NOUMENOpen app
NOUMEN

Mistral · Open weights

Mistral Small 4 119B Thinking

Added Mar 17, 2026Open weights

Compare models

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

Loading models…

Use in the app

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.

  • Reasoning
  • Tools
  • Vision
  • Structured output
Input
Text, Images
Output
Text
Reasoning effort
none · high
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
16.4K
Average output (7 days)
997 tokens
Longer than 70% of 465 models

Side by side

Mistral Small 4 119B Thinking 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 Small 4 119B ThinkingMistralThis modelMistral Code Agent LatestMistralRemove
ProviderMistralMistral
Discovery tierOpen weightsOpen weights
AddedMar 17, 2026Jun 2, 2026
Limits
Context window262.14K262.14K
Max output16.38K32.77KBest
Average output997 tokens316 tokens
Pricing, USD per 1M tokens
Input$0.40$0.40
Output$1.40Best$2.00
Performance
Throughput123.6 tok/s—
Time to first token1.7 s—
Request success (24h)95.9%100.0%Best
Benchmark indexes
Intelligence Index11.3Best8.6
Coding Index26.631.3Best
Math Index—36.7
Capabilities
ReasoningYesNo
ToolsYesYes
VisionYesNo
Structured outputYesYes
Reasoning effortnone, high—

Public evaluations

Benchmarks

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

  • Mistral Small 4 119B Thinking
  • Mistral Code Agent Latest

Intelligence Index

  • Mistral Small 4 119B Thinking11.3
  • Mistral Code Agent Latest8.6

Mistral Small 4 119B Thinking: Better than 25% of 326 scored models

3.8Catalog models by score55.1

Indexes

  • Coding Index

    Composite of the coding evaluations

    • Mistral Small 4 119B Thinking: 26.6
    • Mistral Code Agent Latest: 31.3Top

  • Math Index

    Composite of the math evaluations

    • Mistral Small 4 119B Thinking: —
    • Mistral Code Agent Latest: 36.7

Agentic work

  • AutomationBench-AA

    Workflow automation, penalized for guardrail violations

    • Mistral Small 4 119B Thinking: 1.0%
    • Mistral Code Agent Latest: 3.1%Top

  • AutomationBench-AA tasks completed

    Workflows finished end to end without a guardrail violation

    • Mistral Small 4 119B Thinking: 0.0%Top
    • Mistral Code Agent Latest: 0.0%Top

  • AA-Briefcasev1.1

    Agentic knowledge work, rated head to head

    • Mistral Small 4 119B Thinking: 241 Elo
    • Mistral Code Agent Latest: 482 EloTop

  • GDPval-AAv2.1

    Economically valuable occupational tasks, rated head to head

    • Mistral Small 4 119B Thinking: 362 Elo
    • Mistral Code Agent Latest: 544 EloTop

Document reasoning

  • GDP.pdf

    Professional reasoning over PDF documents, all-pass rate

    • Mistral Small 4 119B Thinking: 0.0%
    • Mistral Code Agent Latest: 2.4%Top

  • AA-LCRv1.1

    Reasoning across long documents

    • Mistral Small 4 119B Thinking: 49.7%Top
    • Mistral Code Agent Latest: 32.3%

  • MLCR-AA

    Long-context reasoning over medical records

    • Mistral Small 4 119B Thinking: 1.7%
    • Mistral Code Agent Latest: —

Reasoning and knowledge

  • Humanity’s Last Exam

    Expert-level questions across academic fields

    • Mistral Small 4 119B Thinking: 9.9%Top
    • Mistral Code Agent Latest: 3.6%

  • GPQA Diamond

    Graduate-level science questions

    • Mistral Small 4 119B Thinking: 76.9%Top
    • Mistral Code Agent Latest: 59.4%

  • MMLU-Pro

    Multi-subject knowledge and reasoning

    • Mistral Small 4 119B Thinking: —
    • Mistral Code Agent Latest: 76.2%

  • IFBench

    Following precise output instructions

    • Mistral Small 4 119B Thinking: 48.2%Top
    • Mistral Code Agent Latest: 38.1%

Coding

  • Terminal-Benchv4.0

    Practical software engineering in a terminal

    • Mistral Small 4 119B Thinking: 0.0%Top
    • Mistral Code Agent Latest: 0.0%Top

  • SciCode

    Scientific computing in Python

    • Mistral Small 4 119B Thinking: 38.8%Top
    • Mistral Code Agent Latest: 32.8%

  • LiveCodeBench

    Recent competitive programming problems

    • Mistral Small 4 119B Thinking: —
    • Mistral Code Agent Latest: 44.8%

Math

  • AIME 2025

    Competition mathematics, 2025 problems

    • Mistral Small 4 119B Thinking: —
    • Mistral Code Agent Latest: 36.7%

Legacy evaluations

  • Terminal-Bench Hard

    Earlier terminal task suite

    • Mistral Small 4 119B Thinking: 17.4%
    • Mistral Code Agent Latest: 18.9%Top

  • τ²-Bench Telecom

    Tool use in a customer-support simulation

    • Mistral Small 4 119B Thinking: 41.2%Top
    • Mistral Code Agent Latest: 24.9%

  • AA-LCR (unversioned)

    Long-context reasoning, earlier grading

    • Mistral Small 4 119B Thinking: 49.7%Top
    • Mistral Code Agent Latest: 32.3%

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.

Throughput
123.6 tok/s
Faster than 70% of 251 models
Time to first token
1.7 s
Quicker than 83% of 251 models
Prompt cache hits
37.5%
Request success (24h)
95.0%
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 66.6%
  • 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/mistral-small-4-119b-2603:thinking",
    "reasoning_effort": "none",
    "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/mistral-small-4-119b-2603:thinking",
    messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)

Mistral

Other Mistral models, starting with the same family.