlp26Feb 26, 2026
Toxicity ClassificationDCnlp26Feb 26, 2026
Toxicity ClassificationWZnlp26Feb 26, 2026
Question AnsweringNaturalQAnlp26Feb 26, 2026
Misinformation DetectionPHEMEnlp26Feb 26, 2026
Citation Hallucination DetectionNeuCLIR 2024 (test)retrieval search ragnlp26Feb 26, 2026
Deep Searchxbench DeepSearch (test)retrieval search ragagents tool use26Feb 26, 2026
Question AnsweringComQAnlp26May 14, 2026
Agricultural Agent Planning and ExecutionAgriAgent Non-Zeroagents tool userobotics embodied ai26Feb 26, 2026
Agricultural Agent Planning and ExecutionAgriAgent Full setagents tool userobotics embodied ai26Feb 26, 2026
Toxicity EvaluationBOLDadversarial safety securitynlp26Jun 1, 2026
Coreference ResolutionXWinogradnlp26May 22, 2026
Prompt classificationToxiCadversarial safety securityllm chat instruction26Jul 3, 2026