Ministral 3 8B (Reasoning) Benchmark Scores & Performance

Benchmark analysis of Ministral 3 8B (Reasoning) by Mistral across 32 sourced tests on BenchLM.

According to BenchLM.ai, Ministral 3 8B (Reasoning) ranks #108 out of 123 models with an overall score of 36/100. While not a frontier model, it offers specific advantages depending on the use case.

Ministral 3 8B (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 8B (Reasoning) sits inside the Ministral 3 8B family alongside Ministral 3 8B.

Its strongest category is Instruction Following (#92), while its weakest is Multimodal & Grounded (#114). 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

36#108 of 123

Arena Elo

1061

Family & Lineage

Family

Ministral 3 8B

Reasoning

Canonical Entry

Ministral 3 8B

Sibling Models

Knowledge Benchmarks

MMLU
30
GPQA
29
SuperGPQA
27
OpenBookQA
25
MMLU-Pro
54
HLE
5
FrontierScience
34

Coding Benchmarks

HumanEval
24
SWE-bench Verified
17
LiveCodeBench
16
SWE-bench Pro
14

Mathematics Benchmarks

AIME 2023
33
AIME 2024
35
AIME 2025
34
HMMT Feb 2023
29
HMMT Feb 2024
31
HMMT Feb 2025
30
BRUMO 2025
32
MATH-500
67

Reasoning Benchmarks

SimpleQA
32
MuSR
33
BBH
70
LongBench v2
44
MRCRv2
47

Agentic Benchmarks

Terminal-Bench 2.0
39
BrowseComp
41
OSWorld-Verified
36

Multimodal & Grounded Benchmarks

MMMU-Pro
28
OfficeQA Pro
40

Instruction Following Benchmarks

IFEval
70

Multilingual Benchmarks

MGSM
63
MMLU-ProX
61

Frequently Asked Questions

How does Ministral 3 8B (Reasoning) perform overall in AI benchmarks?

Ministral 3 8B (Reasoning) ranks #108 out of 123 models with an overall score of 36. It is created by Mistral and features a 128K context window.

Is Ministral 3 8B (Reasoning) good for knowledge and understanding?

Ministral 3 8B (Reasoning) ranks #112 out of 123 models in knowledge and understanding benchmarks with an average score of 30. There are stronger options in this category.

Is Ministral 3 8B (Reasoning) good for coding and programming?

Ministral 3 8B (Reasoning) ranks #103 out of 123 models in coding and programming benchmarks with an average score of 15.2. There are stronger options in this category.

Is Ministral 3 8B (Reasoning) good for mathematics?

Ministral 3 8B (Reasoning) ranks #99 out of 123 models in mathematics benchmarks with an average score of 47.8. There are stronger options in this category.

Is Ministral 3 8B (Reasoning) good for reasoning and logic?

Ministral 3 8B (Reasoning) ranks #107 out of 123 models in reasoning and logic benchmarks with an average score of 42.1. There are stronger options in this category.

Is Ministral 3 8B (Reasoning) good for agentic tool use and computer tasks?

Ministral 3 8B (Reasoning) ranks #97 out of 123 models in agentic tool use and computer tasks benchmarks with an average score of 38.5. There are stronger options in this category.

Is Ministral 3 8B (Reasoning) good for multimodal and grounded tasks?

Ministral 3 8B (Reasoning) ranks #114 out of 123 models in multimodal and grounded tasks benchmarks with an average score of 33.4. There are stronger options in this category.

Is Ministral 3 8B (Reasoning) good for instruction following?

Ministral 3 8B (Reasoning) ranks #92 out of 123 models in instruction following benchmarks with an average score of 70. There are stronger options in this category.

Is Ministral 3 8B (Reasoning) good for multilingual tasks?

Ministral 3 8B (Reasoning) ranks #92 out of 123 models in multilingual tasks benchmarks with an average score of 61.7. There are stronger options in this category.

Is Ministral 3 8B (Reasoning) open source?

Yes, Ministral 3 8B (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 8B (Reasoning)?

Ministral 3 8B (Reasoning) belongs to the Ministral 3 8B family. Related variants on BenchLM include Ministral 3 8B.

What is the context window size of Ministral 3 8B (Reasoning)?

Ministral 3 8B (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.