Mistral · Balanced
Mistral Medium 3
Mistral Medium 3 delivers frontier performance while being an order of magnitude less expensive. For instance, the model performs at or above 90% of Claude Sonnet 3.7 on benchmarks across the board at a significantly lower cost. On performance, Mistral Medium 3 also surpasses leading open models such as Llama 4 Maverick and enterprise models such as Cohere Command A. On pricing, the model beats cost leaders such as DeepSeek v3, both in API and self-deployed systems.
- Vision
- Input
- Text, Images
- Output
- Text
- Discovery tier
- Balanced
Pricing
USD per 1M tokens- Input
- $0.40
- Output
- $2.00
Reference prices as published by the model provider. API example
Specifications
- Context window
- 131.1K
- Max output
- 32.8K
- Average output (7 days)
- 683 tokens
- Longer than 61% of 465 models
Side by side
Compare models
Put Mistral Medium 3 next to up to three other models. The comparison stays in the link, so you can share it.
Public evaluations
Benchmarks
Independent evaluation results, with how each score ranks among the models in the Noumen catalog.
Intelligence Index
9.0
Better than 16% of 326 scored models
Indexes
Math Index
30.3Composite of the math evaluations
Better than 29% of 118 scored models
Document reasoning
AA-LCRv1.1
31.3%Reasoning across long documents
Better than 13% of 309 scored models
Reasoning and knowledge
Humanity’s Last Exam
4.1%Expert-level questions across academic fields
Better than 7% of 323 scored models
GPQA Diamond
57.8%Graduate-level science questions
Better than 16% of 291 scored models
MMLU-Pro
76.0%Multi-subject knowledge and reasoning
Better than 36% of 132 scored models
IFBench
39.3%Following precise output instructions
Better than 26% of 215 scored models
Coding
LiveCodeBench
40.0%Recent competitive programming problems
Better than 31% of 129 scored models
Math
AIME 2025
30.3%Competition mathematics, 2025 problems
Better than 29% of 118 scored models
AIME
44.0%Competition mathematics
Better than 51% of 72 scored models
MATH-500
90.7%Competition math problems
Better than 49% of 73 scored models
Legacy evaluations
Terminal-Bench Hard
3.8%Earlier terminal task suite
Better than 8% of 212 scored models
τ²-Bench Telecom
24.3%Tool use in a customer-support simulation
Better than 12% of 214 scored models
AA-LCR (unversioned)
31.3%Long-context reasoning, earlier grading
Better than 13% of 309 scored models
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
- 107.8 tok/s
- Faster than 63% of 250 models
- Time to first token
- 0.7 s
- Quicker than 99% of 250 models
- Prompt cache hits
- 86.4%
- Request success (24h)
- 100.0%
- 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.
- 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.
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",
"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",
messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)Mistral
Related models
Other Mistral models, starting with the same family.