Ministral 3 (14B Base 2512) vs Ministral 3 (8B Base 2512)
Ministral 3 (14B Base 2512) and Ministral 3 (8B Base 2512) are closely matched at 3.6 and -1.1 on the LLM Stats Score.
Mistral AI · Mistral AI · Updated for 2026
Which is better?
Ministral 3 (14B Base 2512) and Ministral 3 (8B Base 2512) are closely matched on the overall LLM Stats Score at 3.6 and -1.1.
In the 6 individual benchmarks reported for both models, Ministral 3 (14B Base 2512) wins 6; this is a narrower head-to-head signal than the composite indexes.
Based on current LLM Stats indexes, shared benchmarks, pricing, and model metadata for 2026.
Choose Ministral 3 (14B Base 2512)
- you value its reported benchmark strengths — it wins 6 of 6 exact shared results
Choose Ministral 3 (8B Base 2512)
- you are already invested in the Mistral AI ecosystem
At a glance
The differences that matter most.
Capability indexes
Additional strengths measured across groups of related public benchmarks
Individual benchmarks
6 reported for Ministral 3 (14B Base 2512) · 6 for Ministral 3 (8B Base 2512)
Ministral 3 (14B Base 2512) outperforms in 6 benchmarks (AGIEval, MATH (CoT), MMLU, MMLU-Redux, Multilingual MMLU, TriviaQA), while Ministral 3 (8B Base 2512) is better at 0 benchmarks.
Ministral 3 (14B Base 2512) significantly outperforms across most benchmarks.
Human preference
Blind head-to-head votes and playground preference scores
Model Size
Parameter count comparison
Ministral 3 (14B Base 2512) has 6.0B more parameters than Ministral 3 (8B Base 2512), making it 75.0% larger.
Input capabilities
Documented input modalities across available providers
Both Ministral 3 (14B Base 2512) and Ministral 3 (8B Base 2512) support multimodal inputs.
They are both capable of processing various types of data, offering versatility in application.
Ministral 3 (14B Base 2512)
Ministral 3 (8B Base 2512)
License
Usage and distribution terms
Both models are licensed under Apache 2.0.
Both models share the same licensing terms, providing consistent usage rights.
Apache 2.0
Open weights
Apache 2.0
Open weights
Release Timeline
When each model was launched
Both models were released on 2025-12-04.
They likely represent similar generations of model development.
Dec 4, 2025
10 months ago
Dec 4, 2025
10 months ago
Knowledge Cutoff
When training data ends
Neither model specifies a knowledge cutoff date.
Unable to compare the recency of their training data.
Outputs Comparison
Judge for yourself.
Run your own prompts against Ministral 3 (14B Base 2512) and Ministral 3 (8B Base 2512) side-by-side, then vote on the output you prefer.
FAQ
Common questions about Ministral 3 (14B Base 2512) vs Ministral 3 (8B Base 2512).