Ministral 3B is a tiny, efficient 3B parameter model from Mistral AI with vision capabilities, designed for edge deployment.
Added Dec 4, 2025
Model weightsContext Window
131.1K
Max Output
32.8K
Avg output tokens (7d)
79 tokens
Input Price (Auto)
$0.10/1M
Output Price (Auto)
$0.10/1M
Cache Read (Auto)
$0.050/1M
Benchmarks
Benchmarks
Performance metrics and benchmarks
Sourced from Artificial Analysis.
Intelligence Index
4.8
Coding Index
4.8
Agentic Index
0.8
Agentic work
AutomationBench-AA
Workflow automation with guardrail penalties
0.7%
Better than 13% of models compared
AA-Briefcase
Agentic knowledge work (Elo)
16 Elo
Better than 6% of models compared
GDPval-AA v2
Economically valuable tasks (Elo)
234 Elo
Better than 11% of models compared
Document reasoning
GDP.pdf
Professional PDF reasoning: all-pass rate
0.0%
Better than 1% of models compared
AA-LCR v1.1
Long context reasoning with updated grading
17.0%
Better than 21% of models compared
Reasoning
HLE
Humanity's Last Exam
5.4%
Better than 35% of models compared
IFBench
Instruction-following benchmark
26.8%
Better than 10% of models compared
CritPt
Research-level physics reasoning
0.0%
Coding
Terminal-Bench v4.0
Practical coding and terminal tasks
0.0%
Better than 17% of models compared
SciCode
Python programming for scientific computing
15.3%
Better than 1% of models compared
LiveCodeBench
Contamination-free coding benchmark
24.7%
Better than 26% of models compared
Math
AIME 2025
American Invitational Mathematics Examination 2025
22.0%
Better than 24% of models compared
Knowledge
MMLU-Pro
Professional and academic subject knowledge
52.4%
Better than 16% of models compared
AA-Omniscience Accuracy
Proportion of correctly answered questions
9.0%
AA-Omniscience Hallucination Rate
Rate of incorrect answers among non-correct responses
80.2%
Legacy benchmarks
GPQA Diamond (legacy)
Graduate-level scientific reasoning
35.8%
Better than 12% of models compared
Terminal-Bench Hard (legacy)
Agentic coding and terminal use
0.0%
Better than 5% of models compared
T²-Bench Telecom (legacy)
Conversational AI agents in dual-control scenarios
24.9%
Better than 28% of models compared
AA-LCR (unversioned / legacy)
Long context reasoning evaluation
17.0%
Better than 21% of models compared
GDPval-AA (unversioned / legacy)
Economically valuable tasks
0.0%
Last updated Sep 13, 2026
Artificial AnalysisProviders
Auto routing is available for this model. Explicit provider selection is not available.
Loading provider options…
Related text models
Compare Ministral 3B with similar models from the same provider or model family.
Ministral 14B
mistralai/ministral-14b-2512Ministral 14B is a powerful 14B parameter model from Mistral AI with vision capabilities, offering frontier performance in a compact size.
Ministral 8B
mistralai/ministral-8b-2512Ministral 8B is an efficient 8B parameter model from Mistral AI with vision capabilities, designed for edge deployment.
Ministral 3 14B
mistralai/ministral-14b-instruct-2512Ministral 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.
Mistral Large 3 675B
mistralai/mistral-large-3-675b-instruct-2512Mistral Large 3 675B is Mistral AI's flagship language model featuring advanced rope scaling and Eagle speculative decoding. Delivers exceptional performance across reasoning, coding, and multilingual tasks.
Devstral 2 123B
mistralai/devstral-2-123b-instruct-2512Devstral 2 123B is a 123 billion parameter model from Mistral AI optimized for coding and development tasks. Features advanced reasoning capabilities for software engineering workflows.
Mistral Small 3 24B (2501)
mistralai/mistral-small-24b-instruct-2501Mistral Small 3 24B (2501) hosted by IONOS in Berlin, Germany. Zero data retention.