Key Specifications

Vendormistral
Versionministral-3b
Release Date2024-10-16
Context Window128000 tokens
Input Modalitiestext
Output Modalitiestext
LicenseMistral Research License
Documentationhttps://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 / MtokUSD
Output$0.04 / MtokUSD
Cache Read$0 / MtokUSD
Cache Write$0 / MtokUSD

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 Performance

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

  • Context window 128K.

Weaknesses

  • MMLU 42.4, weak knowledge reasoning.
  • HumanEval 37.2, coding weak.
  • Proprietary, not self-hostable.

Use Cases

  • Long document summarization

References