Mistral Small 3.2
MistralMistral開源權重Apache 2.0 · 商用許可
描述
Mistral-Small-3.2-24B-Instruct-2506 is a minor update of Mistral-Small-3.1-24B-Instruct-2503.
發布日期
2025-06-20
參數規模
23.6B
上下文長度
128K
支援模態
image, text
能力雷達圖
26
general
19
coding
40
reasoning
34
science
34
agents
90
multimodal
排行榜排名
基準測試分數 (LLM Stats)
(LLM Stats (zeroeval))Factuality
SimpleQA
12.1%自報
General
IF
84.8%自報
MMLU
80.5%自報
Wild Bench
65.3%自報
Arena Hard
43.1%自報
Language
MMLU-Pro
69.1%自報
Math
MATH
69.4%自報
MathVista
67.1%自報
Multimodal
MMMU
62.5%自報
Reasoning
HumanEval Plus
92.9%自報
ChartQAMasry et al. (2022)
87.4%自報
MBPP Plus
78.3%自報
GPQANYU + Cohere + Anthropic (2023)
46.1%自報
Vision
DocVQADocVQA (2020)
94.9%自報
AI2D
92.9%自報
AA 評測指數
(Artificial Analysis)Math 500(OpenAI (2024), subset of Hendrycks et al. MATH (2021))88.3
Mmlu Pro(TIGER-Lab (Univ. of Waterloo, Toronto, CMU, 2024))68.1
Gpqa(NYU + Cohere + Anthropic (2023))50.5
Ifbench(Google Research (2023))33.5
Aime(MAA (Mathematical Association of America))32.3
Tau2(Sierra + U Toronto + Vector Institute (2025))29.5
Scicode(UIUC + Argonne National Lab (2024))28.6
Livecodebench(UC Berkeley + MIT + Cornell (2024))27.5
Math Index(Artificial Analysis)27.0
Aime 25(MAA (Mathematical Association of America))27.0
Lcr(Artificial Analysis)20.3
Coding Index(Artificial Analysis)12.5
Intelligence Index(Artificial Analysis)8.2
Terminalbench Hard(Stanford × Laude Institute (2026))6.8
Tau Banking6.2
Terminalbench V2 15.6
Hle(Center for AI Safety + Scale AI (2025))4.3
Terminalbench V4 00.0
LLM Stats 分類評分
(LLM Stats (zeroeval))Image To Text90
Multimodal80
Vision80
Language70
Legal70
Math70
Finance70
General70
Healthcare70
Communication70
Reasoning60
Physics50
Biology50
Chemistry50
Chat40
Creativity40
Writing40
Factuality10
定價
輸入價格$0.075 / 1M tokens
輸出價格$0.2 / 1M tokens
混合價格(3:1)$0.106 / 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
3 個供應商
最便宜: DeepInfra最貴: DevPass (LLM Gateway)
供應商輸入輸出
1DeepInfra最便宜
$0
$0
2Mistral主要
$0.075
$0.2
3DevPass (LLM Gateway)
$0.1
$0.3
比較該模型在不同 API 供應商之間的定價。