Mistral Large 3 vs Ministral 3 3B (Reasoning)

Side-by-side benchmark comparison across agentic, coding, multimodal, knowledge, reasoning, and math workflows.

Mistral Large 3 is clearly ahead on the aggregate, 61 to 31. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.

Mistral Large 3's sharpest advantage is in multimodal & grounded, where it averages 75.5 against 30.4. The single biggest benchmark swing on the page is HumanEval, 68 to 16.

Mistral Large 3 is also the more expensive model on tokens at $2.00 input / $6.00 output per 1M tokens, versus $0.00 input / $0.00 output per 1M tokens for Ministral 3 3B (Reasoning). That is roughly Infinityx on output cost alone. Ministral 3 3B (Reasoning) is the reasoning model in the pair, while Mistral Large 3 is not. That usually helps on harder chain-of-thought-heavy tests, but it can also mean more latency and more token spend in real use.

Quick Verdict

Pick Mistral Large 3 if you want the stronger benchmark profile. Ministral 3 3B (Reasoning) only becomes the better choice if you want the cheaper token bill or you want the stronger reasoning-first profile.

Agentic

Mistral Large 3

Mistral Large 3

52.5

Ministral 3 3B (Reasoning)

34

52
Terminal-Bench 2.0
33
58
BrowseComp
37
49
OSWorld-Verified
33

Coding

Mistral Large 3

Mistral Large 3

41

Ministral 3 3B (Reasoning)

7.2

68
HumanEval
16
45
SWE-bench Verified
9
39
LiveCodeBench
8
42
SWE-bench Pro
6

Multimodal & Grounded

Mistral Large 3

Mistral Large 3

75.5

Ministral 3 3B (Reasoning)

30.4

75
MMMU-Pro
25
76
OfficeQA Pro
37

Reasoning

Mistral Large 3

Mistral Large 3

70.6

Ministral 3 3B (Reasoning)

35.3

73
SimpleQA
26
71
MuSR
26
81
BBH
63
67
LongBench v2
37
67
MRCRv2
40

Knowledge

Mistral Large 3

Mistral Large 3

57.1

Ministral 3 3B (Reasoning)

25.2

76
MMLU
25
75
GPQA
24
73
SuperGPQA
22
71
OpenBookQA
20
74
MMLU-Pro
49
12
HLE
1
67
FrontierScience
29

Instruction Following

Mistral Large 3

Mistral Large 3

83

Ministral 3 3B (Reasoning)

68

83
IFEval
68

Multilingual

Mistral Large 3

Mistral Large 3

78.8

Ministral 3 3B (Reasoning)

59.7

82
MGSM
61
77
MMLU-ProX
59

Mathematics

Mistral Large 3

Mistral Large 3

77.3

Ministral 3 3B (Reasoning)

40.9

76
AIME 2023
27
78
AIME 2024
29
77
AIME 2025
28
72
HMMT Feb 2023
23
74
HMMT Feb 2024
25
73
HMMT Feb 2025
24
75
BRUMO 2025
26
80
MATH-500
59

Frequently Asked Questions

Which is better, Mistral Large 3 or Ministral 3 3B (Reasoning)?

Mistral Large 3 is ahead overall, 61 to 31. The biggest single separator in this matchup is HumanEval, where the scores are 68 and 16.

Which is better for knowledge tasks, Mistral Large 3 or Ministral 3 3B (Reasoning)?

Mistral Large 3 has the edge for knowledge tasks in this comparison, averaging 57.1 versus 25.2. Inside this category, MMLU is the benchmark that creates the most daylight between them.

Which is better for coding, Mistral Large 3 or Ministral 3 3B (Reasoning)?

Mistral Large 3 has the edge for coding in this comparison, averaging 41 versus 7.2. Inside this category, HumanEval is the benchmark that creates the most daylight between them.

Which is better for math, Mistral Large 3 or Ministral 3 3B (Reasoning)?

Mistral Large 3 has the edge for math in this comparison, averaging 77.3 versus 40.9. Inside this category, AIME 2023 is the benchmark that creates the most daylight between them.

Which is better for reasoning, Mistral Large 3 or Ministral 3 3B (Reasoning)?

Mistral Large 3 has the edge for reasoning in this comparison, averaging 70.6 versus 35.3. Inside this category, SimpleQA is the benchmark that creates the most daylight between them.

Which is better for agentic tasks, Mistral Large 3 or Ministral 3 3B (Reasoning)?

Mistral Large 3 has the edge for agentic tasks in this comparison, averaging 52.5 versus 34. Inside this category, BrowseComp is the benchmark that creates the most daylight between them.

Which is better for multimodal and grounded tasks, Mistral Large 3 or Ministral 3 3B (Reasoning)?

Mistral Large 3 has the edge for multimodal and grounded tasks in this comparison, averaging 75.5 versus 30.4. Inside this category, MMMU-Pro is the benchmark that creates the most daylight between them.

Which is better for instruction following, Mistral Large 3 or Ministral 3 3B (Reasoning)?

Mistral Large 3 has the edge for instruction following in this comparison, averaging 83 versus 68. Inside this category, IFEval is the benchmark that creates the most daylight between them.

Which is better for multilingual tasks, Mistral Large 3 or Ministral 3 3B (Reasoning)?

Mistral Large 3 has the edge for multilingual tasks in this comparison, averaging 78.8 versus 59.7. Inside this category, MGSM is the benchmark that creates the most daylight between them.

Last updated: March 12, 2026

Weekly LLM Benchmark Digest

Get notified when new models drop, benchmark scores change, or the leaderboard shifts. One email per week.

Free. No spam. Unsubscribe anytime. We only store derived location metadata for consent routing.