Mistral AI model product
The smallest model in the Ministral 3 family, Ministral 3 3B is a powerful, efficient tiny language model with vision capabilities.
Updated Aug 12, 2026. Default version: Min istral 3 (3B Reasoning 2512)
Technical details for the model's default version.
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Benchmark scores for Min istral 3 (3B Reasoning 2512).
| AIME 2024 | 77.5% | 33 | 53 | 38.5% | C | |
| LiveCodeBench | 54.8% | 38 | 73 | 48.6% | C | |
| AIME 2025 | 72.1% | 84 | 114 | 26.6% | C | |
| GPQA | 53.4% | 169 | 234 | 27.9% | C |
Preference and agent-evaluation results for the default version.
The default version does not have a matching Arena result yet.
Provider-specific output speed and catalog latency for Min istral 3 (3B Reasoning 2512). Runtime does not affect the capability score.
| Mistral AI | 1,222 tok/s | 0.16 s | 131.1K | 131.1K |
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
Official vendor API pricing appears first, followed by individual provider offers.
| Mistral | ministral-3b-latest | global | $0.04 | $0.04 | 128K | |
| Clarifai | mistralai/completion/models/Ministral-3-3B-Reasoning-2512 | global | $1.04 | $0.5483 | 262.1K |
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
Available versions of this model. The score column identifies the version used in the overall ranking.
| Min istral 3 (3B Reasoning 2512) | 20.8 | 3B | 131.1K | 131.1K | No | Apache 2.0 |
Key information about Min istral 3 and its available data.
The smallest model in the Ministral 3 family, Ministral 3 3B is a powerful, efficient tiny language model with vision capabilities. This model is the reasoning post-trained version, trained for reasoning tasks, making it ideal for math, coding and stem related use cases.
The Ministral 3 family is designed for edge deployment, capable of running on a wide range of hardware. Ministral 3 3B can even be deployed locally, fitting in 16GB of VRAM in BF16, and less than 8GB of RAM/VRAM when quantized.
Data as of 2026-08-11.
Open a comparison with the three ranked models immediately above and below this model.
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
Common questions about Min istral 3.
Min istral 3's default version was released on Dec 4, 2025.
Min istral 3's official API price is $0.04 per million input tokens and $0.04 per million output tokens via Mistral. The lowest tracked third-party offer starts at $1.04 input and $0.5483 output via Clarifai.
Min istral 3 was created by Mistral AI.
The default version has a 131.1K token context window.
No. The default version is not marked as having publicly available weights.
2 provider offerings are linked to the default version.
Nearby ranked alternatives include Gemini 2.0 Flash Lite, Grok 2, Nova Pro.