Unverified50% confidenceOpinionExact time
The top-ranked embedding model on MTEB often only ranks third or fourth in a specific domain, and sometimes worse.
1
Sources
50%
Confidence
Long-term
Relevance
10/13/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe MTP head parameter count is typically less than 1% of the main model and is jointly pre-trained with the main model.67% similarUnverifiedEach MTP head shares the hidden state representation of the main model and contains only a small feed-forward network and an output projection layer, with a parameter count typically less than 1% of the main model.63% similarUnverifiedThe same model may rank very differently across different evaluation platforms.60% similarUnverifiedSAGE outperforms the simple baseline on rank correlation and has a lower error rate.60% similarUnverifiedIn real-world RAG pipelines, switching between the top 15 MTEB-ranked embedding models produces performance fluctuations of 15 to 25 percentage points.60% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1021925API
curl https://kongchang.com/api/v1/knowledge/claims/1021925MCP
get_claim(id=1021925)