Mistral: Ministral 3 3B 2512
Mistral's Ministral 3 3B 2512 has no benchmark data available, so capability cannot be reliably assessed. As a 3B-class model it is likely suited only to lightweight tasks, though vision support and tool calling are useful additions for its size.
Assessment date: March 14, 2026
Our methodology takes into account a range of factors including pricing, functionality, capabilities, benchmark performance, and real-world applicability. Rankings are reviewed and updated regularly as new models are released. Issues with our rankings? Contact us
The smallest model in the Ministral 3 family, Ministral 3 3B is a powerful, efficient tiny language model with vision capabilities.
Capabilities
Architecture
| Modality | Text + Image → Text |
| Tokenizer | Mistral |
| Parameters | 3B |
Model Information
Pricing
| Token Type | Cost per 1M tokens | Cost per 1K tokens |
|---|---|---|
| Input | $0.10 | $0.000100 |
| Output | $0.10 | $0.000100 |
Live Performance
Live endpoint metrics — refreshed every 30 minutes.
External Resources
Data sourced from OpenRouter API, Artificial Analysis and Hugging Face Open LLM Leaderboard. Scores are editorially curated by our team.
Last updated: March 15, 2026 7:52 pm