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.
發布日期
2026-06-02
參數規模
—
上下文長度
—
支援模態
—
能力雷達圖
60
general
60
coding
40
reasoning
68
science估算
60
agents
20
multimodal
缺少專門科學評測時,Science 由 LLM Stats 科學得分或推理能力估算。
排行榜排名
暫無排名資料
基準測試分數 (LLM Stats)
(LLM Stats (zeroeval))Code
Artifacts Bench
36.4%自報
Communication
Tau2 Telecom
71.7%自報
Instruction Following
IFBench
75.0%自報
AdvancedIF
71.4%自報
Robust IF
61.2%自報
Math
AIME 2026
92.5%自報
AMO Bench
40.0%自報
FrontierMath
6.3%自報
Reasoning
GPQANYU + Cohere + Anthropic (2023)
84.6%自報
SWE-Bench Verified
71.6%自報
SWE-bench Multilingual
65.5%自報
Frontier Science
58.2%自報
Terminal-Bench 2.0Stanford × Laude Institute (2026)
54.8%自報
SWE-Bench ProPrinceton NLP (2024)
51.2%自報
Humanity's Last Exam
18.0%自報
AA 評測指數
(Artificial Analysis)暫無 AA 評測資料
LLM Stats 分類評分
(LLM Stats (zeroeval))Physics80
Instruction Following80
Biology80
Chemistry80
Communication70
Reasoning60
General60
Code60
Tool Calling60
Frontend Development50
Agents50
Math40
Vision20
定價
暫無定價資料
速度
暫無速度資料
供應商價格排行
暫無提供商資料