Mistral Small 3.1
MistralMistral오픈 웨이트Apache 2.0 · 상업적 사용 가능
설명
Mistral Small 3 is a 24B-parameter LLM licensed under Apache-2.0. It focuses on low-latency, high-efficiency instruction following, maintaining performance comparable to larger models. It provides quick, accurate responses for conversational agents, function calling, and domain-specific fine-tuning. Suitable for local inference when quantized, it rivals models 2–3× its size while using significantly fewer compute resources.
출시일
2025-03-17
파라미터
24.0B
컨텍스트 길이
33K
모달리티
image, text
능력 레이더
24
general
25
coding
19
reasoning
31
science
21
agents
60
multimodal
랭킹
벤치마크 점수 (LLM Stats)
(LLM Stats (zeroeval))Chat
MT-Bench
0.83 / 100자체 보고
IFEvalGoogle Research (2023)
82.9%자체 보고
Factuality
SimpleQA
10.4%자체 보고
General
Arena Hard
87.6%자체 보고
MMLU
80.6%자체 보고
TriviaQA
80.5%자체 보고
Wild Bench
52.2%자체 보고
Language
MMLU-Pro
66.8%자체 보고
Math
MATH
69.3%자체 보고
Multimodal
MMMU
59.3%자체 보고
Reasoning
HumanEvalOpenAI (2021)
88.4%자체 보고
MBPP
0.75 / 100자체 보고
GPQANYU + Cohere + Anthropic (2023)
46.0%자체 보고
AA 평가 지수
(Artificial Analysis)Math 500(OpenAI (2024), subset of Hendrycks et al. MATH (2021))70.7
Mmlu Pro(TIGER-Lab (Univ. of Waterloo, Toronto, CMU, 2024))65.9
Gpqa(NYU + Cohere + Anthropic (2023))45.4
Ifbench(Google Research (2023))29.9
Scicode(UIUC + Argonne National Lab (2024))27.8
Coding Index(Artificial Analysis)26.3
Terminalbench V2 126.2
Tau2(Sierra + U Toronto + Vector Institute (2025))25.1
Lcr(Artificial Analysis)22.3
Livecodebench(UC Berkeley + MIT + Cornell (2024))21.2
Aime(MAA (Mathematical Association of America))9.3
Terminalbench Hard(Stanford × Laude Institute (2026))7.6
Tau Banking7.4
Intelligence Index(Artificial Analysis)7.1
Hle(Center for AI Safety + Scale AI (2025))4.3
Math Index(Artificial Analysis)3.7
Aime 25(MAA (Mathematical Association of America))3.7
LLM Stats 카테고리 점수
(LLM Stats (zeroeval))Creativity90
Writing90
Chat80
Instruction Following80
Roleplay80
Structured Output80
Code80
Language70
Legal70
Math70
Reasoning70
Finance70
General70
Healthcare70
Communication70
Physics50
Biology50
Chemistry50
가격
입력 가격$0.11 / 1M 토큰
출력 가격$0.17 / 1M 토큰
혼합 가격 (3:1)$0.125 / 1M 토큰
속도
토큰/초0.0
첫 토큰 지연0.00s
첫 응답 지연0.00s
공급자 가격 순위
공급자 가격 순위
2개 공급자
최저가: DeepInfra최고가: Mistral
공급자입력출력
1DeepInfra최저가
$0
$0
2Mistral주요
$0.11
$0.17
이 모델의 다양한 API 공급자 간 가격 비교.