NOUMENOpen app
NOUMEN

Mistral · Balanced

Codestral 2508

Added Aug 1, 2025

Compare models

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

Loading models…

Use in the app

Mistral's cutting-edge language model for coding released end of July 2025. Codestral specializes in low-latency, high-frequency tasks such as fill-in-the-middle (FIM), code correction and test generation.

Input
Text
Output
Text
Discovery tier
Balanced

Pricing

USD per 1M tokens
Input
$0.30
Output
$0.90

Reference prices as published by the model provider. API example

Specifications

Context window
256K
Max output
32.8K
Average output (7 days)
124 tokens
Longer than 12% of 468 models

Side by side

Codestral 2508 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…

Codestral 2508MistralThis modelQwen3 VL 235B A22B Instruct OriginalQwenRemove
ProviderMistralQwen
Discovery tierBalancedBalanced
AddedAug 1, 2025Sep 25, 2025
Limits
Context window256K—
Max output32.77K32.77K
Average output124 tokens288 tokens
Pricing, USD per 1M tokens
Input$0.30$0.30
Output$0.90Best$1.90
Performance
Request success (24h)—100.0%
Benchmark indexes
Intelligence Index—9.9
Math Index—70.7
Capabilities
VisionNoYes
Reasoning effort——

Public evaluations

Benchmarks

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

  • Codestral 2508
  • Qwen3 VL 235B A22B Instruct Original

Intelligence Index

  • Codestral 2508—
  • Qwen3 VL 235B A22B Instruct Original9.9
3.8Catalog models by score55.1

Indexes

  • Math Index

    Composite of the math evaluations

    • Codestral 2508: —
    • Qwen3 VL 235B A22B Instruct Original: 70.7

Document reasoning

  • AA-LCRv1.1

    Reasoning across long documents

    • Codestral 2508: —
    • Qwen3 VL 235B A22B Instruct Original: 32.7%

Reasoning and knowledge

  • Humanity’s Last Exam

    Expert-level questions across academic fields

    • Codestral 2508: —
    • Qwen3 VL 235B A22B Instruct Original: 6.6%

  • GPQA Diamond

    Graduate-level science questions

    • Codestral 2508: —
    • Qwen3 VL 235B A22B Instruct Original: 71.2%

  • MMLU-Pro

    Multi-subject knowledge and reasoning

    • Codestral 2508: —
    • Qwen3 VL 235B A22B Instruct Original: 82.3%

  • IFBench

    Following precise output instructions

    • Codestral 2508: —
    • Qwen3 VL 235B A22B Instruct Original: 42.7%

Coding

  • LiveCodeBench

    Recent competitive programming problems

    • Codestral 2508: —
    • Qwen3 VL 235B A22B Instruct Original: 59.4%

Math

  • AIME 2025

    Competition mathematics, 2025 problems

    • Codestral 2508: —
    • Qwen3 VL 235B A22B Instruct Original: 70.7%

Legacy evaluations

  • Terminal-Bench Hard

    Earlier terminal task suite

    • Codestral 2508: —
    • Qwen3 VL 235B A22B Instruct Original: 6.8%

  • τ²-Bench Telecom

    Tool use in a customer-support simulation

    • Codestral 2508: —
    • Qwen3 VL 235B A22B Instruct Original: 35.1%

  • AA-LCR (unversioned)

    Long-context reasoning, earlier grading

    • Codestral 2508: —
    • Qwen3 VL 235B A22B Instruct Original: 32.7%

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": "mistralai/codestral-2508",
    "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/codestral-2508",
    messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)

Mistral

Other Mistral models, starting with the same family.