Ministral 3 3B
MistralMistralOpen WeightApache 2.0 · Commercial OK
Description
The smallest model in the Ministral 3 family, Ministral 3 3B is a powerful, efficient tiny language model with vision capabilities. This model is the instruct post-trained version in FP8, fine-tuned for instruction tasks, making it ideal for chat and instruction based use cases. The Ministral 3 family is designed for edge deployment, capable of running on a wide range of hardware. Ministral 3 3B can even be deployed locally, fitting in 16GB of VRAM in BF16, and less than 8GB of RAM/VRAM when quantized.
Release Date
2025-12-02
Parameters
3.0B
Context Length
131K
Modalities
image, text
Capability Radar
19
general
13
coding
24
reasoning
23
science
21
agents
10
multimodal
Rankings
| Domain | #Rank | Score | Source |
|---|---|---|---|
| Code Ranking | 569 | 12.0 | AA |
| General Ranking | 564 | 22.0 | AA |
| Science | 599 | 17.0 | AA |
Benchmark Scores (LLM Stats)
(LLM Stats (zeroeval))Chat
MM-MT-Bench
0.08 / 100SR
General
MMLU
70.7%SR
Multilingual MMLU
65.2%SR
TriviaQA
59.2%SR
Wild Bench
56.8%SR
Arena Hard
30.5%SR
Language
MMLU-Redux
73.5%SR
Math
MATH
83.0%SR
AIME 2024
77.5%SR
AIME 2025
72.1%SR
MATH (CoT)
60.1%SR
Reasoning
LiveCodeBench
54.8%SR
GPQANYU + Cohere + Anthropic (2023)
53.4%SR
AGIEval
51.1%SR
AA Evaluation Indices
(Artificial Analysis)Mmlu Pro(TIGER-Lab (Univ. of Waterloo, Toronto, CMU, 2024))52.4
Gpqa(NYU + Cohere + Anthropic (2023))35.8
Ifbench(Google Research (2023))26.8
Tau2(Sierra + U Toronto + Vector Institute (2025))24.9
Livecodebench(UC Berkeley + MIT + Cornell (2024))24.7
Math Index(Artificial Analysis)22.0
Aime 25(MAA (Mathematical Association of America))22.0
Lcr(Artificial Analysis)17.0
Scicode(UIUC + Argonne National Lab (2024))15.3
Hle(Center for AI Safety + Scale AI (2025))5.4
Intelligence Index(Artificial Analysis)4.8
Coding Index(Artificial Analysis)4.8
Tau Banking4.7
Terminalbench Hard(Stanford × Laude Institute (2026))0.0
Terminalbench V2 10.0
Terminalbench V4 00.0
LLM Stats Category Scores
(LLM Stats (zeroeval))Math80
Reasoning60
General40
Communication30
Creativity30
Writing30
Chat20
Multimodal10
Pricing
Input Price$0.1 / 1M tokens
Output Price$0.1 / 1M tokens
Blended Price (3:1)$0.1 / 1M tokens
Cache Read Price$0.01 / 1M tokens
Speed
Tokens/sec242.8
Time to First Token0.58s
Time to Answer0.58s
Provider Price Ranking
Provider Price Ranking
4 providers
Cheapest: MistralMost Expensive: Kilo Gateway
ProviderInputOutput
1MistralPRIMARY
$0.1
$0.1
2NanoGPT
$0.1
$0.1
3OpenRouter
$0.1
$0.1
4Kilo Gateway
$0.1
$0.1
Compare pricing across different API providers for this model.