Home / Companies / Mixedbread / Blog / Post Details
Content Deep Dive

Beyond the Limit: Introduce Mixedbread Wholembed v3

Blog post from Mixedbread

Post Details
Company
Date Published
Author
Mixedbread Team
Word Count
1,096
Company Posts That Month
2
Language
English
Hacker News Points
4
Post removed?
No
Summary

Mixedbread has released Wholembed v3, a unified late-interaction retrieval model designed for multilingual, multimodal search across text, images, audio, and video, which will power all new Mixedbread Search stores by default. The company positions the model as a response to limitations in traditional semantic retrieval, particularly for complex agentic applications and real-world data such as OCR documents, scanned PDFs, screenshots, and instructional videos. Wholembed v3 reportedly achieved state-of-the-art results on the LIMIT benchmark, where it surpassed BM25 lexical retrieval with 92.45 Recall@5 versus 85.7, and was also evaluated for supporting deep-research agents on BrowseComp-Plus. Mixedbread attributes its performance to precise candidate discrimination and robustness to noisy, heterogeneous information, while claiming partner testing showed it could replace more complex retrieval pipelines across several domains. The model is publicly available through Mixedbread Search, includes built-in audio and video support, offers new users two million free tokens, and is accessible through the platform or API.

Trends Found in this Post
Trend Post Mentions Total Month Mentions Posts Companies MoM
Vector Search 2 3,215 679 175 +33%
Developer Experience 1 963 451 130 +91%
Use This Data

Use this post, company, and trend context to find content marketing opportunities, perform competitive analysis, or address product feature gaps via the Plushcap MCP server or the Plushcap API.