Ministral 3 14B (Reasoning) Benchmark Scores & Performance

Benchmark analysis of Ministral 3 14B (Reasoning) by Mistral across 32 sourced tests on BenchLM.

According to BenchLM.ai, Ministral 3 14B (Reasoning) ranks #61 out of 123 models with an overall score of 60/100. While not a frontier model, it offers specific advantages depending on the use case.

Ministral 3 14B (Reasoning) is a open weight model with a 128K token context window. It uses explicit chain-of-thought reasoning, which typically improves performance on math and complex reasoning tasks at the cost of higher latency and token usage.

Ministral 3 14B (Reasoning) sits inside the Ministral 3 14B family alongside Ministral 3 14B.

Its strongest category is Multimodal & Grounded (#47), while its weakest is Knowledge (#71). This performance profile makes it particularly strong for screenshots, documents, charts, and grounded multimodal workflows.

Creator

Mistral

Source Type

Open Weight

Reasoning

Reasoning

Context Window

128K

Overall Score

60#61 of 123

Arena Elo

1245

Family & Lineage

Family

Ministral 3 14B

Reasoning

Canonical Entry

Ministral 3 14B

Sibling Models

Knowledge Benchmarks

MMLU
71
GPQA
70
SuperGPQA
68
OpenBookQA
66
MMLU-Pro
69
HLE
7
FrontierScience
62

Coding Benchmarks

HumanEval
62
SWE-bench Verified
39
LiveCodeBench
33
SWE-bench Pro
36

Mathematics Benchmarks

AIME 2023
73
AIME 2024
75
AIME 2025
74
HMMT Feb 2023
69
HMMT Feb 2024
71
HMMT Feb 2025
70
BRUMO 2025
72
MATH-500
79

Reasoning Benchmarks

SimpleQA
70
MuSR
70
BBH
80
LongBench v2
66
MRCRv2
66

Agentic Benchmarks

Terminal-Bench 2.0
60
BrowseComp
61
OSWorld-Verified
55

Multimodal & Grounded Benchmarks

MMMU-Pro
71
OfficeQA Pro
72

Instruction Following Benchmarks

IFEval
81

Multilingual Benchmarks

MGSM
81
MMLU-ProX
76

Frequently Asked Questions

How does Ministral 3 14B (Reasoning) perform overall in AI benchmarks?

Ministral 3 14B (Reasoning) ranks #61 out of 123 models with an overall score of 60. It is created by Mistral and features a 128K context window.

Is Ministral 3 14B (Reasoning) good for knowledge and understanding?

Ministral 3 14B (Reasoning) ranks #71 out of 123 models in knowledge and understanding benchmarks with an average score of 52.1. There are stronger options in this category.

Is Ministral 3 14B (Reasoning) good for coding and programming?

Ministral 3 14B (Reasoning) ranks #69 out of 123 models in coding and programming benchmarks with an average score of 35. There are stronger options in this category.

Is Ministral 3 14B (Reasoning) good for mathematics?

Ministral 3 14B (Reasoning) ranks #56 out of 123 models in mathematics benchmarks with an average score of 75.2. There are stronger options in this category.

Is Ministral 3 14B (Reasoning) good for reasoning and logic?

Ministral 3 14B (Reasoning) ranks #64 out of 123 models in reasoning and logic benchmarks with an average score of 69.2. There are stronger options in this category.

Is Ministral 3 14B (Reasoning) good for agentic tool use and computer tasks?

Ministral 3 14B (Reasoning) ranks #48 out of 123 models in agentic tool use and computer tasks benchmarks with an average score of 58.5. There are stronger options in this category.

Is Ministral 3 14B (Reasoning) good for multimodal and grounded tasks?

Ministral 3 14B (Reasoning) ranks #47 out of 123 models in multimodal and grounded tasks benchmarks with an average score of 71.5. There are stronger options in this category.

Is Ministral 3 14B (Reasoning) good for instruction following?

Ministral 3 14B (Reasoning) ranks #69 out of 123 models in instruction following benchmarks with an average score of 81. There are stronger options in this category.

Is Ministral 3 14B (Reasoning) good for multilingual tasks?

Ministral 3 14B (Reasoning) ranks #63 out of 123 models in multilingual tasks benchmarks with an average score of 77.8. There are stronger options in this category.

Is Ministral 3 14B (Reasoning) open source?

Yes, Ministral 3 14B (Reasoning) is an open weight model created by Mistral, meaning it can be downloaded and run locally or fine-tuned for specific use cases.

Which sibling models are related to Ministral 3 14B (Reasoning)?

Ministral 3 14B (Reasoning) belongs to the Ministral 3 14B family. Related variants on BenchLM include Ministral 3 14B.

What is the context window size of Ministral 3 14B (Reasoning)?

Ministral 3 14B (Reasoning) has a context window of 128K, which determines how much text it can process in a single interaction.

Last updated: March 12, 2026

Weekly LLM Updates

New model releases, benchmark scores, and leaderboard changes. Every Friday.

Free. Your signup is stored with a derived country code for compliance routing.