Ministral 3 3B (Reasoning) Benchmark Scores & Performance

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

According to BenchLM.ai, Ministral 3 3B (Reasoning) ranks #119 out of 123 models with an overall score of 31/100. While not a frontier model, it offers specific advantages depending on the use case.

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

Its strongest category is Instruction Following (#105), while its weakest is Knowledge (#120). This performance profile makes it a well-rounded choice across a range of tasks.

Creator

Mistral

Source Type

Open Weight

Reasoning

Reasoning

Context Window

128K

Overall Score

31#119 of 123

Arena Elo

1043

Family & Lineage

Family

Ministral 3 3B

Reasoning

Canonical Entry

Ministral 3 3B

Sibling Models

Knowledge Benchmarks

MMLU
25
GPQA
24
SuperGPQA
22
OpenBookQA
20
MMLU-Pro
49
HLE
1
FrontierScience
29

Coding Benchmarks

HumanEval
16
SWE-bench Verified
9
LiveCodeBench
8
SWE-bench Pro
6

Mathematics Benchmarks

AIME 2023
27
AIME 2024
29
AIME 2025
28
HMMT Feb 2023
23
HMMT Feb 2024
25
HMMT Feb 2025
24
BRUMO 2025
26
MATH-500
59

Reasoning Benchmarks

SimpleQA
26
MuSR
26
BBH
63
LongBench v2
37
MRCRv2
40

Agentic Benchmarks

Terminal-Bench 2.0
33
BrowseComp
37
OSWorld-Verified
33

Multimodal & Grounded Benchmarks

MMMU-Pro
25
OfficeQA Pro
37

Instruction Following Benchmarks

IFEval
68

Multilingual Benchmarks

MGSM
61
MMLU-ProX
59

Frequently Asked Questions

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

Ministral 3 3B (Reasoning) ranks #119 out of 123 models with an overall score of 31. It is created by Mistral and features a 128K context window.

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

Ministral 3 3B (Reasoning) ranks #120 out of 123 models in knowledge and understanding benchmarks with an average score of 25.2. There are stronger options in this category.

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

Ministral 3 3B (Reasoning) ranks #119 out of 123 models in coding and programming benchmarks with an average score of 7.2. There are stronger options in this category.

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

Ministral 3 3B (Reasoning) ranks #112 out of 123 models in mathematics benchmarks with an average score of 40.9. There are stronger options in this category.

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

Ministral 3 3B (Reasoning) ranks #117 out of 123 models in reasoning and logic benchmarks with an average score of 35.3. There are stronger options in this category.

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

Ministral 3 3B (Reasoning) ranks #106 out of 123 models in agentic tool use and computer tasks benchmarks with an average score of 34. There are stronger options in this category.

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

Ministral 3 3B (Reasoning) ranks #120 out of 123 models in multimodal and grounded tasks benchmarks with an average score of 30.4. There are stronger options in this category.

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

Ministral 3 3B (Reasoning) ranks #105 out of 123 models in instruction following benchmarks with an average score of 68. There are stronger options in this category.

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

Ministral 3 3B (Reasoning) ranks #108 out of 123 models in multilingual tasks benchmarks with an average score of 59.7. There are stronger options in this category.

Is Ministral 3 3B (Reasoning) open source?

Yes, Ministral 3 3B (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 3B (Reasoning)?

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

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

Ministral 3 3B (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.