Ministral 3 8B Benchmark Scores & Performance

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

According to BenchLM.ai, Ministral 3 8B ranks #116 out of 123 models with an overall score of 32/100. While not a frontier model, it offers specific advantages depending on the use case.

Ministral 3 8B is a open weight model with a 128K token context window. It processes queries without explicit chain-of-thought reasoning, offering faster response times and lower token usage.

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

Its strongest category is Multilingual (#93), while its weakest is Knowledge (#117). This performance profile makes it a well-rounded choice across a range of tasks.

Creator

Mistral

Source Type

Open Weight

Reasoning

Non-Reasoning

Context Window

128K

Overall Score

32#116 of 123

Arena Elo

1057

Family & Lineage

Family

Ministral 3 8B

Base entry

Knowledge Benchmarks

MMLU
28
GPQA
27
SuperGPQA
25
OpenBookQA
23
MMLU-Pro
52
HLE
3
FrontierScience
32

Coding Benchmarks

HumanEval
23
SWE-bench Verified
16
LiveCodeBench
15
SWE-bench Pro
13

Mathematics Benchmarks

AIME 2023
30
AIME 2024
32
AIME 2025
33
HMMT Feb 2023
26
HMMT Feb 2024
28
HMMT Feb 2025
27
BRUMO 2025
29
MATH-500
60

Reasoning Benchmarks

SimpleQA
28
MuSR
26
BBH
63
LongBench v2
38
MRCRv2
41

Agentic Benchmarks

Terminal-Bench 2.0
26
BrowseComp
36
OSWorld-Verified
27

Multimodal & Grounded Benchmarks

MMMU-Pro
27
OfficeQA Pro
39

Instruction Following Benchmarks

IFEval
69

Multilingual Benchmarks

MGSM
63
MMLU-ProX
61

Frequently Asked Questions

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

Ministral 3 8B ranks #116 out of 123 models with an overall score of 32. It is created by Mistral and features a 128K context window.

Is Ministral 3 8B good for knowledge and understanding?

Ministral 3 8B ranks #117 out of 123 models in knowledge and understanding benchmarks with an average score of 28. There are stronger options in this category.

Is Ministral 3 8B good for coding and programming?

Ministral 3 8B ranks #110 out of 123 models in coding and programming benchmarks with an average score of 14.2. There are stronger options in this category.

Is Ministral 3 8B good for mathematics?

Ministral 3 8B ranks #106 out of 123 models in mathematics benchmarks with an average score of 43.3. There are stronger options in this category.

Is Ministral 3 8B good for reasoning and logic?

Ministral 3 8B ranks #115 out of 123 models in reasoning and logic benchmarks with an average score of 36.1. There are stronger options in this category.

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

Ministral 3 8B ranks #117 out of 123 models in agentic tool use and computer tasks benchmarks with an average score of 28.9. There are stronger options in this category.

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

Ministral 3 8B ranks #116 out of 123 models in multimodal and grounded tasks benchmarks with an average score of 32.4. There are stronger options in this category.

Is Ministral 3 8B good for instruction following?

Ministral 3 8B ranks #95 out of 123 models in instruction following benchmarks with an average score of 69. There are stronger options in this category.

Is Ministral 3 8B good for multilingual tasks?

Ministral 3 8B ranks #93 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 open source?

Yes, Ministral 3 8B 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?

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

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

Ministral 3 8B 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.