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

80
general
60
coding
40
reasoning
68
science估算
60
agents
20
multimodal

Science 在缺少专门科学评测时使用推理能力代理估算。

排行榜排名

领域#排名分数来源
智能体能力模型榜75
53.0
LS

基准测试分数 (LLM Stats)

Agents

Terminal-Bench 2.054.8%自报
SWE-Bench Pro51.2%自报

Biology

GPQA84.6%自报

Code

SWE-Bench Verified71.6%自报
SWE-bench Multilingual65.5%自报
Artifacts Bench36.4%自报

Communication

Tau2 Telecom71.7%自报

General

IFBench75.0%自报
AdvancedIF71.4%自报
Frontier Science58.2%自报

Instruction Following

Robust IF61.2%自报

Math

AIME 202692.5%自报
AMO Bench40.0%自报
Humanity's Last Exam18.0%自报
FrontierMath6.3%自报

AA 评测指数

暂无 AA 评测数据

LLM Stats 分类评分

General
80
Instruction Following
80
Physics
80
Biology
80
Chemistry
80
Frontend Development
70
Communication
70
Tool Calling
60
Reasoning
60
Code
60
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