List your company

Research

Benchmarks

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

309,131 benchmarksPage 653 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
Machine-Generated Text DetectionReuters (Claude)nlp36Feb 26, 2026
Machine-Generated Text DetectionReuters GPT4Allnlp36Feb 26, 2026
Mathematical ReasoningCHAMP standard (test)llm chat instructionnlp36Feb 26, 2026
Agent PerformanceACEBench Agentagents tool use36Feb 26, 2026
Question AnsweringNarrativeQAnlp36Feb 26, 2026
MathMath (test)llm chat instruction36Feb 26, 2026
ReasoningReasoning Benchmark Suite Aggregatellm chat instructionnlp36Mar 17, 2026
Multimodal Science Question AnsweringScienceQAmultimodalnlp36Feb 26, 2026
Legal Domain Fabrication and Factuality AnalysisJURIDICO-FCR 75 tasksnlpbio medical36Feb 26, 2026
Grid World NavigationFrozenLake (Source)robotics embodied ai36Feb 26, 2026
Issue ResolutionSWE-bench Verified (test)code developer ai36Feb 26, 2026
Embodied Task CompletionALFRED EBrobotics embodied ai36May 27, 2026
Graph-to-ImageSemArtgraphimage generation editing36Jul 1, 2026
Multi-turn Medical DiagnosisMed-Inquire DiagnosisArena (915 cases)llm chat instructionbio medical36Feb 26, 2026
Text Generation5 Generation tasksnlp36Feb 26, 2026
Concept UnlearningUnlearnDiffAtkcomputer visionnlp36Feb 26, 2026
Mathematical ReasoningOlympiadBenchllm chat instructionnlp36Mar 4, 2026
Phenotype predictionMIMIC-IVbio medicaltabular time series36May 12, 2026
Medical Visual Question AnsweringPMC-VQA (test)multimodalbio medical36Mar 25, 2026
Error DetectionImageNetnlp36May 26, 2026
Tamper LocalizationColumbiacomputer vision36Jun 24, 2026
Road SceneRoadSceneBenchcomputer vision36Feb 26, 2026
Text classificationSMS Spam Collection (5-fold cross-validation)nlp36Feb 26, 2026
Text classificationYelp (5-fold cross-validation)nlp36Feb 26, 2026
Text classificationDrug Review Norgestimate (5-fold cross-validation)nlp36Feb 26, 2026