Benchmarks

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

309,131 indexed

Task	Dataset	Domain	Results	Last Update
driver-top3 classification	rel-f1	computer visionadversarial safety security	30	Jul 9, 2026
driver-dnf classification	rel-f1	computer vision	30	Jul 9, 2026
Multimodal Sentiment Analysis	MVSA-Single (test)	multimodalnlp	30	Jul 9, 2026
Multimodal Action Recognition	Kinetics-Sounds (KS) (test)	computer visionmultimodal	30	Jul 9, 2026
Multimodal Emotion Recognition	CREMA-D (test)	multimodalnlp+1