LLM Reference

MAI-Code-1-Flash

Released
2026-06-02
Last refreshed
2026-06-15
Status
Researched 81d ago
ProprietaryCommercial use: conditionalCodingRAGAgentsLong contextJSON / Tool use

MAI-Code-1-Flash is worth evaluating for coding, rag, and agents when its provider route and context window match the workload.

Use it for

  • Teams evaluating coding, rag, and agents
  • Workloads that can use a 256k context window
  • Buyers comparing 1 tracked provider route

Do not use it for

  • Vision or document-understanding workloads
Specifications
Family
MAI
Released
2026-06-02
Context
256k
Specialization
code
Openness
Proprietary
License
ProprietaryCommercial use: conditional
Weights
Not released
Code
Unknown
Training
Fine-tuned
Created by

Applied AI products and platforms from Microsoft

Redmond, Washington, United States
Website
Pricing
Output / 1M
$4.50
Input / 1M
$0.750

Cheapest of 1 route · Microsoft Foundry · cache read $0.075

About

MAI-Code-1-Flash is Microsoft AI's lightweight agentic coding model built directly inside GitHub Copilot's production harness. It is designed for fast everyday developer workflows, adaptive thinking by task complexity, multi-turn instruction following, and token-efficient coding. Microsoft reports 51.2% on SWE-bench Pro versus 35.2% for Claude Haiku 4.5 in the same Copilot harness, plus stronger results on SWE-bench Verified, SWE-bench Multilingual, and Terminal-Bench 2.0 without publishing exact scores for those secondary benchmarks.

Top use-case fit: coding, agents, and build tasks

Coding

Q/$ D

2 relevant benchmarks in the decision map.

RAG

Included by capability and metadata signals in the decision map.

Agents

Q/$ C

1 relevant benchmark in the decision map.

Capabilities

ReasoningJSON / Tool use

Benchmark peer barsfor Coding

Benchmark scores(4)

Scores are benchmark-specific and are direction-aware: the same numeric gap can mean very different outcomes across suites. Use the leaderboard context and this model's provider route to decide whether the winning margin is meaningful for your workload.
BenchmarkScoreVersionEvaluationSource
SWE-bench Pro51.2GitHub Copilot production harnessObserved 2026-06-02Source
Google-Proof Q&A84.6GPQA Diamond (accuracy)Observed 2026-06-07Source
SWE-bench Verified71.6SWE-bench Verified (resolved)Observed 2026-06-07Source
Terminal-Bench 2.054.8Terminal-Bench 2.0 (accuracy%)Observed 2026-06-07Source

Migration checks

No linked migration route is available for this model yet.