llmboard.aiLeaderboard Center
Overall
Overall RankingOpen Models
Tools
Model DirectoryCompare Models
Capabilities
CodingReasoningMathKnowledgeInstruction Following
Price & Efficiency
Price & ValueCapability vs. PriceRuntime Performance
Modalities
Image GenerationVideo GenerationSpeech ModelsEmbeddings
Core Benchmarks
GPQAMMLU-ProAIME 2025SWE-Bench VerifiedMMLUHumanity's Last ExamLiveCodeBenchMATHHumanEvalMMMU-ProView all benchmarks
Methods
Scoring & Data
393 models668 benchmarks

Leaderboard Center

Overall RankingCodingCore BenchmarksPrice & ValueRuntime Performance

Modalities

All ModelsImage GenerationImage EditingVideo GenerationImage-to-VideoVideo EditingText-to-SpeechSpeech-to-TextEmbeddings

Data & Methods

Scoring MethodAll BenchmarksReasoningMath

Vendors

All VendorsOpenAIAnthropicGoogle
llmboard.aiCopyright 2026 llmboard.ai

Model vendor

Microsoft

Technology company

Updated Aug 11, 2026. Data as of 2026-08-11

Website
Models12
Versions12
Open defaults1
CountryUS

On this page

  • Models
  • Scores
  • Highlights
  • About
  • FAQ

Microsoft models

Default-version specifications and scored-version capability values are labeled separately.

12 rows
Columns

Show columns

MIMAI Thinking 1MicrosoftMAI-Thinking-155.1100.0%N/AClosed weightsJun 2, 2026MAI-Thinking-1
MIMAI Code 1 FlashMicrosoftMAI-Code-1-Flash50.4100.0%256KClosed weightsJun 2, 2026MAI-Code-1-Flash
MIPhi 4 Reasoning PlusMicrosoftPhi 4 Reasoning Plus26.8100.0%N/AClosed weightsApr 30, 2025Phi 4 Reasoning Plus
MIPhi 4 ReasoningMicrosoftPhi 4 Reasoning22.0100.0%N/AClosed weightsApr 30, 2025Phi 4 Reasoning
MIPhi 4 Mini ReasoningMicrosoftPhi 4 Mini Reasoning13.840.0%N/AClosed weightsApr 30, 2025Phi 4 Mini Reasoning
MIPhi 4MicrosoftPhi 49.4100.0%16KClosed weightsDec 12, 2024Phi 4
MIPhi 4 multimodalMicrosoftPhi-4-multimodal-instruct7.40.0%128KClosed weightsFeb 1, 2025Phi-4-multimodal-instruct
MIPhi 3.5 MoEMicrosoftPhi-3.5-MoE-instruct4.9100.0%N/AClosed weightsAug 23, 2024Phi-3.5-MoE-instruct
MIPhi 3.5 miniMicrosoftPhi-3.5-mini-instruct0.0100.0%128KClosed weightsAug 23, 2024Phi-3.5-mini-instruct
MIPhi 3.5 visionMicrosoftPhi-3.5-vision-instruct0.00.0%N/AClosed weightsAug 23, 2024Phi-3.5-vision-instruct
MIPhi 4 MiniMicrosoftPhi 4 Mini0.060.0%128KOpen weightsFeb 1, 2025Phi 4 Mini
MIMAI Image 2.5MicrosoftMAI-Image-2.5N/AN/AN/AClosed weightsN/ANot scored

Microsoft capability scores

Each unique model uses its latest scored version.

Microsoft LLMBoard scores

Microsoft Highlights

Leading Microsoft models by score, price and context window.

Top scoreMAI Thinking 155.1 LLMBoardLowest official inputPhi 4 Mini Reasoning$0.07 / 1MLargest contextMAI Code 1 Flash256K tokens
Open-weight defaults1of 12 models

What is Microsoft?

Background and model catalog information for Microsoft.

Technology company

Model ownership is separate from API hosting. One model can be offered by multiple API providers with different prices.

Vendor
Microsoft
Models
12
Versions
12
Country
US
Founded
Not available

Catalog data as of 2026-08-11.

FAQ

Common questions about Microsoft.

What is Microsoft's highest-ranked model?

MAI Thinking 1 currently has the strongest LLMBoard score from this vendor.

How many Microsoft models are tracked?

The catalog contains 12 independently selectable Microsoft models and 12 versions.

Does Microsoft host every listed model API?

Not necessarily. Vendor identifies the model developer; API providers are tracked separately.

Does Microsoft publish open-weight models?

1 current default versions are marked as open weight.