MAI-Code-1-Flash

Tool callingStructured outputReasoning

Model card Website

Microsoft coding model built for fast, efficient assistance in everyday developer workflows

Context: 256K
Released: 4mo ago

Sources:models.dev

Benchmarks

DeepSWE is the primary coding benchmark where an exact model evaluation exists. Other sourced evaluations appear below; missing scores are not zero.

Not evaluated in DeepSWE 1.1 as of 2026-09-22. Results are only shown for exact model versions in the official dataset. Official leaderboard.

No benchmark results have been matched to this model yet.

Specifications

Developer: Microsoft
Model family: MAI Code
Type: Language model
Predecessor: —
Successor: —
Released: June 2, 2026
Model ID: microsoft/mai-code-1-flash
Openness: Closed
License: —
Input modalities: text
Output modalities: text
Modality: text->text
Max output tokens: 128K
Knowledge cutoff: 2025-12
Hugging Face: —
Source freshness: Metadata synced Oct 8, 2026, 10:17 PM UTC

Additional source evidence

Source model: microsoft/mai-code-1-flash
Source family: mai
Last updated: 2026-06-08
Knowledge cutoff: 2025-12
Model context: 256K
Model output limit: 128K
Open weights: No
File attachments: No
Reasoning: Yes
Tool calling: Yes
Structured output: Yes
Temperature control: Yes

Published benchmarks

Benchmark	Score	Evaluation details	Evidence
SWE-Bench Pro	51.2 · resolve rate	GitHub Copilot · 2026-06-02	Source
SWE-Bench Verified	71.6 · resolved	—	Source
Terminal-Bench	54.8 · success rate	2.0	Source
GPQA Diamond	84.6 · accuracy	—	Source

Official references

Complete source record (JSON)

{
  "id": "microsoft/mai-code-1-flash",
  "name": "MAI-Code-1-Flash",
  "description": "Microsoft coding model built for fast, efficient assistance in everyday developer workflows",
  "family": "mai",
  "last_updated": "2026-06-08",
  "knowledge": "2025-12",
  "attachment": false,
  "reasoning": true,
  "tool_call": true,
  "structured_output": true,
  "temperature": true,
  "modalities": {
    "input": [
      "text"
    ],
    "output": [
      "text"
    ]
  },
  "limit": {
    "context": 256000,
    "output": 128000
  },
  "benchmarks": [
    {
      "name": "SWE-Bench Pro",
      "score": 51.2,
      "source": "https://microsoft.ai/news/introducingmai-code-1-flash/",
      "metric": "resolve rate",
      "harness": "GitHub Copilot",
      "date": "2026-06-02"
    },
    {
      "name": "SWE-Bench Verified",
      "score": 71.6,
      "source": "https://llm-stats.com/benchmarks/swe-bench-verified",
      "metric": "resolved"
    },
    {
      "name": "Terminal-Bench",
      "score": 54.8,
      "source": "https://llm-stats.com/benchmarks/terminal-bench-2",
      "metric": "success rate",
      "version": "2.0"
    },
    {
      "name": "GPQA Diamond",
      "score": 84.6,
      "source": "https://llm-stats.com/benchmarks/gpqa",
      "metric": "accuracy"
    }
  ],
  "release_date": "2026-06-02",
  "open_weights": false,
  "links": [
    {
      "url": "https://microsoft.ai/pdf/MAI-Code-1-Flash-Model-Card.PDF",
      "label": "Model card",
      "type": "model_card"
    },
    {
      "url": "https://microsoft.ai/news/introducingmai-code-1-flash/",
      "label": "Announcement",
      "type": "announcement"
    }
  ]
}

Infrastructure

Provider availability

All providers

Provider endpoint data will appear after this model's first OpenRouter endpoint sync.