Devstral Medium

MistralMistralProprietary

描述

Devstral Medium builds upon the strengths of Devstral Small and takes performance to the next level with a score of 61.6% on SWE-Bench Verified. Devstral Medium is available through the Mistral public API, and offers exceptional performance at a competitive price point, making it an ideal choice for businesses and developers looking for a high-quality, cost-effective model.

发布日期

2025-07-10

参数规模

—

上下文长度

128K

支持模态

text

能力雷达图

general

coding

reasoning

science

agents

multimodal

排行榜排名

领域	#排名	分数	来源
代码能力榜	439	29.0	AA
通用能力榜	481	29.0	AA
科学能力	515	25.0	AA

基准测试分数 (LLM Stats)

(LLM Stats (zeroeval))

Reasoning

SWE-Bench Verified

61.6%自报

AA 评测指数

(Artificial Analysis)

Mmlu Pro(TIGER-Lab (Univ. of Waterloo, Toronto, CMU, 2024))

70.8

Math 500(OpenAI (2024), subset of Hendrycks et al. MATH (2021))

70.7

Gpqa(NYU + Cohere + Anthropic (2023))

49.2

Livecodebench(UC Berkeley + MIT + Cornell (2024))

33.7

Lcr(Artificial Analysis)

32.0

Ifbench(Google Research (2023))

29.9

Tau2(Sierra + U Toronto + Vector Institute (2025))

19.9

Terminalbench Hard(Stanford × Laude Institute (2026))

9.1

Intelligence Index(Artificial Analysis)

9.0

Aime(MAA (Mathematical Association of America))

6.7

Math Index(Artificial Analysis)

4.7

Aime 25(MAA (Mathematical Association of America))

4.7

Hle(Center for AI Safety + Scale AI (2025))

3.8

LLM Stats 分类评分

(LLM Stats (zeroeval))

Reasoning

Frontend Development

General

Code

定价

输入价格免费

输出价格免费

混合价格(3:1)免费

速度

Tokens/秒0.0

首Token延迟0.00s

首回答延迟0.00s

供应商价格排行

1 个供应商

供应商输入输出

1Mistral

$0.4

比较该模型在不同 API 供应商之间的定价。

外部链接

LLM Stats Artificial Analysis