Ministral 3 3B
MistralMistral开源权重Apache 2.0 · 商用许可
描述
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 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 3B can even be deployed locally, fitting in 16GB of VRAM in BF16, and less than 8GB of RAM/VRAM when quantized.
发布日期
2025-12-02
参数规模
3.0B
上下文长度
131K
支持模态
image, text
能力雷达图
19
general
13
coding
24
reasoning
23
science
21
agents
10
multimodal
排行榜排名
基准测试分数 (LLM Stats)
(LLM Stats (zeroeval))Chat
MM-MT-Bench
0.08 / 100自报
General
MMLU
70.7%自报
Multilingual MMLU
65.2%自报
TriviaQA
59.2%自报
Wild Bench
56.8%自报
Arena Hard
30.5%自报
Language
MMLU-Redux
73.5%自报
Math
MATH
83.0%自报
AIME 2024
77.5%自报
AIME 2025
72.1%自报
MATH (CoT)
60.1%自报
Reasoning
LiveCodeBench
54.8%自报
GPQANYU + Cohere + Anthropic (2023)
53.4%自报
AGIEval
51.1%自报
AA 评测指数
(Artificial Analysis)Mmlu Pro(TIGER-Lab (Univ. of Waterloo, Toronto, CMU, 2024))52.4
Gpqa(NYU + Cohere + Anthropic (2023))35.8
Ifbench(Google Research (2023))26.8
Tau2(Sierra + U Toronto + Vector Institute (2025))24.9
Livecodebench(UC Berkeley + MIT + Cornell (2024))24.7
Math Index(Artificial Analysis)22.0
Aime 25(MAA (Mathematical Association of America))22.0
Lcr(Artificial Analysis)17.0
Scicode(UIUC + Argonne National Lab (2024))15.3
Hle(Center for AI Safety + Scale AI (2025))5.4
Intelligence Index(Artificial Analysis)4.8
Coding Index(Artificial Analysis)4.8
Tau Banking4.7
Terminalbench Hard(Stanford × Laude Institute (2026))0.0
Terminalbench V2 10.0
LLM Stats 分类评分
(LLM Stats (zeroeval))Math80
Reasoning60
General40
Communication30
Creativity30
Writing30
Chat20
Multimodal10
定价
输入价格$0.1 / 1M tokens
输出价格$0.1 / 1M tokens
混合价格(3:1)$0.1 / 1M tokens
缓存读取价格$0.01 / 1M tokens
速度
Tokens/秒239.9
首Token延迟0.52s
首回答延迟0.52s
供应商价格排行
供应商价格排行
4 个供应商
最便宜: Mistral最贵: Kilo Gateway
供应商输入输出
1Mistral主要
$0.1
$0.1
2NanoGPT
$0.1
$0.1
3OpenRouter
$0.1
$0.1
4Kilo Gateway
$0.1
$0.1
比较该模型在不同 API 供应商之间的定价。