NOUMENOpen app
NOUMEN

Mistral · Open weights

Mistral Small 4 119B

Added Mar 16, 2026Open weights

Compare models

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

Loading models…

Use in the app

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.

  • Reasoning
  • Tools
  • Vision
  • Structured output
Input
Text, Images
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
16.4K
Average output (7 days)
92 tokens
Longer than 9% of 468 models

Side by side

Mistral Small 4 119B 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 119BMistralThis modelQwen3 Coder NextQwenRemove
ProviderMistralQwen
Discovery tierOpen weightsOpen weights
AddedMar 16, 2026Dec 8, 2025
Limits
Context window262.14K262.14K
Max output16.38K65.54KBest
Average output92 tokens182 tokens
Pricing, USD per 1M tokens
Input$0.40$0.25Best
Output$1.40$0.80Best
Cache read—$0.0798
Performance
Throughput128.8 tok/sBest119.9 tok/s
Time to first token0.7 sBest1.6 s
Request success (24h)99.6%Best92.3%
Benchmark indexes
Intelligence Index9.09.2Best
Coding Index—36.2
Capabilities
ReasoningYesNo
ToolsYesYes
VisionYesNo
Structured outputYesYes
Reasoning effort——

Public evaluations

Benchmarks

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

  • Mistral Small 4 119B
  • Qwen3 Coder Next

Intelligence Index

  • Mistral Small 4 119B9.0
  • Qwen3 Coder Next9.2

Mistral Small 4 119B: Better than 16% of 326 scored models

3.8Catalog models by score55.1

Indexes

  • Coding Index

    Composite of the coding evaluations

    • Mistral Small 4 119B: —
    • Qwen3 Coder Next: 36.2

Agentic work

  • AutomationBench-AA

    Workflow automation, penalized for guardrail violations

    • Mistral Small 4 119B: —
    • Qwen3 Coder Next: 1.1%

  • AutomationBench-AA tasks completed

    Workflows finished end to end without a guardrail violation

    • Mistral Small 4 119B: —
    • Qwen3 Coder Next: 0.0%

  • AA-Briefcasev1.1

    Agentic knowledge work, rated head to head

    • Mistral Small 4 119B: —
    • Qwen3 Coder Next: 404 Elo

  • GDPval-AAv2.1

    Economically valuable occupational tasks, rated head to head

    • Mistral Small 4 119B: —
    • Qwen3 Coder Next: 513 Elo

Document reasoning

  • GDP.pdf

    Professional reasoning over PDF documents, all-pass rate

    • Mistral Small 4 119B: —
    • Qwen3 Coder Next: 2.6%

  • AA-LCRv1.1

    Reasoning across long documents

    • Mistral Small 4 119B: 28.3%
    • Qwen3 Coder Next: 47.0%Top

Reasoning and knowledge

  • Humanity’s Last Exam

    Expert-level questions across academic fields

    • Mistral Small 4 119B: 3.8%
    • Qwen3 Coder Next: 10.1%Top

  • GPQA Diamond

    Graduate-level science questions

    • Mistral Small 4 119B: 57.1%
    • Qwen3 Coder Next: 73.7%Top

  • IFBench

    Following precise output instructions

    • Mistral Small 4 119B: 32.8%
    • Qwen3 Coder Next: 35.2%Top

Coding

  • Terminal-Benchv4.0

    Practical software engineering in a terminal

    • Mistral Small 4 119B: —
    • Qwen3 Coder Next: 0.0%

  • SciCode

    Scientific computing in Python

    • Mistral Small 4 119B: —
    • Qwen3 Coder Next: 36.2%

Legacy evaluations

  • Terminal-Bench Hard

    Earlier terminal task suite

    • Mistral Small 4 119B: 10.6%
    • Qwen3 Coder Next: 18.2%Top

  • τ²-Bench Telecom

    Tool use in a customer-support simulation

    • Mistral Small 4 119B: 18.4%
    • Qwen3 Coder Next: 79.5%Top

  • AA-LCR (unversioned)

    Long-context reasoning, earlier grading

    • Mistral Small 4 119B: 28.3%
    • Qwen3 Coder Next: 47.0%Top

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
128.8 tok/s
Faster than 70% of 254 models
Time to first token
0.7 s
Quicker than 99% of 254 models
Prompt cache hits
16.9%
Request success (24h)
99.6%
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 95.4%
  • 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",
    "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",
    messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)

Mistral

Other Mistral models, starting with the same family.