Microsoft logo

MAI-Code-1-Flash

Microsoft

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.

Key Specifications

Parameters
-
Context
-
Release Date
June 2, 2026
Average Score
57.2%

Timeline

Key dates in the model's history
Announcement
June 2, 2026
Last Update
September 12, 2026
Today
October 5, 2026

Technical Specifications

Parameters
-
Training Tokens
-
Knowledge Cutoff
-
Family
-
Capabilities
MultimodalZeroEval

Benchmark Results

Model performance metrics across various tests and benchmarks

Programming

Programming skills tests
SWE-Bench Verified
GitHub Copilot production harness • Self-reported
71.6%

Reasoning

Logical reasoning and analysis
GPQA
Diamond • Self-reported
84.6%

Other Tests

Specialized benchmarks
AdvancedIF
Single/multi-turn average • Self-reported
71.4%
AIME 2026
• Self-reported
92.5%
AMO Bench
• Self-reported
40.0%
Artifacts Bench
• Self-reported
36.4%
FrontierMath
Tier 1-3 • Self-reported
6.3%
Frontier Science
• Self-reported
58.2%
Humanity's Last Exam
Text only • Self-reported
18.0%
IFBench
Single/multi-turn average • Self-reported
75.0%
Robust IF
Single/multi-turn average • Self-reported
61.2%
SWE-bench Multilingual
GitHub Copilot production harness • Self-reported
65.5%
SWE-Bench Pro
GitHub Copilot production harness • Self-reported
51.2%
Tau2 Telecom
• Self-reported
71.7%
Terminal-Bench 2.0
GitHub Copilot production harness • Self-reported
54.8%

License & Metadata

License
proprietary
Announcement Date
June 2, 2026
Last Updated
September 12, 2026

Similar Models

All Models

Recommendations are based on similarity of characteristics: developer organization, multimodality, parameter size, and benchmark performance. Choose a model to compare or go to the full catalog to browse all available AI models.