Ministral 3 8B
Ministral 3 8B is Mistral AI's edge model built via Cascade Distillation, offering base, instruct, and reasoning variants with vision and a 256K context.
Model Overview
Capabilities, design details, and architectural traits
Ministral 3 8B - Frontier AI at the Edge
Ministral 3 8B is a parameter-efficient dense language model from Mistral AI, built for compute and memory constrained applications such as edge and local deployment. It is part of the Ministral 3 family and is derived through a documented training recipe rather than standard pretraining alone.
| Trait | Detail |
|---|---|
| Training method | Cascade Distillation: an iterative pruning and continued training with distillation technique |
| Variants | Base, Instruct, and Reasoning, each with image understanding capabilities |
| Context window | Up to 256K tokens |
| Vision encoder | A 410M parameter ViT inherited from Mistral Small 3.1 Base, kept frozen, with a newly trained projection layer |
| License | Apache 2.0 |
Token-Efficient Instruct Variant
The instruct variant often produces an order of magnitude fewer output tokens, favoring efficiency over verbosity in real-world use.
Reasoning Variant Thinks Longer
The reasoning variant spends more inference time working through a problem before answering, favoring accuracy when accuracy matters more than speed.
Benchmark Performance
Independent evaluations · Artificial Analysis
Accuracy & Capability Details
Compare Models Side-by-Side
Evaluate specifications, pricing, and independent benchmark indices
| Model Details | |||
|---|---|---|---|
| General Info | |||
| Provider | Mistral | Anthropic | Anthropic |
| Release Date | December 2, 2025 | September 22, 2026 | September 28, 2026 |
| Knowledge Cutoff | - | - | Jun 2026 |
| Context & Limits | |||
| Context Window | 262K | 1M Best Context Window | 1M Best Context Window |
| Pricing (per 1M tokens) | |||
| Input Pricing | $0.15 Best Input Pricing | $4 | $2 |
| Output Pricing | $0.15 Best Output Pricing | $20 | $10 |
| Modalities | |||
| Inputs | textimage | textimagefile | textimagefile |
| Outputs | text | text | text |
| Benchmarks (0-100) | |||
| Intelligence Index | 5.5 | 57.6 Best Intelligence Index | 56.0 |
| Coding Index | 9.7 | - | - |
| Agentic Index | 0.6 | - | - |
Humanity's Last Exam
Extremely difficult logical reasoning and knowledge.
Long Context Reasoning
Logical reasoning over long context windows.
SciCode Benchmark
Scientific coding and mathematical modeling.
Independent evaluation data provided by Artificial Analysis. To view the latest benchmarks and full details, visit their official site.
Explore more from Mistral
Other models by Mistral
Mistral Large 4 Preview
Mistral Medium 3.5
Mistral Large 3
Mistral Medium 3.1
Top AI Models
Leading alternatives by intelligence score
