Ministral 3 8B
MistralMistral開源權重Mistral Research License
描述
The Ministral-8B-Instruct-2410 is an instruct fine-tuned model for local intelligence, on-device computing, and at-the-edge use cases, significantly outperforming existing models of similar size.
發布日期
2025-12-02
參數規模
8.0B
上下文長度
—
支援模態
image, text
能力雷達圖
25
general
18
coding
34
reasoning
29
science
29
agents
80
multimodal
排行榜排名
基準測試分數 (LLM Stats)
(LLM Stats (zeroeval))Biology
GPQANYU + Cohere + Anthropic (2023)
66.8%自報
Code
LiveCodeBench
61.6%自報
HumanEvalOpenAI (2021)
34.8%自報
Communication
MT-Bench
0.83 / 100自報
Wild Bench
66.8%自報
MM-MT-Bench
0.08 / 100自報
Creativity
Arena Hard
70.9%自報
Finance
MMLU
65.0%自報
French MMLU
57.5%自報
General
MMLU-Redux
79.3%自報
ARC-C
71.9%自報
Multilingual MMLU
70.6%自報
MBPP pass@1
70.0%自報
TriviaQA
65.5%自報
AGIEval
48.3%自報
Language
Winogrande
75.3%自報
Math
AIME 2024
86.0%自報
AIME 2025
78.7%自報
MATH (CoT)
62.6%自報
MATH
54.5%自報
AA 評測指數
(Artificial Analysis)Math Index(Artificial Analysis)31.7
Coding Index(Artificial Analysis)9.7
Intelligence Index(Artificial Analysis)9.0
Mmlu Pro(TIGER-Lab (Univ. of Waterloo, Toronto, CMU, 2024))0.6
Gpqa(NYU + Cohere + Anthropic (2023))0.5
Aime 25(MAA (Mathematical Association of America))0.3
Livecodebench(UC Berkeley + MIT + Cornell (2024))0.3
Ifbench(Google Research (2023))0.3
Tau2(Sierra + U Toronto + Vector Institute (2025))0.3
Lcr(Artificial Analysis)0.3
Scicode(UIUC + Argonne National Lab (2024))0.2
Terminalbench Hard(Stanford × Laude Institute (2026))0.0
Hle(Center for AI Safety + Scale AI (2025))0.0
Terminalbench V2 10.0
Tau Banking0.0
LLM Stats 分類評分
(LLM Stats (zeroeval))Roleplay80
Communication80
Creativity80
Language70
Finance70
Healthcare70
Writing70
Legal60
Math60
Reasoning60
General60
Code30
定價
輸入價格$0.15 / 1M tokens
輸出價格$0.15 / 1M tokens
混合價格(3:1)$0.15 / 1M tokens
速度
Tokens/秒105.5
首Token延遲0.49s
首回答延遲0.49s
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最便宜
$0.1
$0.1
2NanoGPT
$0.15
$0.15
3OpenRouter
$0.15
$0.15
4Kilo Gateway
$0.15
$0.15
比較該模型在不同 API 供應商之間的定價。