Mistral Small (Sep '24)
MistralMistral開源權重Apache 2.0 · 商用許可
描述
Mistral Small 4 is Mistral AI's hybrid small model that unifies instruct, reasoning, multimodal understanding, and coding capabilities in a single efficient system. It uses a 119B-parameter Mixture-of-Experts architecture with native image input, a 256k context window, and configurable reasoning depth for general chat, coding agents, and long-context reasoning workloads.
發布日期
2024-09-17
參數規模
119.0B
上下文長度
256K
支援模態
image, text
能力雷達圖
20
general
14
coding
28
reasoning
28
science
24
agents
60
multimodal
排行榜排名
基準測試分數 (LLM Stats)
(LLM Stats (zeroeval))General
MMLU
80.7%自報
TriviaQA
80.3%自報
Arena Hard
58.3%自報
Instruction Following
IFBench
48.0%自報
Language
MMLU-Pro
78.0%自報
COLLIE
62.9%自報
Math
AIME 2025
83.8%自報
GSM8k
80.7%自報
MATH
46.0%自報
Reasoning
ARC-C
91.3%自報
GPQANYU + Cohere + Anthropic (2023)
71.2%自報
AA-LCR
71.2%自報
MBPP
0.70 / 100自報
AGIEval
65.8%自報
LiveCodeBench
63.6%自報
Vision
MMMU-Pro
60.0%自報
AA 評測指數
(Artificial Analysis)Math 500(OpenAI (2024), subset of Hendrycks et al. MATH (2021))56.3
Mmlu Pro(TIGER-Lab (Univ. of Waterloo, Toronto, CMU, 2024))52.9
Gpqa(NYU + Cohere + Anthropic (2023))38.1
Livecodebench(UC Berkeley + MIT + Cornell (2024))14.1
Aime(MAA (Mathematical Association of America))6.3
Intelligence Index(Artificial Analysis)5.8
Hle(Center for AI Safety + Scale AI (2025))4.3
LLM Stats 分類評分
(LLM Stats (zeroeval))Legal80
Math80
Finance80
Healthcare80
Language70
Long Context70
Physics70
Reasoning70
General70
Biology70
Chemistry70
Chat60
Multimodal60
Code60
Creativity60
Vision60
Writing60
Instruction Following50
定價
輸入價格免費
輸出價格免費
混合價格(3:1)免費
快取讀取價格$0.015 / 1M tokens
速度
Tokens/秒0.0
首Token延遲0.00s
首回答延遲0.00s
供應商價格排行
供應商價格排行
2 個供應商
最便宜: Mistral AI最貴: Helicone
供應商輸入輸出
1Mistral AI最便宜
$0
$0
2Helicone
$0.075
$0.2
比較該模型在不同 API 供應商之間的定價。