NOUMENOpen app
NOUMEN

Mistral · Open weights

The Drummer Cydonia 24B v4.3

Added Dec 25, 2025Open weights

Compare models

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

Loading models…

Use in the app

Cydonia 24B v4.3 continues TheDrummer's Cydonia series with updated tuning on Mistral Small and a 128K context window.

Input
Text
Output
Text
Discovery tier
Open weights

Pricing

USD per 1M tokens
Input
$0.12
Output
$0.15

Reference prices as published by the model provider. API example

Specifications

Context window
131.1K
Max output
—
Average output (7 days)
231 tokens
Longer than 25% of 465 models

Side by side

The Drummer Cydonia 24B v4.3 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…

The Drummer Cydonia 24B v4.3MistralThis modelMistral Code Agent LatestMistralRemove
ProviderMistralMistral
Discovery tierOpen weightsOpen weights
AddedDec 25, 2025Jun 2, 2026
Limits
Context window131.07K262.14KBest
Max output—32.77K
Average output231 tokens316 tokens
Pricing, USD per 1M tokens
Input$0.12Best$0.40
Output$0.15Best$2.00
Performance
Throughput26.5 tok/s—
Time to first token2.1 s—
Request success (24h)63.9%100.0%Best
Benchmark indexes
Intelligence Index—8.6
Coding Index—31.3
Math Index—36.7
Capabilities
ToolsNoYes
Structured outputNoYes
Reasoning effort——

Public evaluations

Benchmarks

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

  • The Drummer Cydonia 24B v4.3
  • Mistral Code Agent Latest

Intelligence Index

  • The Drummer Cydonia 24B v4.3—
  • Mistral Code Agent Latest8.6
3.8Catalog models by score55.1

Indexes

  • Coding Index

    Composite of the coding evaluations

    • The Drummer Cydonia 24B v4.3: —
    • Mistral Code Agent Latest: 31.3

  • Math Index

    Composite of the math evaluations

    • The Drummer Cydonia 24B v4.3: —
    • Mistral Code Agent Latest: 36.7

Agentic work

  • AutomationBench-AA

    Workflow automation, penalized for guardrail violations

    • The Drummer Cydonia 24B v4.3: —
    • Mistral Code Agent Latest: 3.1%

  • AutomationBench-AA tasks completed

    Workflows finished end to end without a guardrail violation

    • The Drummer Cydonia 24B v4.3: —
    • Mistral Code Agent Latest: 0.0%

  • AA-Briefcasev1.1

    Agentic knowledge work, rated head to head

    • The Drummer Cydonia 24B v4.3: —
    • Mistral Code Agent Latest: 482 Elo

  • GDPval-AAv2.1

    Economically valuable occupational tasks, rated head to head

    • The Drummer Cydonia 24B v4.3: —
    • Mistral Code Agent Latest: 544 Elo

Document reasoning

  • GDP.pdf

    Professional reasoning over PDF documents, all-pass rate

    • The Drummer Cydonia 24B v4.3: —
    • Mistral Code Agent Latest: 2.4%

  • AA-LCRv1.1

    Reasoning across long documents

    • The Drummer Cydonia 24B v4.3: —
    • Mistral Code Agent Latest: 32.3%

Reasoning and knowledge

  • Humanity’s Last Exam

    Expert-level questions across academic fields

    • The Drummer Cydonia 24B v4.3: —
    • Mistral Code Agent Latest: 3.6%

  • GPQA Diamond

    Graduate-level science questions

    • The Drummer Cydonia 24B v4.3: —
    • Mistral Code Agent Latest: 59.4%

  • MMLU-Pro

    Multi-subject knowledge and reasoning

    • The Drummer Cydonia 24B v4.3: —
    • Mistral Code Agent Latest: 76.2%

  • IFBench

    Following precise output instructions

    • The Drummer Cydonia 24B v4.3: —
    • Mistral Code Agent Latest: 38.1%

Coding

  • Terminal-Benchv4.0

    Practical software engineering in a terminal

    • The Drummer Cydonia 24B v4.3: —
    • Mistral Code Agent Latest: 0.0%

  • SciCode

    Scientific computing in Python

    • The Drummer Cydonia 24B v4.3: —
    • Mistral Code Agent Latest: 32.8%

  • LiveCodeBench

    Recent competitive programming problems

    • The Drummer Cydonia 24B v4.3: —
    • Mistral Code Agent Latest: 44.8%

Math

  • AIME 2025

    Competition mathematics, 2025 problems

    • The Drummer Cydonia 24B v4.3: —
    • Mistral Code Agent Latest: 36.7%

Legacy evaluations

  • Terminal-Bench Hard

    Earlier terminal task suite

    • The Drummer Cydonia 24B v4.3: —
    • Mistral Code Agent Latest: 18.9%

  • τ²-Bench Telecom

    Tool use in a customer-support simulation

    • The Drummer Cydonia 24B v4.3: —
    • Mistral Code Agent Latest: 24.9%

  • AA-LCR (unversioned)

    Long-context reasoning, earlier grading

    • The Drummer Cydonia 24B v4.3: —
    • 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
26.5 tok/s
Faster than 17% of 250 models
Time to first token
2.1 s
Quicker than 76% of 250 models
Prompt cache hits
0.6%
Request success (24h)
63.9%

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.

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": "TheDrummer/Cydonia-24B-v4.3",
    "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="TheDrummer/Cydonia-24B-v4.3",
    messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)

Mistral

Other Mistral models, starting with the same family.