NOUMENOpen app
NOUMEN

Mistral · Open weights

Devstral 2 123B

Added Dec 9, 2025Open weights

Compare models

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

Loading models…

Use in the app

Devstral 2 123B is a 123 billion parameter model from Mistral AI optimized for coding and development tasks. Features advanced reasoning capabilities for software engineering workflows.

Input
Text
Output
Text
Discovery tier
Open weights

Pricing

USD per 1M tokens
Input
$0.40
Output
$1.40

Reference prices as published by the model provider. API example

Specifications

Context window
262.1K
Max output
65.5K
Average output (7 days)
120 tokens
Longer than 11% of 468 models

Side by side

Devstral 2 123B 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…

Devstral 2 123BMistralThis modelMistral Small 3 24B (2501)MistralRemove
ProviderMistralMistral
Discovery tierOpen weightsOpen weights
AddedDec 9, 2025Sep 10, 2026
Limits
Context window262.14KBest32.77K
Max output65.54KBest8.19K
Average output120 tokens403 tokens
Pricing, USD per 1M tokens
Input$0.40$0.12Best
Output$1.40$0.35Best
Performance
Request success (24h)99.7%—
Benchmark indexes
Intelligence Index8.6Best6.7
Coding Index31.3—
Math Index36.7Best4.3
Capabilities
ToolsNoYes
Reasoning effort——

Public evaluations

Benchmarks

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

  • Devstral 2 123B
  • Mistral Small 3 24B (2501)

Intelligence Index

  • Devstral 2 123B8.6
  • Mistral Small 3 24B (2501)6.7

Devstral 2 123B: Better than 15% of 326 scored models

3.8Catalog models by score55.1

Indexes

  • Coding Index

    Composite of the coding evaluations

    • Devstral 2 123B: 31.3
    • Mistral Small 3 24B (2501): —

  • Math Index

    Composite of the math evaluations

    • Devstral 2 123B: 36.7Top
    • Mistral Small 3 24B (2501): 4.3

Agentic work

  • AutomationBench-AA

    Workflow automation, penalized for guardrail violations

    • Devstral 2 123B: 3.1%
    • Mistral Small 3 24B (2501): —

  • AutomationBench-AA tasks completed

    Workflows finished end to end without a guardrail violation

    • Devstral 2 123B: 0.0%
    • Mistral Small 3 24B (2501): —

  • AA-Briefcasev1.1

    Agentic knowledge work, rated head to head

    • Devstral 2 123B: 482 Elo
    • Mistral Small 3 24B (2501): —

  • GDPval-AAv2.1

    Economically valuable occupational tasks, rated head to head

    • Devstral 2 123B: 544 Elo
    • Mistral Small 3 24B (2501): —

Document reasoning

  • GDP.pdf

    Professional reasoning over PDF documents, all-pass rate

    • Devstral 2 123B: 2.4%
    • Mistral Small 3 24B (2501): —

  • AA-LCRv1.1

    Reasoning across long documents

    • Devstral 2 123B: 32.3%Top
    • Mistral Small 3 24B (2501): 0.0%

Reasoning and knowledge

  • Humanity’s Last Exam

    Expert-level questions across academic fields

    • Devstral 2 123B: 3.6%
    • Mistral Small 3 24B (2501): 3.8%Top

  • GPQA Diamond

    Graduate-level science questions

    • Devstral 2 123B: 59.4%Top
    • Mistral Small 3 24B (2501): 46.2%

  • MMLU-Pro

    Multi-subject knowledge and reasoning

    • Devstral 2 123B: 76.2%Top
    • Mistral Small 3 24B (2501): 65.2%

  • IFBench

    Following precise output instructions

    • Devstral 2 123B: 38.1%Top
    • Mistral Small 3 24B (2501): 26.4%

Coding

  • Terminal-Benchv4.0

    Practical software engineering in a terminal

    • Devstral 2 123B: 0.0%
    • Mistral Small 3 24B (2501): —

  • SciCode

    Scientific computing in Python

    • Devstral 2 123B: 32.8%
    • Mistral Small 3 24B (2501): —

  • LiveCodeBench

    Recent competitive programming problems

    • Devstral 2 123B: 44.8%Top
    • Mistral Small 3 24B (2501): 25.2%

Math

  • AIME 2025

    Competition mathematics, 2025 problems

    • Devstral 2 123B: 36.7%Top
    • Mistral Small 3 24B (2501): 4.3%

  • AIME

    Competition mathematics

    • Devstral 2 123B: —
    • Mistral Small 3 24B (2501): 8.0%

  • MATH-500

    Competition math problems

    • Devstral 2 123B: —
    • Mistral Small 3 24B (2501): 71.5%

Legacy evaluations

  • Terminal-Bench Hard

    Earlier terminal task suite

    • Devstral 2 123B: 18.9%
    • Mistral Small 3 24B (2501): —

  • τ²-Bench Telecom

    Tool use in a customer-support simulation

    • Devstral 2 123B: 24.9%Top
    • Mistral Small 3 24B (2501): 19.6%

  • AA-LCR (unversioned)

    Long-context reasoning, earlier grading

    • Devstral 2 123B: 32.3%Top
    • Mistral Small 3 24B (2501): 0.0%

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)
99.7%
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 20.0%
  • 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": "mistralai/devstral-2-123b-instruct-2512",
    "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="mistralai/devstral-2-123b-instruct-2512",
    messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)

Mistral

Other Mistral models, starting with the same family.