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

Mistral AI

French AI company

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

Website
Models22
Versions44
Open defaults8
CountryFR

On this page

  • Models
  • Scores
  • Highlights
  • About
  • FAQ

Mistral AI models

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

22 rows
Columns

Show columns

MAMistral Medium 3.5Mistral AIMistral Medium 3.549.260.0%262.1KOpen weightsApr 29, 2026Mistral Medium 3.5
MAMistral Small 4Mistral AIMistral Small 433.4100.0%256KOpen weightsMar 16, 2026Mistral Small 4
MAMinistral 3Mistral AIMinistral 3 (8B Reasoning 2512)29.060.0%262.1KClosed weightsDec 4, 2025Ministral 3 (8B Reasoning 2512)
MADevstral MediumMistral AIDevstral Medium24.020.0%128KClosed weightsJul 10, 2025Devstral Medium
MAPixtral LargeMistral AIPixtral Large21.20.0%128KClosed weightsNov 18, 2024Pixtral Large
MAMin istral 3Mistral AIMin istral 3 (3B Reasoning 2512)20.860.0%131.1KClosed weightsDec 4, 2025Min istral 3 (3B Reasoning 2512)
MAMagistral SmallMistral AIMagistral Small 250619.860.0%131.1KOpen weightsJun 10, 2025Magistral Small 2506
MAMagistral MediumMistral AIMagistral Medium19.880.0%N/AClosed weightsJun 10, 2025Magistral Medium
MADevstral Small 1.1Mistral AIDevstral Small 1.117.120.0%128KOpen weightsJul 11, 2025Devstral Small 1.1
MAMistral Small 3.2 24BMistral AIMistral Small 3.2 24B Instruct15.980.0%N/AClosed weightsJun 20, 2025Mistral Small 3.2 24B Instruct
MAMistral Large 3Mistral AIMistral Large 3 (675B Instruct 2512)15.880.0%262.1KOpen weightsDec 4, 2025Mistral Large 3 (675B Instruct 2512)
MAMistral Small 3.1 24BMistral AIMistral Small 3.1 24B Instruct8.480.0%N/AClosed weightsMar 17, 2025Mistral Small 3.1 24B Instruct
MAMistral Small 3 24BMistral AIMistral Small 3 24B Instruct7.5100.0%32KClosed weightsJan 30, 2025Mistral Small 3 24B Instruct
MAMistral Large 2Mistral AIMistral Large 27.080.0%128KClosed weightsJul 24, 2024Mistral Large 2
MACodestral 22BMistral AICodestral-22B1.620.0%N/AClosed weightsMay 29, 2024Codestral-22B
MAMinistral 8BMistral AIMinistral 8B Instruct0.0100.0%131.1KOpen weightsOct 16, 2024Ministral 8B Instruct
MAMistral NeMoMistral AIMistral NeMo Instruct0.040.0%128KClosed weightsJul 18, 2024Mistral NeMo Instruct
MAPixtral 12BMistral AIPixtral-12B0.080.0%128KOpen weightsSep 17, 2024Pixtral-12B
MADevstral 2Mistral AIDevstral 2N/AN/A262.1KOpen weightsDec 9, 2025Not scored
MAMistral Medium 3Mistral AIMistral Medium 3N/AN/A131.1KClosed weightsMay 7, 2025Not scored
MAMistral SmallMistral AIMistral SmallN/AN/A32.8KClosed weightsSep 17, 2024Not scored
MAVoxtral MiniMistral AIVoxtral MiniN/AN/AN/AClosed weightsN/ANot scored

Mistral AI capability scores

Each unique model uses its latest scored version.

Mistral AI LLMBoard scores

Mistral AI Highlights

Leading Mistral AI models by score, price and context window.

Top scoreMistral Medium 3.549.2 LLMBoardLowest official inputMin istral 3$0.04 / 1MLargest contextDevstral 2262.1K tokens
Open-weight defaults8of 22 models

What is Mistral AI?

Background and model catalog information for Mistral AI.

French AI company

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

Vendor
Mistral AI
Models
22
Versions
44
Country
FR
Founded
Not available

Catalog data as of 2026-08-11.

FAQ

Common questions about Mistral AI.

What is Mistral AI's highest-ranked model?

Mistral Medium 3.5 currently has the strongest LLMBoard score from this vendor.

How many Mistral AI models are tracked?

The catalog contains 22 independently selectable Mistral AI models and 44 versions.

Does Mistral AI host every listed model API?

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

Does Mistral AI publish open-weight models?

8 current default versions are marked as open weight.