List your company

Research

Benchmarks

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

309,131 benchmarksPage 540 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
Graph Fraud DetectionYelp (test)graph40May 26, 2026
Graph Fraud DetectionAmazon (test)graph40May 26, 2026
Image ClassificationCaltech101computer vision40Jun 23, 2026
Computational Complexity AnalysisWildGuardMix 1.0 (test)miscellaneous40May 26, 2026
Safety MonitoringWildGuardMix (test)adversarial safety security40May 26, 2026
ClassificationLiver ultrasound dataset (10% train, 90% test)computer visionnlp+340May 26, 2026
Semi-supervised classificationADNI CN vs. AD (90% test)computer vision40May 26, 2026
Long-context understandingLongBenchllm chat instructionnlp40Jun 11, 2026
GenerationCoding domainllm chat instruction40May 26, 2026
GenerationQA domainllm chat instruction40May 26, 2026
GenerationMath domainllm chat instruction40May 26, 2026
Code GenerationCodingcode developer ai40May 26, 2026
Question AnsweringQAnlp40May 26, 2026
Safety and Utility EvaluationSafety and Utility evaluation suite (test)adversarial safety securityllm chat instruction40May 26, 2026
Semi-supervised image classificationCorel5k 10% (train)computer vision40May 26, 2026
Semi-supervised image classificationFlowers 10% (train)computer vision40May 26, 2026
Zero-shot Reasoning and General KnowledgeEvaluation Suite Zero-shot (PIQA, ARC-Easy, ARC-Challenge, HellaSwag, WinoGrande, MathQA, MMLU)llm chat instructionnlp40May 25, 2026
Text-to-SpeechSeed-TTS-Eval (test)speech audio40Jun 4, 2026
Matrix EstimationMovieLens Symmetric Noisetabular time series40May 21, 2026
Matrix EstimationMovieLens Pairflip Noisetabular time series40May 21, 2026
Mathematical ReasoningMathematical Reasoning Suite GSM8K, MATH, SVAMP, SimulEq, AQuA, SAT, MMLUllm chat instructionnlp40May 21, 2026
Question AnsweringTriviaQAnlp40May 20, 2026
Selective Question AnsweringTriviaQAnlpretrieval search rag40May 20, 2026
Engineering Design Workflow EvaluationBeams2Dmiscellaneous40May 20, 2026
Faithfulness EvaluationImageNet-1Knlp40May 19, 2026