NOUMENOpen app
NOUMEN

Mistral · Open weights

Mistral Code Agent Latest

Added Jun 2, 2026Open weights

Compare models

Choose up to 3 models to compare.1 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 468 models

Side by side

Mistral Code Agent Latest compared

Specifications, prices, speed and benchmark scores next to each other. Benchmarks below show every compared model too.

Compare models

Choose up to 3 models to compare.1 of 3 chosen

Loading models…

Mistral Code Agent LatestMistralThis modelLFM2.5 2.6BliquidRemove
ProviderMistralliquid
Discovery tierOpen weightsOpen weights
AddedJun 2, 2026Aug 12, 2026
Limits
Context window262.14KBest128K
Max output32.77K32.77K
Average output316 tokens459 tokens
Pricing, USD per 1M tokens
Input$0.40$0.10Best
Output$2.00$0.20Best
Performance
Request success (24h)100.0%100.0%
Benchmark indexes
Intelligence Index8.6Best8.4
Coding Index31.3Best7.7
Math Index36.7—
Capabilities
ReasoningNoYes
ToolsYesYes
Structured outputYesYes
Reasoning effort—minimal, low, medium, high, xhigh

Public evaluations

Benchmarks

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

  • Mistral Code Agent Latest
  • LFM2.5 2.6B

Intelligence Index

  • Mistral Code Agent Latest8.6
  • LFM2.5 2.6B8.4

Mistral Code Agent Latest: Better than 15% of 326 scored models

3.8Catalog models by score55.1

Indexes

  • Coding Index

    Composite of the coding evaluations

    • Mistral Code Agent Latest: 31.3Top
    • LFM2.5 2.6B: 7.7

  • Math Index

    Composite of the math evaluations

    • Mistral Code Agent Latest: 36.7
    • LFM2.5 2.6B: —

Agentic work

  • AutomationBench-AA

    Workflow automation, penalized for guardrail violations

    • Mistral Code Agent Latest: 3.1%
    • LFM2.5 2.6B: —

  • AutomationBench-AA tasks completed

    Workflows finished end to end without a guardrail violation

    • Mistral Code Agent Latest: 0.0%
    • LFM2.5 2.6B: —

  • AA-Briefcasev1.1

    Agentic knowledge work, rated head to head

    • Mistral Code Agent Latest: 482 Elo
    • LFM2.5 2.6B: —

  • GDPval-AAv2.1

    Economically valuable occupational tasks, rated head to head

    • Mistral Code Agent Latest: 544 Elo
    • LFM2.5 2.6B: —

Document reasoning

  • GDP.pdf

    Professional reasoning over PDF documents, all-pass rate

    • Mistral Code Agent Latest: 2.4%
    • LFM2.5 2.6B: —

  • AA-LCRv1.1

    Reasoning across long documents

    • Mistral Code Agent Latest: 32.3%Top
    • LFM2.5 2.6B: 5.7%

Reasoning and knowledge

  • Humanity’s Last Exam

    Expert-level questions across academic fields

    • Mistral Code Agent Latest: 3.6%
    • LFM2.5 2.6B: 6.2%Top

  • GPQA Diamond

    Graduate-level science questions

    • Mistral Code Agent Latest: 59.4%Top
    • LFM2.5 2.6B: 55.8%

  • MMLU-Pro

    Multi-subject knowledge and reasoning

    • Mistral Code Agent Latest: 76.2%
    • LFM2.5 2.6B: —

  • IFBench

    Following precise output instructions

    • Mistral Code Agent Latest: 38.1%
    • LFM2.5 2.6B: —

Coding

  • Terminal-Benchv4.0

    Practical software engineering in a terminal

    • Mistral Code Agent Latest: 0.0%
    • LFM2.5 2.6B: —

  • SciCode

    Scientific computing in Python

    • Mistral Code Agent Latest: 32.8%Top
    • LFM2.5 2.6B: 14.4%

  • LiveCodeBench

    Recent competitive programming problems

    • Mistral Code Agent Latest: 44.8%
    • LFM2.5 2.6B: —

Math

  • AIME 2025

    Competition mathematics, 2025 problems

    • Mistral Code Agent Latest: 36.7%
    • LFM2.5 2.6B: —

Legacy evaluations

  • Terminal-Bench Hard

    Earlier terminal task suite

    • Mistral Code Agent Latest: 18.9%
    • LFM2.5 2.6B: —

  • τ²-Bench Telecom

    Tool use in a customer-support simulation

    • Mistral Code Agent Latest: 24.9%
    • LFM2.5 2.6B: —

  • AA-LCR (unversioned)

    Long-context reasoning, earlier grading

    • Mistral Code Agent Latest: 32.3%Top
    • LFM2.5 2.6B: 5.7%

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.

Request success (24h)
100.0%
Reliable
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.