Key Specifications
| Vendor | mistral |
| Version | ministral-3b |
| Release Date | 2024-10-16 |
| Context Window | 128000 tokens |
| Input Modalities | text |
| Output Modalities | text |
| License | Mistral Research License |
| Documentation | https://docs.mistral.ai/ |
Benchmark Performance
| Benchmark |
Score |
Unit |
Evaluated At |
Notes |
Source |
| MMLU |
42.4 |
% |
2024-10-16 |
5-shot |
view |
| HUMANEVAL |
37.2 |
pass@1 |
2024-10-16 |
— |
view |
| GSM8K |
32.2 |
% |
2024-10-16 |
0-shot CoT |
view |
| MATH |
10.1 |
% |
2024-10-16 |
0-shot CoT |
view |
| BBH |
50.1 |
% |
2024-10-16 |
3-shot CoT |
view |
| GPQA |
19 |
% |
2024-10-16 |
0-shot |
view |
| IFEVAL |
47.8 |
% |
2024-10-16 |
prompt_strict |
view |
| ARC |
81.5 |
% |
2024-10-16 |
challenge |
view |
| MUSR |
29.4 |
% |
2024-10-16 |
0-shot |
view |
| WINOGRANDE |
64.8 |
% |
2024-10-16 |
0-shot |
view |
Pricing
| Tier |
Price |
Currency |
| Input | $0.04 / Mtok | USD |
| Output | $0.04 / Mtok | USD |
| Cache Read | $0 / Mtok | USD |
| Cache Write | $0 / Mtok | USD |
Source:
https://mistral.ai/technology/
· as of 2024-10-16
Compliance
- Data Residency: EU
- SOC2: ✓
- HIPAA: ✗
- GDPR: ✓
- ISO 27001: ✓
Ministral 3B
Model Overview
Mistral Ministral 3B 超轻量边缘模型, 128K 上下文, 3B 参数, 最具性价比的边缘部署模型。
Core Specifications
| Vendor |
Version |
Release Date |
Context Window |
Input Modalities |
Output Modalities |
License |
| Mistral |
ministral-3b |
2024-10-16 |
128K |
text |
text |
Mistral Research License |
| Benchmark |
Score |
Unit |
Notes |
| MMLU (Massive Multitask Language Understanding) |
42.4 |
% |
5-shot |
| HumanEval |
37.2 |
pass@1 |
— |
| GSM8K (Grade School Math 8K) |
32.2 |
% |
0-shot CoT |
| MATH |
10.1 |
% |
0-shot CoT |
| BBH (BIG-Bench Hard) |
50.1 |
% |
3-shot CoT |
| GPQA |
19.0 |
% |
0-shot |
| IFEval |
47.8 |
% |
prompt_strict |
| ARC |
81.5 |
% |
challenge |
| MUSR |
29.4 |
% |
0-shot |
| WinoGrande |
64.8 |
% |
0-shot |
Pricing
| Input |
Output |
Cache Read |
Cache Write |
| — |
— |
— |
— |
per million tokens
Strengths
Weaknesses
- MMLU 42.4, weak knowledge reasoning.
- HumanEval 37.2, coding weak.
- Proprietary, not self-hostable.
Use Cases
- Long document summarization
References