List your company

Research

Benchmarks

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

309,131 benchmarksPage 2040 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
4D Spatial-Temporal ReasoningMLLM4D-Bench3d vision geometrycomputer vision17Mar 4, 2026
Long-Video UnderstandingLongVideoBench 8s~60mcomputer vision17Mar 4, 2026
Affect recognitionWESAD (test)computer visionnlp+117Mar 13, 2026
Safety EvaluationAggregate JBB, SR, WJadversarial safety security17Mar 4, 2026
Safety EvaluationStrongReject (SR)adversarial safety security17Mar 4, 2026
Jailbreak SafetyWildJailbreakadversarial safety security17Mar 4, 2026
Jailbreak SafetyJailbreakBenchadversarial safety security17Mar 4, 2026
Video Object SegmentationMOSE v2 (val)computer vision17Mar 31, 2026
Video Object SegmentationMOSE v1 (val)computer vision17Mar 31, 2026
Multi-hop Question Answering2Wikinlpretrieval search rag17Mar 4, 2026
Multi-hop Question AnsweringHotPotQAnlpretrieval search rag17Mar 4, 2026
Zero-shot Question AnsweringBenchmarks (ArcC, ArcE, PiQA, Wino) Zero-shotnlpllm chat instruction17Mar 4, 2026
Multimodal Mathematical ReasoningMathVistamultimodalnlp+117Mar 4, 2026
Image ClassificationImageNet HRcomputer vision17Mar 4, 2026
Mathematical ReasoningMathVistallm chat instructionnlp17Mar 4, 2026
Zero-shot PredictionARC-Cnlpllm chat instruction17Feb 27, 2026
Response SelectionMWOZ 2.1nlp17Feb 27, 2026
Multi-hop Question Answering2WikiMHQA (test)nlpretrieval search rag17Feb 27, 2026
Multi-hop Question AnsweringMuSiQue v1 (test)nlpretrieval search rag17Feb 27, 2026
Multi-hop Question Answering2WikiMHQA in-distributionnlpretrieval search rag17Feb 27, 2026
Multi-hop Question AnsweringHotpotQA in-distributionnlpretrieval search rag17Feb 27, 2026
Multi-hop Question AnsweringMuSiQue in-distributionnlpretrieval search rag17Feb 27, 2026
Music-to-DanceAIST++multimodal17Feb 27, 2026
Vision-Language EvaluationMME (test)multimodalcomputer vision+117Feb 27, 2026
Visual CaptioningMS-COCO English In-domain (test)multimodalcomputer vision+117Feb 27, 2026