Tencent Open-Sources WeMM-Embedding: A Top-Ranked Multimodal Model
abhishek__AI · x · 2026-08-28
Tencent has open-sourced WeMM-Embedding, a multimodal embedding model powering WeChat.
Key Features:
- Multimodal Understanding: Supports unified embeddings for text, images, videos, and visual documents.
- Multiple Sizes: Available in 2B, 4B, and 9B parameter versions.
- SOTA Performance: Achieves #1 ranking on both MMEB-v2 and v3 benchmarks.
- Use Case: Specifically built for multimodal retrieval tasks.
The model is 100% open source, with code and weights publicly available.
Related event: Tencent Open-Sources WeMM-Embedding, Tops MMEB Leaderboard(3 posts)→
More from Models
- Why AI Models Always Pick the Number 3 When Asked to Choose Between 1-4 — LChoshen · 2026-08-28
- Tavus launches Sparrow-2 for real-time conversational understanding — jasonkneen · 2026-08-28
- Model comparison: Qwen, GLM, and Grok pass while ChatGPT and Claude fail — QuixiAI · 2026-08-28
- Qwen4 speculation: 27B model may see a leap in intelligence — Iory1998 · 2026-08-28
- Sparse attention can replace global attention without downsides — stochasticchasm · 2026-08-28
- ChatGPT Invents Its Own German Dumpling Dialect, One Fake Word at a Time — Farbenmieze · 2026-08-28