List your company

Research

Benchmarks

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

309,131 benchmarksPage 988 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
Safety Behavior PredictionAssistant Turnsadversarial safety securityllm chat instruction27Jul 9, 2026
Document RetrievalCMDR-Benchretrieval search rag27Jul 8, 2026
2D Medical Image SegmentationPMTCXRcomputer visionbio medical27Jul 7, 2026
Candidate RetrievalRecGames 1retrieval search rag27Jul 7, 2026
Candidate RetrievalRecGames1retrieval search rag27Jul 7, 2026
Overthinking AttackFixed image subsetadversarial safety security27Jul 3, 2026
Model MergingTED Talks and XLSum 40 sequential tasks (test)nlp27Jul 2, 2026
Quadruped LocomotionBarkour MJX simulation (test)robotics embodied ai27Jul 2, 2026
Faithful CalibrationAverage across datasets (PQA, SA, SQA, HE, MMLU, SQ, MT, UM, AC, SG)llm chat instructionnlp27Jul 1, 2026
Faithful CalibrationPQAllm chat instructionnlp27Jul 1, 2026
Web NavigationMind2Web Allagents tool userobotics embodied ai27Jun 30, 2026
Text-to-Image GenerationDrawBench (200 prompts)image generation editing27Jun 30, 2026
Tabular ClassificationN. Thyroidtabular time series27Jun 30, 2026
Tabular Classificationglass6tabular time series27Jun 30, 2026
Tabular Classificationglass 5tabular time series27Jun 30, 2026
Tabular ClassificationFlare-Ftabular time series27Jun 30, 2026
Tabular ClassificationFetal Healthtabular time series27Jun 30, 2026
Tabular Classificationecoli 4tabular time series27Jun 30, 2026
Tabular Classificationecoli2tabular time series27Jun 30, 2026
Tabular ClassificationDry Beantabular time series27Jun 30, 2026
Truthful Question AnsweringTruthfulQAllm chat instructionnlp27Jun 30, 2026
Content InjectionContent Injection Scenarioadversarial safety security27Jun 30, 2026
Over-refusal evaluationPoisoned GPT4-LLM subsetllm chat instructionadversarial safety security27Jun 30, 2026
Omnidirectional Image Super-ResolutionSUN360 (test)computer vision27Jun 30, 2026
Omnidirectional Image Super-ResolutionODI-SR (test)computer vision27Jun 30, 2026