跳转到主要内容

MAI-Code-1-Flash

MicrosoftProprietary

描述

MAI-Code-1-Flash is a Microsoft AI coding model built for fast, efficient assistance in everyday developer workflows, built end-to-end by Microsoft on clean and appropriately licensed data. It is trained directly with the GitHub Copilot harnesses used in production for agentic coding in real developer environments, and uses adaptive solution length control to stay concise on simple requests while spending more reasoning budget on complex tasks. It outperforms Claude Haiku 4.5 across coding benchmarks while using up to 60% fewer tokens, and is rolling out to GitHub Copilot individual users in Visual Studio Code via the model picker and the default Auto picker.

发布日期
2026-06-02
参数规模
上下文长度
支持模态

能力雷达图

60
general
60
coding
40
reasoning
68
science估算
60
agents
20
multimodal

缺少专门科学评测时,Science 由 LLM Stats 科学得分或推理能力估算。

排行榜排名

暂无排名数据

基准测试分数 (LLM Stats)

(LLM Stats (zeroeval))

Code

Artifacts Bench36.4%自报

Communication

Tau2 Telecom71.7%自报

Instruction Following

IFBench75.0%自报
AdvancedIF71.4%自报
Robust IF61.2%自报

Math

AIME 202692.5%自报
AMO Bench40.0%自报
FrontierMath6.3%自报

Reasoning

GPQANYU + Cohere + Anthropic (2023)84.6%自报
SWE-Bench Verified71.6%自报
SWE-bench Multilingual65.5%自报
Frontier Science58.2%自报
Terminal-Bench 2.0Stanford × Laude Institute (2026)54.8%自报
SWE-Bench ProPrinceton NLP (2024)51.2%自报
Humanity's Last Exam18.0%自报

AA 评测指数

(Artificial Analysis)

暂无 AA 评测数据

LLM Stats 分类评分

(LLM Stats (zeroeval))
Physics
80
Instruction Following
80
Biology
80
Chemistry
80
Communication
70
Reasoning
60
General
60
Code
60
Tool Calling
60
Frontend Development
50
Agents
50
Math
40
Vision
20

定价

暂无定价数据

速度

暂无速度数据

供应商价格排行

暂无提供商数据

外部链接