Ministral 3 14B
MistralMistralOpen WeightApache 2.0 · Commercial OK
Descripción
A balanced model in the Ministral 3 family, Ministral 3 14B is a powerful, efficient tiny language model with vision capabilities. This model is the reasoning post-trained version, trained for reasoning tasks, making it ideal for math, coding and stem related use cases. The Ministral 3 family is designed for edge deployment, capable of running on a wide range of hardware. Ministral 3 14B can even be deployed locally, capable of fitting in 24GB of VRAM in BF16, and less than 12GB of RAM/VRAM when quantized.
Fecha de lanzamiento
2025-12-02
Parámetros
14.0B
Longitud del contexto
262K
Modalidades
image, text
Radar de capacidades
30
general
21
coding
35
reasoning
35
scienceest.
0
agents
10
multimodal
Science usa un proxy de razonamiento cuando los benchmarks científicos dedicados no están disponibles.
Rankings
| Dominio | #Posición | Puntuación | Fuente |
|---|---|---|---|
| Code Ranking | 318 | 22.0 | AA |
| General Ranking | 322 | 34.0 | AA |
| Math Reasoning | 265 | 30.0 | AA |
| Science | 306 | 35.0 | AA |
Puntuaciones de benchmarks (LLM Stats)
Biology
GPQA
71.2%Aut.
Code
LiveCodeBench
64.6%Aut.
Math
AIME 2024
89.8%Aut.
AIME 2025
85.0%Aut.
Índices de evaluación AA
Math Index30.0
Intelligence Index16.0
Coding Index10.9
Mmlu Pro0.7
Gpqa0.6
Livecodebench0.4
Ifbench0.3
Aime 250.3
Tau20.3
Scicode0.2
Lcr0.2
Hle0.0
Terminalbench Hard0.0
Puntuaciones por categoría LLM Stats
Math90
Reasoning80
Biology70
Chemistry70
General70
Physics70
Code60
Precios
Precio de entrada$0.2 / 1M tokens
Precio de salida$0.2 / 1M tokens
Precio mixto (3:1)$0.2 / 1M tokens
Velocidad
Tokens/seg143.4 tokens/s
Retraso del primer token0.33s
Tiempo hasta la respuesta0.33s
Proveedores disponibles
(Unidades internas LS)No hay datos de proveedores disponibles