Microsoft model product
MAI Code 1 Flash
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 17, 2026. Default version: MAI-Code-1-Flash
LLMBoard Score49.9MAI-Code-1-Flash
Coverage100%11 benchmark families
Context window256KTokens
Official input priceN/AOfficial price unavailable
MAI Code 1 Flash Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
MAI Code 1 Flash Benchmark Results
Benchmark scores for MAI-Code-1-Flash.
Sort by
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkAMO Bench | Score40.0% | Rank01 | Participants1 | Percentile100.0% | EvidenceC | Evaluated |
| BenchmarkFrontier Science | Score58.2% | Rank01 | Participants1 | Percentile100.0% | EvidenceC | Evaluated |
| BenchmarkRobust IF | Score61.2% | Rank01 | Participants1 | Percentile100.0% | EvidenceC | Evaluated |
| BenchmarkAdvancedIF | Score71.4% | Rank02 | Participants2 | Percentile0.0% | EvidenceC | Evaluated |
| BenchmarkArtifacts Bench | Score36.4% | Rank03 | Participants3 | Percentile0.0% | EvidenceC | Evaluated |
| BenchmarkAIME 2026 | Score92.5% | Rank13 | Participants21 | Percentile40.0% | EvidenceC | Evaluated |
| BenchmarkIFBench | Score75.0% | Rank13 | Participants34 | Percentile63.6% | EvidenceC | Evaluated |
| BenchmarkFrontierMath | Score6.3% | Rank16 | Participants17 | Percentile6.3% | EvidenceC | Evaluated |
| BenchmarkSWE-bench Multilingual | Score65.5% | Rank26 | Participants38 | Percentile32.4% | EvidenceC | Evaluated |
| BenchmarkTau2 Telecom | Score71.7% | Rank26 | Participants35 | Percentile26.5% | EvidenceC | Evaluated |
| BenchmarkTerminal-Bench 2.0 | Score54.8% | Rank30 | Participants51 | Percentile42.0% | EvidenceC | Evaluated |
| BenchmarkSWE-Bench Pro | Score51.2% | Rank45 | Participants50 | Percentile10.2% | EvidenceC | Evaluated |
| BenchmarkSWE-Bench Verified | Score71.6% | Rank57 | Participants111 | Percentile49.1% | EvidenceC | Evaluated |
| BenchmarkGPQA | Score84.6% | Rank61 | Participants239 | Percentile74.8% | EvidenceC | Evaluated |
| BenchmarkHumanity's Last Exam | Score18.0% | Rank67 | Participants99 | Percentile32.6% | EvidenceC | Evaluated |
MAI Code 1 Flash Arena Results
Preference and agent-evaluation results for the default version.
No Arena results
The default version does not have a matching Arena result yet.
MAI Code 1 Flash Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- N/A
- Official provider
- N/A
- Lowest third-party
- N/A
- Tracked offerings
- 1
Sort by
Provider | Provider model ID | Region | Input / 1M | Output / 1M | Context | Updated |
|---|
| ProviderGitHub Copilot | Provider model IDmai-code-1-flash-picker | Regionglobal | Input / 1M$0.75 | Output / 1M$4.5 | Context256K | Updated |
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
MAI Code 1 Flash Runtime Performance
Provider-specific output speed and catalog latency for MAI-Code-1-Flash. Runtime does not affect the capability score.
No runtime data
Browse runtime rankingsNo 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.
MAI Code 1 Flash Specifications
Technical details for the model's default version.
- Version
- MAI-Code-1-Flash
- Released
- Jun 2, 2026
- Knowledge cutoff
- Dec 1, 2025
- Parameters
- N/A
- Context window
- 256K
- Max output
- 128K
- Inputs
- text
- Outputs
- text
- Open weights
- No
- License
- Proprietary
MAI Code 1 Flash Versions
Available versions of this model. The score column identifies the version used in the overall ranking.
Sort by
Version | Released | LLMBoard | Parameters | Context | Max output | Open weights | License |
|---|
| VersionMAI-Code-1-Flash | Released | LLMBoard49.9 | ParametersN/A | Context256K | Max output128K | Open weightsNo | LicenseProprietary |
MAI Code 1 Flash vs nearby models
Open a comparison with the three ranked models immediately above and below this model.
Models similar to MAI Code 1 Flash
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
MI
MAI Code 1.1 Flash
Microsoft
MI
MAI Thinking 1
Microsoft
MI
Phi 4 Reasoning Plus
Microsoft
MI
Phi 4 Reasoning
Microsoft
MI
Phi 4 Mini Reasoning
Microsoft
MI
Phi 4
Microsoft
What is MAI Code 1 Flash?
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 2026-08-17.
FAQ
Common questions about MAI Code 1 Flash.
When was MAI Code 1 Flash released?
MAI Code 1 Flash's default version was released on Jun 2, 2026.
How much does MAI Code 1 Flash cost?
No official standard PAYG price is currently available for MAI Code 1 Flash.
Who created MAI Code 1 Flash?
MAI Code 1 Flash was created by Microsoft.
What is the context window for MAI Code 1 Flash?
The default version has a 256K token context window.
Is MAI Code 1 Flash open weight?
No. The default version is not marked as having publicly available weights.
How many API providers offer MAI Code 1 Flash?
1 provider offerings are linked to the default version.
What models should I compare MAI Code 1 Flash with?
Nearby ranked alternatives include MiMo V2 Omni, MiMo V2 Flash, Grok 4.1 Thinking.