跳轉到主要內容

Ministral 3 14B

MistralMistral開源權重Apache 2.0 · 商用許可

描述

A balanced model in the Ministral 3 family, Ministral 3 14B is a powerful, efficient tiny language model with vision capabilities. This model is the instruct post-trained version in FP8, fine-tuned for instruction tasks, making it ideal for chat and instruction based use cases. The Ministral 3 family is designed for edge deployment, capable of running on a wide range of hardware. Ministral 3 14B can even be deployed locally, capable of fitting in 24GB of VRAM in BF16, and less than 12GB of RAM/VRAM when quantized.

發布日期
2025-12-02
參數規模
14.0B
上下文長度
262K
支援模態
image, text

能力雷達圖

25
general
23
coding
35
reasoning
35
science
31
agents
10
multimodal

排行榜排名

領域#排名分數來源
程式碼能力榜487
22.0
AA
通用能力榜506
28.0
AA
科學能力467
30.0
AA

基準測試分數 (LLM Stats)

(LLM Stats (zeroeval))

Chat

MM-MT-Bench0.08 / 100自報

General

MMLU79.4%自報
TriviaQA74.9%自報
Multilingual MMLU74.2%自報
Wild Bench68.5%自報
Arena Hard55.1%自報

Language

MMLU-Redux82.0%自報

Math

MATH90.4%自報
AIME 202489.8%自報
AIME 202585.0%自報
MATH (CoT)67.6%自報

Reasoning

GPQANYU + Cohere + Anthropic (2023)71.2%自報
AGIEval64.8%自報
LiveCodeBench64.6%自報

AA 評測指數

(Artificial Analysis)
Mmlu Pro(TIGER-Lab (Univ. of Waterloo, Toronto, CMU, 2024))
69.3
Gpqa(NYU + Cohere + Anthropic (2023))
57.2
Livecodebench(UC Berkeley + MIT + Cornell (2024))
35.1
Ifbench(Google Research (2023))
32.0
Math Index(Artificial Analysis)
30.0
Aime 25(MAA (Mathematical Association of America))
30.0
Tau2(Sierra + U Toronto + Vector Institute (2025))
27.2
Lcr(Artificial Analysis)
26.3
Scicode(UIUC + Argonne National Lab (2024))
23.8
Coding Index(Artificial Analysis)
14.4
Terminalbench V2 1
9.7
Tau Banking
6.6
Intelligence Index(Artificial Analysis)
6.0
Hle(Center for AI Safety + Scale AI (2025))
4.6
Terminalbench Hard(Stanford × Laude Institute (2026))
4.5

LLM Stats 分類評分

(LLM Stats (zeroeval))
Math
90
Reasoning
70
General
60
Creativity
60
Writing
60
Communication
40
Chat
30
Multimodal
10

定價

輸入價格$0.2 / 1M tokens
輸出價格$0.2 / 1M tokens
混合價格(3:1)$0.2 / 1M tokens
快取讀取價格$0.02 / 1M tokens

速度

Tokens/秒91.3
首Token延遲0.52s
首回答延遲0.52s

供應商價格排行

供應商價格排行

4 個供應商

最便宜: Mistral最貴: Kilo Gateway
供應商輸入輸出
1Mistral主要
$0.2
$0.2
2NanoGPT
$0.2
$0.2
3OpenRouter
$0.2
$0.2
4Kilo Gateway
$0.2
$0.2

比較該模型在不同 API 供應商之間的定價。

外部連結