Mistral AI·2025-05-28 20:00· 2025-05-28

Codestral Embed

AI summary

Mistral AI released its first code-focused embedding model, Codestral Embed, outperforming Voyage Code 3, Cohere Embed v4.0 and OpenAI's large embedding model on real-world code retrieval.

Selection record

Threshold 60Official, first-handFirst 62Second 62

AdmittedSum of both 124 ≥ twice the threshold 120

Source tier: Official, first-hand; this tier's threshold is 60
Pre-filter: passed：发布代码嵌入模型，属AI技术
Why it was chosen: Retrieval comparisons and dimension-precision trade-offs support assessment of storage costs for code RAG.

A model scores each item twice, independently, against one written standard, out of 100. An item is admitted only when the two scores add up to twice the threshold. The threshold is set per source tier.

Source: Mistral AI · mistral.ai

#Model releases #Coding #RAG #Deployment