List your company

Research

Benchmarks

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

309,131 benchmarksPage 1869 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
Defense against adaptive adversarial attacksCelebAadversarial safety security18Mar 24, 2026
Defense against adaptive adversarial attacksBankadversarial safety security18Mar 24, 2026
Mathematical ReasoningGSM8Kllm chat instructionnlp18Mar 24, 2026
1D Regression1D Regression 20 points (test)tabular time series18Mar 24, 2026
MaxCutGSET (|V|>=3K)graph18May 26, 2026
MaxCutGSET |V|=2Kgraph18May 26, 2026
No-reference Image Quality AssessmentAGIQAcomputer vision18Mar 24, 2026
Edge DetectionBSDS (test)computer vision18Mar 24, 2026
Agentic CodingTerminal Bench 2.0agents tool usecode developer ai18May 28, 2026
Video UnderstandingTOMATOcomputer vision18Mar 31, 2026
Text-to-Image GenerationLAION 5B 1Kimage generation editing18Mar 24, 2026
Text-to-Image GenerationMS-COCO 1Kimage generation editing18Mar 24, 2026
End-to-end RetrievalMSMARCOretrieval search rag18Mar 24, 2026
Scientific Paper RetrievalSCIFULLBENCH ACL-EMNLP (Citations) 1.0retrieval search rag18Mar 24, 2026
Scientific Paper RetrievalSCIFULLBENCH ACL-EMNLP (References) 1.0retrieval search rag18Mar 24, 2026
Scientific Paper RetrievalSCIFULLBENCH ICLR-NeurIPS (Citations) 1.0retrieval search rag18Mar 24, 2026
Scientific Paper RetrievalSCIFULLBENCH ICLR-NeurIPS (References) 1.0retrieval search rag18Mar 24, 2026
Trajectory PredictionSimulated Datasetrobotics embodied aitabular time series18Mar 24, 2026
Trajectory PredictionNGSIMrobotics embodied aitabular time series18Mar 24, 2026
Diverse Image SegmentationLIDCcomputer vision18Mar 23, 2026
Diverse Image SegmentationCityscapescomputer vision18Mar 23, 2026
Value Function EstimationGame B Matrix Gamerobotics embodied ai18Mar 23, 2026
Sentiment ClassificationCM, EN, and HI (test)nlp18Mar 23, 2026
Sentiment ClassificationHindi (HI) (test)nlp18Mar 23, 2026
Sentiment ClassificationEnglish (EN) (test)nlp18Mar 23, 2026