ModelLLMsv1.0

E5-Mistral-7B-Instruct

by Microsoft · open-source · Last verified 2026-03-17

Microsoft's instruction-tuned embedding model built on Mistral 7B, achieving state-of-the-art performance among open-source embeddings. Uses task-specific prompting to generate high-quality embeddings for diverse retrieval scenarios.

https://huggingface.co/intfloat/e5-mistral-7b-instruct ↗

C+

C+—Average

Adoption: C+Quality: B+Freshness: C+Citations: BEngagement: F

Specifications

License: MIT
Pricing: open-source
Capabilities: embedding, semantic-search, instruction-following, task-specific-embedding, passage-retrieval
Integrations: huggingface, langchain, sentence-transformers, vllm
Use Cases: semantic-search, document-retrieval, question-answering, text-classification
API Available: No
Parameters: 7B
Context Window: 32K tokens
Modalities: text
Training Cutoff: Mid 2023
Tags: embedding, open-source, instruction-tuned, mistral-based, microsoft
Added: 2026-03-17
Completeness: 92%

Index Score

53.3

Adoption

Quality

Freshness

Citations

Engagement

Explore the full AI ecosystem on Agents as a Service