List your company

Research

Benchmarks

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

309,131 benchmarksPage 997 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
Truthfulness EvaluationTruthfulQAllm chat instructionnlp27May 13, 2026
Instruction FollowingIFEvalllm chat instruction27May 13, 2026
Pixel-level Anomaly LocalizationBraTScomputer vision27May 12, 2026
Pixel-level Anomaly LocalizationRESCcomputer vision27May 12, 2026
Pixel-level Anomaly LocalizationMPDDcomputer vision27May 12, 2026
Mathematical Problem SolvingAMC 2023nlpagents tool use27Jun 23, 2026
Node ClassificationPubmed 1-shotgraph27Jun 4, 2026
Node ClassificationCora 1-shotgraph27Jun 4, 2026
Node ClassificationCiteseer 1-shotgraph27Jun 4, 2026
Visual GroundingBLINKmultimodalcomputer vision27May 20, 2026
Reasoning2WikiMultiHopQA (OOD)llm chat instructionnlp27May 12, 2026
ReasoningMuSiQue (OOD)llm chat instructionnlp27May 12, 2026
ReasoningHotpotQA (ID)llm chat instructionnlp27May 12, 2026
Question Answering2WikiMultiHopQA (OOD)nlp27May 12, 2026
Question AnsweringMuSiQue (OOD)nlp27May 12, 2026
Question AnsweringHotpotQA (ID)nlp27May 12, 2026
Logical ReasoningSLR-BENCH (test)nlp27May 12, 2026
ReasoningGPQAllm chat instructionnlp27May 12, 2026
Video ReasoningVideoMathQA MCQcomputer vision27May 12, 2026
Video ReasoningVideoMMMU comprehensioncomputer vision27May 12, 2026
Video ReasoningVideoMMMU adaptationcomputer vision27May 12, 2026
Image ReasoningMMMU Pro Visioncomputer visionmultimodal27May 12, 2026
Image ReasoningMathVision minicomputer visionmultimodal27May 12, 2026
Image ReasoningMMStarcomputer visionmultimodal27May 12, 2026
Neural Super-Resolution for Mesh-Based SimulationsDataset 33d vision geometry27May 12, 2026