Private AI

Nano GPT logo
NanoGPT
Nano GPT logo
NanoGPT
Nano GPT logo
NanoGPT
Search
 
 
 
 
All conversations

Create

Chat
Studio

Explore

Models
Pricing
AI Apps
Blog

Library

Gallery
Workspace
Usage & billing
API
Suggestions and bugs
Use cases

|

Terms

|

Privacy

|

Refunds
Usage & billing
Teams
Referrals
Presets
Settings
FAQPress & mediaBrand assetsBenchmarksNano RPCEarn crypto
  1. Models
  2. Text
  3. Mistral

Mistral Medium 3.1

Mistral Medium 3.1 is an updated version of Mistral Medium 3, which is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at significantly reduced operational cost. It balances state-of-the-art reasoning and multimodal performance with 8× lower cost compared to traditional large models, making it suitable for scalable deployments across professional and industrial use cases. The model excels in domains such as coding, STEM reasoning, and enterprise adaptation. It supports hybrid, on-prem, and in-VPC deployments and is optimized for integration into custom workflows. Mistral Medium 3.1 offers competitive accuracy relative to larger models like Claude Sonnet 3.5/3.7, Llama 4 Maverick, and Command R+, while maintaining broad compatibility across deployment environments.

Added Sep 5, 2025

Pricing

Auto routing · per 1M tokens
Input
$0.40
Output
$2.00
Cache read
$0.20
Compare provider prices

Specifications

Context window
131.1K
Max output
32.8K

Benchmarks

Sourced from LMArena.

Arena Score

1408.1

Overall Rank

#159 / 421

Votes

94,752

Confidence Interval

1405.5 - 1410.7

Category Scores

Coding

#157 / 416

21,410 votes

1453.8

Math

#171 / 404

5,936 votes

1395.1

Longer Query

#164 / 399

27,618 votes

1408.4

Creative Writing

#150 / 419

13,927 votes

1378.1

Instruction Following

#162 / 421

27,465 votes

1395.1

Hard Prompts

#156 / 421

52,602 votes

1426.9

Additional Categories
22

French

#129 / 301

2,096 votes

1434.6

German

#133 / 320

1,741 votes

1402.0

Japanese

#135 / 288

1,121 votes

1358.4

Polish

#136 / 243

3,322 votes

1400.6

Industry Medicine And Healthcare

#143 / 391

5,957 votes

1433.4

Korean

#143 / 289

1,995 votes

1351.0

English

#148 / 421

40,583 votes

1425.1

Russian

#148 / 385

9,681 votes

1404.1

Hard Prompts English

#151 / 419

23,014 votes

1438.2

Industry Legal And Government

#151 / 393

6,654 votes

1416.9

Spanish

#151 / 304

2,848 votes

1401.6

Industry Writing And Literature And Language

#152 / 420

21,793 votes

1386.5

Industry Entertainment And Sports And Media

#155 / 419

17,911 votes

1374.0

Industry Business And Management And Financial Operations

#157 / 414

17,781 votes

1406.9

Industry Life And Physical And Social Science

#157 / 419

15,180 votes

1424.7

Exclude Ties

#158 / 421

68,086 votes

1393.3

Multi Turn

#159 / 419

16,321 votes

1407.0

Industry Software And It Services

#160 / 421

33,700 votes

1439.3

Non English

#164 / 421

54,144 votes

1388.8

Chinese

#170 / 395

7,097 votes

1426.0

Expert

#172 / 371

6,523 votes

1410.9

Industry Mathematical

#174 / 402

5,044 votes

1400.5

Published 2026-11-11 · Matched as Mistral Medium 3.1 (2508) · CC BY 4.0

LMArena Dataset

Leaderboard results

BenchmarkScoreRank on NanoGPT
EQ-Bench

EQ-Bench data, MIT · Updated Nov 17, 2026

Creative Writing v3

1476

#60 of 96

Longform Writing

46.2

#75 of 97

UGI Leaderboard

UGI Leaderboard data, Apache-2.0 · Updated Oct 16, 2026

UGI Score

48.6

#45 of 149

UGI Willingness

5.8

#33 of 149

UGI Writing

39.5

#93 of 149

Filtered and ranked to models on NanoGPT.

Providers

Auto routing is available for this model. Explicit provider selection is not available.

Auto
Auto
Recommended
$0.40$2.00$0.20N/AN/A

Reliability

Related text models

Compare Mistral Medium 3.1 with similar models from the same provider or model family.

Mistral Medium 3

mistralai/mistral-medium-3

Mistral Medium 3 delivers frontier performance while being an order of magnitude less expensive. For instance, the model performs at or above 90% of Claude Sonnet 3.7 on benchmarks across the board at a significantly lower cost. On performance, Mistral Medium 3 also surpasses leading open models such as Llama 4 Maverick and enterprise models such as Cohere Command A. On pricing, the model beats cost leaders such as DeepSeek v3, both in API and self-deployed systems.

Mistral Small 3 24B (2501)

mistralai/mistral-small-24b-instruct-2501

Mistral Small 3 24B (2501) hosted by IONOS in Berlin, Germany. Zero data retention.

Mistral Small 4 119B Thinking

mistralai/mistral-small-4-119b-2603:thinking

Mistral Small 4 with reasoning enabled (reasoning_effort=high). A hybrid MoE model with deep step-by-step reasoning for complex prompts, coding, and multi-step problem solving.

Mistral Small 4 119B

mistralai/mistral-small-4-119b-2603

Mistral Small 4 is a hybrid MoE model that unifies instruct, reasoning, and coding behavior in a single multimodal model. It supports text and image input, native function calling, JSON output, and per-request reasoning effort controls.

Mistral Devstral Small 2505

mistralai/devstral-small-2505

OpenHands+Devstral is 100% local 100% open, and is SOTA for the category on SWE-Bench Verified: 46.8% accuracy.

Mistral Large 2411

mistralai/mistral-large

Upgrade to Mistral's flagship model. It is fluent in English, French, Spanish, German, and Italian, with high grammatical accuracy, with a long context window.