Mistral · Open weights
Ministral 3 14B
Ministral 3 14B is a balanced model in the Ministral 3 family, designed for edge deployment. A powerful, efficient language model with vision capabilities, fine-tuned for instruction tasks. Features multilingual support, strong system prompt adherence, and native function calling. Apache 2.0 licensed.
- Vision
- Input
- Text, Images
- Output
- Text
- Discovery tier
- Open weights
Pricing
USD per 1M tokens- Input
- $0.10
- Output
- $0.40
Reference prices as published by the model provider. API example
Specifications
- Context window
- 262.1K
- Max output
- 32.8K
- Average output (7 days)
- 203 tokens
- Longer than 22% of 468 models
Side by side
Ministral 3 14B compared
Specifications, prices, speed and benchmark scores next to each other. Benchmarks below show every compared model too.
| Ministral 3 14BMistralThis model | Mistral Code Agent LatestMistralRemove | |
|---|---|---|
| Provider | Mistral | Mistral |
| Discovery tier | Open weights | Open weights |
| Added | Dec 2, 2025 | Jun 2, 2026 |
| Limits | ||
| Context window | 262.14K | 262.14K |
| Max output | 32.77K | 32.77K |
| Average output | 203 tokens | 316 tokens |
| Pricing, USD per 1M tokens | ||
| Input | $0.10Best | $0.40 |
| Output | $0.40Best | $2.00 |
| Performance | ||
| Request success (24h) | 100.0% | 100.0% |
| Benchmark indexes | ||
| Intelligence Index | 6.0 | 8.6Best |
| Coding Index | 14.4 | 31.3Best |
| Math Index | 30.0 | 36.7Best |
| Capabilities | ||
| Tools | No | Yes |
| Vision | Yes | No |
| Structured output | No | Yes |
| Reasoning effort | — | — |
Public evaluations
Benchmarks
Independent evaluation results, with how each score ranks among the models in the Noumen catalog.
- Ministral 3 14B
- Mistral Code Agent Latest
Intelligence Index
- Ministral 3 14B6.0
- Mistral Code Agent Latest8.6
Ministral 3 14B: Better than 3% of 326 scored models
Indexes
Coding Index
Composite of the coding evaluations
- Ministral 3 14B: 14.4
- Mistral Code Agent Latest: 31.3Top
Math Index
Composite of the math evaluations
- Ministral 3 14B: 30.0
- Mistral Code Agent Latest: 36.7Top
Agentic work
AutomationBench-AA
Workflow automation, penalized for guardrail violations
- Ministral 3 14B: 0.6%
- Mistral Code Agent Latest: 3.1%Top
AutomationBench-AA tasks completed
Workflows finished end to end without a guardrail violation
- Ministral 3 14B: 0.2%Top
- Mistral Code Agent Latest: 0.0%
AA-Briefcasev1.1
Agentic knowledge work, rated head to head
- Ministral 3 14B: 131 Elo
- Mistral Code Agent Latest: 482 EloTop
GDPval-AAv2.1
Economically valuable occupational tasks, rated head to head
- Ministral 3 14B: 247 Elo
- Mistral Code Agent Latest: 544 EloTop
Document reasoning
GDP.pdf
Professional reasoning over PDF documents, all-pass rate
- Ministral 3 14B: 1.2%
- Mistral Code Agent Latest: 2.4%Top
AA-LCRv1.1
Reasoning across long documents
- Ministral 3 14B: 26.3%
- Mistral Code Agent Latest: 32.3%Top
MLCR-AA
Long-context reasoning over medical records
- Ministral 3 14B: 2.2%
- Mistral Code Agent Latest: —
Reasoning and knowledge
Humanity’s Last Exam
Expert-level questions across academic fields
- Ministral 3 14B: 4.6%Top
- Mistral Code Agent Latest: 3.6%
GPQA Diamond
Graduate-level science questions
- Ministral 3 14B: 57.2%
- Mistral Code Agent Latest: 59.4%Top
MMLU-Pro
Multi-subject knowledge and reasoning
- Ministral 3 14B: 69.3%
- Mistral Code Agent Latest: 76.2%Top
IFBench
Following precise output instructions
- Ministral 3 14B: 32.0%
- Mistral Code Agent Latest: 38.1%Top
Coding
Terminal-Benchv4.0
Practical software engineering in a terminal
- Ministral 3 14B: 0.0%Top
- Mistral Code Agent Latest: 0.0%Top
SciCode
Scientific computing in Python
- Ministral 3 14B: 23.8%
- Mistral Code Agent Latest: 32.8%Top
LiveCodeBench
Recent competitive programming problems
- Ministral 3 14B: 35.1%
- Mistral Code Agent Latest: 44.8%Top
Math
AIME 2025
Competition mathematics, 2025 problems
- Ministral 3 14B: 30.0%
- Mistral Code Agent Latest: 36.7%Top
Legacy evaluations
Terminal-Bench Hard
Earlier terminal task suite
- Ministral 3 14B: 4.5%
- Mistral Code Agent Latest: 18.9%Top
τ²-Bench Telecom
Tool use in a customer-support simulation
- Ministral 3 14B: 27.2%Top
- Mistral Code Agent Latest: 24.9%
AA-LCR (unversioned)
Long-context reasoning, earlier grading
- Ministral 3 14B: 26.3%
- Mistral Code Agent Latest: 32.3%Top
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.
- Prompt cache hits
- 24.9%
- 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/ministral-14b-instruct-2512",
"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/ministral-14b-instruct-2512",
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.