With demand for enterprise retrieval augmented technology (RAG) on the rise, the chance is ripe for mannequin suppliers to supply their tackle embedding fashions.
French AI firm Mistral threw its hat into the ring with Codestral Embed, its first embedding mannequin, which it stated outperforms present embedding fashions on benchmarks like SWE-Bench.
The mannequin focuses on code and “performs especially well for retrieval use cases on real-world code data.” The mannequin is offered to builders for $0.15 per million tokens.
The corporate stated the Codestral Embed “significantly outperforms leading code embedders” like Voyage Code 3, Cohere Embed v4.0 and OpenAI’s embedding mannequin, Textual content Embedding 3 Massive.
Codestral Embed, a part of Mistral’s Codestral household of coding fashions, could make embeddings that remodel code and knowledge into numerical representations for RAG.
“Codestral Embed can output embeddings with different dimensions and precisions, and the figure below illustrates the trade-offs between retrieval quality and storage costs,” Mistral stated in a weblog submit. “Codestral Embed with dimension 256 and int8 precision still performs better than any model from our competitors. The dimensions of our embeddings are ordered by relevance. For any integer target dimension n, you can choose to keep the first n dimensions for a smooth trade-off between quality and cost.”
Mistral examined the mannequin on a number of benchmarks, together with SWE-Bench and Text2Code from GitHub. In each instances, the corporate stated Codestral Embed outperformed main embedding fashions.
SWE- Bench
Text2Code
Use instances
Mistral stated Codestral Embed is optimized for “high-performance code retrieval” and semantic understanding. The corporate stated the code works greatest for a minimum of 4 sorts of use instances: RAG, semantic code search, similarity search and code analytics.
Embedding fashions usually goal RAG use instances, as they’ll facilitate sooner data retrieval for duties or agentic processes. Subsequently, it’s not stunning that Codestral Embed would give attention to that.
The mannequin can even carry out semantic code search, permitting builders to search out code snippets utilizing pure language. This use case works properly for developer instrument platforms, documentation techniques and coding copilots. Codestral Embed can even assist builders establish duplicated code segments or related code strings, which will be useful for enterprises with insurance policies concerning reused code.
The mannequin helps semantic clustering, which includes grouping code primarily based on its performance or construction. This use case would assist analyze repositories, categorize and discover patterns in code structure.
Competitors is rising within the embedding house
Mistral has been on a roll with releasing new fashions and agentic instruments. It launched Mistral Medium 3, a medium model of its flagship massive language mannequin (LLM), which at present powers its enterprise-focused platform Le Chat Enterprise.
It additionally introduced the Brokers API, which permits builders to entry instruments for creating brokers that carry out real-world duties and orchestrate a number of brokers.
Mistral’s strikes to supply extra mannequin choices to builders haven’t gone unnoticed in developer areas. Some on X observe that Mistral’s timing in releasing Codestral Embed is “coming on the heels of increased competition.”
Mistral AI Simply Dropped a Recreation-Changer: Codestral Embed Crushes OpenAI and Google in Code Search Race
French AI startup Mistral AI has quietly unleashed what may very well be probably the most vital breakthrough in code intelligence this 12 months. Their brand-new Codestral Embed mannequin is not…
— Rahul Khorwal (@rkrahulkhorwal) Could 28, 2025
Mistral on a supply mission
— Joel Basson (@joelbasson) Could 28, 2025
Nonetheless, Mistral should show that Codestral Embed performs properly not simply in benchmark testing. Whereas it competes towards extra closed fashions, comparable to these from OpenAI and Cohere, Codestral Embed additionally faces open-source choices from Qodo, together with Qodo-Embed-1-1.5 B.
VentureBeat reached out to Mistral about Codestral Embed’s licensing choices.
Each day insights on enterprise use instances with VB Each day
If you wish to impress your boss, VB Each day has you coated. We provide the inside scoop on what corporations are doing with generative AI, from regulatory shifts to sensible deployments, so you’ll be able to share insights for max ROI.
An error occured.
