NOUMENOpen app
NOUMEN

Mistral · Open weights

Mistral Medium 3.5

Added Apr 29, 2026Open weights

Compare models

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

Loading models…

Use in the app

Mistral Medium 3.5 is a 128B dense open-weights flagship model for instruction-following, reasoning, coding, long-horizon agentic work, tool use, structured output, and multimodal prompts. It supports a 256k context window and configurable reasoning effort.

  • Reasoning
  • Tools
  • Vision
  • Structured output
Input
Text, Images
Output
Text
Reasoning effort
none · high
Discovery tier
Open weights

Pricing

USD per 1M tokens
Input
$1.50
Output
$7.50

Reference prices as published by the model provider. API example

Specifications

Context window
256K
Max output
32.8K

Side by side

Mistral Medium 3.5 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 Medium 3.5MistralThis modelKimi K2.6 TEEMoonshotRemove
ProviderMistralMoonshot
Discovery tierOpen weightsOpen weights
AddedApr 29, 2026Apr 21, 2026
Limits
Context window256K262.14KBest
Max output32.77K65.54KBest
Average output—3.1K tokens
Pricing, USD per 1M tokens
Input$1.50$1.50
Output$7.50$5.25Best
Cache read—$0.38
Performance
Request success (24h)100.0%100.0%
Benchmark indexes
Intelligence Index—27.0
Coding Index—61.8
Capabilities
ReasoningYesNo
ToolsYesYes
VisionYesYes
Structured outputYesNo
Reasoning effortnone, high—

Public evaluations

Benchmarks

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

  • Mistral Medium 3.5
  • Kimi K2.6 TEE

Intelligence Index

  • Mistral Medium 3.5—
  • Kimi K2.6 TEE27.0
3.8Catalog models by score55.1

Indexes

  • Coding Index

    Composite of the coding evaluations

    • Mistral Medium 3.5: —
    • Kimi K2.6 TEE: 61.8

Agentic work

  • AutomationBench-AA

    Workflow automation, penalized for guardrail violations

    • Mistral Medium 3.5: —
    • Kimi K2.6 TEE: 13.0%

  • AutomationBench-AA tasks completed

    Workflows finished end to end without a guardrail violation

    • Mistral Medium 3.5: —
    • Kimi K2.6 TEE: 1.8%

  • AA-Briefcasev1.1

    Agentic knowledge work, rated head to head

    • Mistral Medium 3.5: —
    • Kimi K2.6 TEE: 819 Elo

  • GDPval-AAv2.1

    Economically valuable occupational tasks, rated head to head

    • Mistral Medium 3.5: —
    • Kimi K2.6 TEE: 1,038 Elo

Document reasoning

  • GDP.pdf

    Professional reasoning over PDF documents, all-pass rate

    • Mistral Medium 3.5: —
    • Kimi K2.6 TEE: 13.0%

  • AA-LCRv1.1

    Reasoning across long documents

    • Mistral Medium 3.5: —
    • Kimi K2.6 TEE: 81.0%

  • MLCR-AA

    Long-context reasoning over medical records

    • Mistral Medium 3.5: —
    • Kimi K2.6 TEE: 11.1%

Reasoning and knowledge

  • Humanity’s Last Exam

    Expert-level questions across academic fields

    • Mistral Medium 3.5: —
    • Kimi K2.6 TEE: 37.5%

  • GPQA Diamond

    Graduate-level science questions

    • Mistral Medium 3.5: —
    • Kimi K2.6 TEE: 91.1%

  • IFBench

    Following precise output instructions

    • Mistral Medium 3.5: —
    • Kimi K2.6 TEE: 76.0%

Coding

  • Terminal-Benchv4.0

    Practical software engineering in a terminal

    • Mistral Medium 3.5: —
    • Kimi K2.6 TEE: 0.5%

  • SciCode

    Scientific computing in Python

    • Mistral Medium 3.5: —
    • Kimi K2.6 TEE: 51.5%

Legacy evaluations

  • Terminal-Bench Hard

    Earlier terminal task suite

    • Mistral Medium 3.5: —
    • Kimi K2.6 TEE: 43.9%

  • τ²-Bench Telecom

    Tool use in a customer-support simulation

    • Mistral Medium 3.5: —
    • Kimi K2.6 TEE: 95.9%

  • AA-LCR (unversioned)

    Long-context reasoning, earlier grading

    • Mistral Medium 3.5: —
    • Kimi K2.6 TEE: 81.0%

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.

Request success (24h)
100.0%
Reliable
Hourly request success · last 72 hoursLowest hour 100.0%
  • 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/mistral-medium-3.5",
    "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-medium-3.5",
    messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)

Mistral

Other Mistral models, starting with the same family.