llmboard.aiAI model intelligence
Home

Model Rankings

OverallOpen ModelsAgentCodingReasoningMathKnowledgeInstruction FollowingTextVision
Image GenerationImage Editing
Video GenerationImage to VideoVideo Editing
Text to SpeechSpeech to Text
Embeddings

Efficiency

Chat Token PricingImage PricingVideo PricingAudio Pricing
Chat Speed & LatencyProvider Reliability

Benchmarks

GPQAMMLU-ProAIME 2025SWE-Bench VerifiedMMLUHumanity's Last ExamLiveCodeBenchMATHHumanEvalMMMU-Pro
All Benchmarks

Tools

Model Directory

Scoring & Data

Scoring & Data
1224 models729 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 Benchmarks
llmboard.aiCopyright 2026 llmboard.ai

Mistral AI model product

Devstral Medium

6% on SWE-Bench Verified.

Updated Sep 8, 2026. Default version: Devstral Medium

LLMBoard Score23.3Devstral Medium
Coverage0%1 benchmark families
Context window128KTokens
Official input price$0.40Mistral API

On this page

  • Capability
  • Benchmarks
  • Arena
  • Pricing
  • Runtime
  • Specification
  • Versions
  • Similar models
  • About
  • FAQ

Devstral Medium Capability Profile

This profile uses the model's current scored version. Arena ratings and prices are shown separately.

Devstral Medium LLMBoard score breakdown

Devstral Medium Benchmark Results

Benchmark scores for Devstral Medium.

2 rows
Columns

Show columns

Sort by
Benchmark
Score
Rank
Participants
Percentile
Evidence
Evaluated
BenchmarkSWE-Bench VerifiedScore61.60%Rank82Participants113Percentile27.68%EvidenceCEvaluatedSep 8, 2026
BenchmarkLM Arena WebdevScore1,080.94 ratingRank97Participants97Percentile0.00%EvidenceAEvaluatedSep 5, 2026

Devstral Medium Arena Results

Preference and agent-evaluation results for the default version.

3 rows
Columns

Show columns

Sort by
Arena
Category
Rank
Rating / score
Votes
Observations
Result date
ArenawebdevCategorywebdev-htmlRank96Rating / score1,087.83Votes831ObservationsN/AResult dateSep 5, 2026
ArenawebdevCategoryoverallRank97Rating / score1,080.94Votes831ObservationsN/AResult dateSep 5, 2026
ArenawebdevCategorywebdevRank97Rating / score1,080.94Votes831ObservationsN/AResult dateSep 5, 2026

Devstral Medium Pricing

Official vendor API pricing appears first, followed by individual provider offers.

Official API
$0.40 input, $2 output per 1M
Official provider
Mistral
Lowest third-party
From $0.40 input, $2 output per 1M via Merge Gateway
Tracked offerings
2
2 rows
Columns

Show columns

Sort by
Provider
Provider model ID
Region
Input / 1M
Output / 1M
Context
Updated
ProviderMerge GatewayProvider model IDmistral/devstral-medium-2507RegionglobalInput / 1M$0.40Output / 1M$2Context128KUpdatedSep 8, 2026
ProviderMistralProvider model IDdevstral-medium-2507RegionglobalInput / 1M$0.40Output / 1M$2Context128KUpdatedSep 8, 2026

Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.

Devstral Medium Runtime Performance

Provider-specific output speed and catalog latency for Devstral Medium. Runtime does not affect the capability score.

1 row
Columns

Show columns

Sort by
Provider
Output Speed
Catalog Latency
Max Input
Max Output
Updated
ProviderMistral AIOutput Speed137.10 tok/sCatalog Latency0.23 sMax Input128KMax Output128KUpdatedSep 8, 2026

Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.

Devstral Medium Specifications

Technical details for the model's default version.

Version
Devstral Medium
Released
Jul 10, 2025
Knowledge cutoff
Unknown
Parameters
N/A
Context window
128K
Max output
128K
Inputs
text
Outputs
text
Open weights
No
License
Proprietary

Devstral Medium Versions

Available versions of this model. The score column identifies the version used in the overall ranking.

1 row
Columns

Show columns

Sort by
Version
Released
LLMBoard
Parameters
Context
Max output
Open weights
License
VersionDevstral MediumReleasedJul 10, 2025LLMBoard23.28ParametersN/AContext128KMax output128KOpen weightsNoLicenseProprietary

Models similar to Devstral Medium

Recommendations prioritize the same model type and family, then the closest LLMBoard score.

#213-3.25
MA

Pixtral Large

Mistral AI

20.03 LLMBoard

Details
#215-3.93
MA

Min istral 3

Mistral AI

19.35 LLMBoard

Details
#217-4.56
MA

Magistral Small

Mistral AI

18.72 LLMBoard

Details
#188+4.59
MA

Ministral 3

Mistral AI

27.87 LLMBoard

Details
#219-5.32
MA

Magistral Medium

Mistral AI

17.96 LLMBoard

Details
#222-7.17
MA

Devstral Small 1.1

Mistral AI

16.11 LLMBoard

Details

What is Devstral Medium?

Key information about Devstral Medium and its available data.

Devstral Medium is an LLM from Mistral AI that builds upon Devstral Small. It is available through the Mistral public API.

Data as of 2026-09-08.

FAQ

Common questions about Devstral Medium.

When was Devstral Medium released?

Devstral Medium's default version was released on Jul 10, 2025.

How much does Devstral Medium cost?

Devstral Medium's official API price is $0.40 per million input tokens and $2 per million output tokens via Mistral. The lowest tracked third-party offer starts at $0.40 input and $2 output via Merge Gateway.

Who created Devstral Medium?

Devstral Medium was created by Mistral AI.

What is the context window for Devstral Medium?

The default version has a 128K token context window.

Is Devstral Medium open weight?

No. The default version is not marked as having publicly available weights.

How many API providers offer Devstral Medium?

2 provider offerings are linked to the default version.