NOUMENOpen app
NOUMEN

Mistral · Open weights

The Drummer Cydonia 24B v4

Added Jul 22, 2025Open weights

Compare models

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

Loading models…

Use in the app

Cydonia 24B v4 is the latest iteration of TheDrummer's Cydonia series, a finetune of Mistral Small.

Input
Text
Output
Text
Discovery tier
Open weights

Pricing

USD per 1M tokens
Input
$0.20
Output
$0.24

Reference prices as published by the model provider. API example

Specifications

Context window
32.8K
Max output
—
Average output (7 days)
535 tokens
Longer than 51% of 468 models

Side by side

The Drummer Cydonia 24B v4 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 v4MistralThis modelGemma 3 4B ITGoogleRemove
ProviderMistralGoogle
Discovery tierOpen weightsOpen weights
AddedJul 22, 2025Jan 1, 2024
Limits
Context window32.77K128KBest
Max output—8.19K
Average output535 tokens115 tokens
Pricing, USD per 1M tokens
Input$0.20$0.20
Output$0.24$0.20Best
Performance
Request success (24h)—99.8%
Benchmark indexes
Intelligence Index—4.8
Coding Index—2.7
Math Index—12.7
Capabilities
PDF inputNoYes
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
  • Gemma 3 4B IT

Intelligence Index

  • The Drummer Cydonia 24B v4—
  • Gemma 3 4B IT4.8
3.8Catalog models by score55.1

Indexes

  • Coding Index

    Composite of the coding evaluations

    • The Drummer Cydonia 24B v4: —
    • Gemma 3 4B IT: 2.7

  • Math Index

    Composite of the math evaluations

    • The Drummer Cydonia 24B v4: —
    • Gemma 3 4B IT: 12.7

Document reasoning

  • AA-LCRv1.1

    Reasoning across long documents

    • The Drummer Cydonia 24B v4: —
    • Gemma 3 4B IT: 6.7%

Reasoning and knowledge

  • Humanity’s Last Exam

    Expert-level questions across academic fields

    • The Drummer Cydonia 24B v4: —
    • Gemma 3 4B IT: 5.3%

  • GPQA Diamond

    Graduate-level science questions

    • The Drummer Cydonia 24B v4: —
    • Gemma 3 4B IT: 29.1%

  • MMLU-Pro

    Multi-subject knowledge and reasoning

    • The Drummer Cydonia 24B v4: —
    • Gemma 3 4B IT: 41.7%

  • IFBench

    Following precise output instructions

    • The Drummer Cydonia 24B v4: —
    • Gemma 3 4B IT: 28.3%

Coding

  • LiveCodeBench

    Recent competitive programming problems

    • The Drummer Cydonia 24B v4: —
    • Gemma 3 4B IT: 11.2%

Math

  • AIME 2025

    Competition mathematics, 2025 problems

    • The Drummer Cydonia 24B v4: —
    • Gemma 3 4B IT: 12.7%

  • AIME

    Competition mathematics

    • The Drummer Cydonia 24B v4: —
    • Gemma 3 4B IT: 6.3%

  • MATH-500

    Competition math problems

    • The Drummer Cydonia 24B v4: —
    • Gemma 3 4B IT: 76.6%

Legacy evaluations

  • Terminal-Bench Hard

    Earlier terminal task suite

    • The Drummer Cydonia 24B v4: —
    • Gemma 3 4B IT: 0.8%

  • τ²-Bench Telecom

    Tool use in a customer-support simulation

    • The Drummer Cydonia 24B v4: —
    • Gemma 3 4B IT: 5.0%

  • AA-LCR (unversioned)

    Long-context reasoning, earlier grading

    • The Drummer Cydonia 24B v4: —
    • Gemma 3 4B IT: 6.7%

Scores from Artificial Analysis, updated Oct 26, 2026. Artificial Analysis

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",
    "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",
    messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)

Mistral

Other Mistral models, starting with the same family.