NOUMENOpen app
NOUMEN

Mistral · Open weights

Mistral Code Agent Latest

Added Jun 2, 2026Open weights

Compare models

Choose up to 3 models to compare.0 of 3 chosen

Loading models…

Use in the app

Mistral Code Agent Latest is Mistral's direct API alias for devstral-2512, an agentic coding model built for autonomous software engineering, tool use, and long-running code tasks.

  • Tools
  • Structured output
Input
Text
Output
Text
Discovery tier
Open weights

Pricing

USD per 1M tokens
Input
$0.40
Output
$2.00

Reference prices as published by the model provider. API example

Specifications

Context window
262.1K
Max output
32.8K
Average output (7 days)
316 tokens
Longer than 34% of 465 models

Side by side

Compare models

Put Mistral Code Agent Latest next to up to three other models. The comparison stays in the link, so you can share it.

Compare models

Choose up to 3 models to compare.0 of 3 chosen

Loading models…

TryGemini 2.0 Pro 0205Amazon Nova 2 LiteLFM2.5 2.6BAll 3

Public evaluations

Benchmarks

Independent evaluation results, with how each score ranks among the models in the Noumen catalog.

Intelligence Index

8.6

Better than 15% of 326 scored models

3.8Catalog models by score55.1

Indexes

  • Coding Index

    31.3

    Composite of the coding evaluations

    Better than 23% of 168 scored models

  • Math Index

    36.7

    Composite of the math evaluations

    Better than 35% of 118 scored models

Agentic work

  • AutomationBench-AA

    3.1%

    Workflow automation, penalized for guardrail violations

    Better than 19% of 173 scored models

  • AutomationBench-AA tasks completed

    0.0%

    Workflows finished end to end without a guardrail violation

    Better than 0% of 173 scored models

  • AA-Briefcasev1.1

    482 Elo

    Agentic knowledge work, rated head to head

    Better than 19% of 166 scored models

  • GDPval-AAv2.1

    544 Elo

    Economically valuable occupational tasks, rated head to head

    Better than 13% of 187 scored models

Document reasoning

  • GDP.pdf

    2.4%

    Professional reasoning over PDF documents, all-pass rate

    Better than 9% of 171 scored models

  • AA-LCRv1.1

    32.3%

    Reasoning across long documents

    Better than 14% of 309 scored models

Reasoning and knowledge

  • Humanity’s Last Exam

    3.6%

    Expert-level questions across academic fields

    Better than 2% of 323 scored models

  • GPQA Diamond

    59.4%

    Graduate-level science questions

    Better than 17% of 291 scored models

  • MMLU-Pro

    76.2%

    Multi-subject knowledge and reasoning

    Better than 37% of 132 scored models

  • IFBench

    38.1%

    Following precise output instructions

    Better than 21% of 215 scored models

Coding

  • Terminal-Benchv4.0

    0.0%

    Practical software engineering in a terminal

    Better than 0% of 171 scored models

  • SciCode

    32.8%

    Scientific computing in Python

    Better than 9% of 174 scored models

  • LiveCodeBench

    44.8%

    Recent competitive programming problems

    Better than 37% of 129 scored models

Math

  • AIME 2025

    36.7%

    Competition mathematics, 2025 problems

    Better than 35% of 118 scored models

Legacy evaluations

  • Terminal-Bench Hard

    18.9%

    Earlier terminal task suite

    Better than 37% of 212 scored models

  • τ²-Bench Telecom

    24.9%

    Tool use in a customer-support simulation

    Better than 13% of 214 scored models

  • AA-LCR (unversioned)

    32.3%

    Long-context reasoning, earlier grading

    Better than 14% of 309 scored models

Scores from Artificial Analysis, updated Oct 26, 2026. Artificial Analysis

Live routing data

Performance and reliability

Recent averages across requests routed for this model. Your own speed depends on prompt length, reasoning effort and load.

Prompt cache hits
0.0%
Request success (24h)
100.0%
Reliable

Cache hits are the share of input tokens recently served from a prompt cache across all requests. They are not a forecast of your own hit rate.

Hourly request success · last 72 hoursLowest hour 93.3%
  • Healthy (98% or more)
  • Degraded (90–98%)
  • Down (under 90%)
  • No requests

Developers

Use it through the API

Noumen’s API is OpenAI-compatible: any Chat Completions client works with a base URL and a key.

Read the quickstart
curl https://www.noumen.xyz/api/v1/chat/completions \
  -H "Authorization: Bearer $NOUMEN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "mistral-code-agent-latest",
    "messages": [{ "role": "user", "content": "Explain this stack trace." }]
  }'
import os
from openai import OpenAI

client = OpenAI(base_url="https://www.noumen.xyz/api/v1", api_key=os.environ["NOUMEN_API_KEY"])
reply = client.chat.completions.create(
    model="mistral-code-agent-latest",
    messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)

Mistral

Other Mistral models, starting with the same family.