List your company

Research

Benchmarks

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

309,131 benchmarksPage 231 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
Few-shot node classificationCoraFullgraph68May 1, 2026
Paraphrase DetectionMRPCnlp68Jun 4, 2026
Multi-Hop ReasoningLoCoMonlpllm chat instruction68May 14, 2026
Scientific ReasoningTheoremQAnlp68May 1, 2026
Image ClassificationCaltech101computer vision68May 26, 2026
Translation Attack17 supported languages LLaMA-3.2 1Badversarial safety securitynlp68Mar 26, 2026
Web BrowsingBrowseCompagents tool use68May 18, 2026
ClassificationMNIST (test)computer visionnlp+368May 12, 2026
Mobile GUI AutomationAndroidWorldagents tool userobotics embodied ai68May 21, 2026
Mathematical ReasoningAIME 24llm chat instructionnlp68Jun 17, 2026
Question AnsweringBambooglenlp68May 11, 2026
Mathematical ReasoningMATHllm chat instructionnlp68Jun 19, 2026
Radiology Question AnsweringRadQA and Board-RadQA Combined (test)bio medicalnlp68Mar 9, 2026
Image ClassificationTinyImageNet-200computer vision68Mar 30, 2026
Out-of-Distribution DetectionAfrican Big Five (test)computer visiontabular time series68Mar 4, 2026
Vision-centric ReasoningRealWorldQAcomputer visionmultimodal68Jun 26, 2026
Deep ResearchBrowseCompmiscellaneous68Jun 9, 2026
Robust Image ClassificationCIFAR-10computer vision68May 27, 2026
Adversarial PurificationCIFAR-10adversarial safety securitycomputer vision68Jul 7, 2026
SIR dynamics forecastingErdős-Rényi graphs (out-of-sample)graphtabular time series68Feb 27, 2026
Safety AlignmentSalad Benchadversarial safety security68Mar 10, 2026
Safety AlignmentHH-RLHFadversarial safety security68Mar 10, 2026
Mathematical ReasoningMATH 500llm chat instructionnlp68May 8, 2026
Robotic ManipulationRoboCasarobotics embodied ai68Jul 7, 2026
3D point cloud semantic segmentationScanNet official (fold S1)3d vision geometry68Jul 1, 2026