Microsoft model product
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.
Updated Aug 12, 2026. Default version: MAI-Code-1-Flash
Technical details for the model's default version.
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Benchmark scores for MAI-Code-1-Flash.
| AMO Bench | 40.0% | 01 | 1 | 100.0% | C | |
| Frontier Science | 58.2% | 01 | 1 | 100.0% | C | |
| Robust IF | 61.2% | 01 | 1 | 100.0% | C | |
| AdvancedIF | 71.4% | 02 | 2 | 0.0% | C | |
| Artifacts Bench | 36.4% | 03 | 3 | 0.0% | C | |
| AIME 2026 | 92.5% | 10 | 18 | 47.1% | C | |
| IFBench | 75.0% | 11 | 29 | 64.3% | C | |
| FrontierMath | 6.3% | 16 | 17 | 6.3% | C | |
| SWE-bench Multilingual | 65.5% | 24 | 34 | 30.3% | C | |
| Tau2 Telecom | 71.7% | 26 | 35 | 26.5% | C | |
| Terminal-Bench 2.0 | 54.8% | 29 | 49 | 41.7% | C | |
| SWE-Bench Pro | 51.2% | 41 | 45 | 9.1% | C | |
| SWE-Bench Verified | 71.6% | 54 | 105 | 49.0% | C | |
| GPQA | 84.6% | 57 | 234 | 76.0% | C | |
| Humanity's Last Exam | 18.0% | 62 | 93 | 33.7% | C |
Preference and agent-evaluation results for the default version.
The default version does not have a matching Arena result yet.
Provider-specific output speed and catalog latency for MAI-Code-1-Flash. Runtime does not affect the capability score.
No provider-specific speed or latency record is linked to the default version yet.
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
Official vendor API pricing appears first, followed by individual provider offers.
| GitHub Copilot | mai-code-1-flash-picker | global | $0.75 | $4.5 | 256K |
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
Available versions of this model. The score column identifies the version used in the overall ranking.
| MAI-Code-1-Flash | 50.4 | N/A | 256K | 128K | No | Proprietary |
Key information about MAI Code 1 Flash and its available data.
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.
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.
Data as of 2026-08-11.
Open a comparison with the three ranked models immediately above and below this model.
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
Common questions about MAI Code 1 Flash.
MAI Code 1 Flash's default version was released on Jun 2, 2026.
No official standard PAYG price is currently available for MAI Code 1 Flash.
MAI Code 1 Flash was created by Microsoft.
The default version has a 256K token context window.
No. The default version is not marked as having publicly available weights.
1 provider offerings are linked to the default version.
Nearby ranked alternatives include Gemini 3.1 Flash Lite, MiMo V2 Flash, Grok 4.1 Thinking.