mteb

Vultr released the VultronRetriever family of models, including Prime-8B, Core-4.5B, and Flash-0.8B, which achieve top rankings on the MTEB leaderboard with high efficiency and offline capabilities.

This paper introduces MVEB, a large-scale benchmark for evaluating video embeddings across 23 tasks, finding that no single model dominates and that audio's contribution depends on dataset annotation provenance. It integrates into the MTEB ecosystem for unified multimodal evaluation.